No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Systematic review of artificial intelligence tack in preventive orthopaedics: is the land coming soon?
Abstract
PurposeThis study aims to describe and assess the current stage of the artificial intelligence (AI) technology integration in preventive orthopaedics of the knee and hip joints.Materials and methodsThe study was conducted in strict compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. Literature databases were searched for articles describing the development and validation of AI models aimed at diagnosing knee or hip joint pathologies or predicting their development or course in patients. The quality of the included articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and QUADAS-AI tools.Results56 articles were found that meet all the inclusion criteria. We identified two problems that block the full integration of AI into the routine of an orthopaedic physician. The first of them is related to the insufficient amount, variety and quality of data for training, and validation and testing of AI models. The second problem is the rarity of rational evaluation of models, which is why their real quality cannot always be evaluated.Conclusion
The vastness and relevance of the studied topic are beyond doubt. Qualitative and optimally validated models exist in all four scopes considered. Additional optimization and confirmation of the models’ quality on various datasets are the last technical stumbling blocks for creating usable software and integrating them into the routine of an orthopaedic physician.
... For articles predating 2022 that by Kurmis et al. [8], which is a salient contribution in this regard including data sources examined up to November 2022 is recommended. Others covering the topic in depth are Korneev et al. [9] and Binvignat et al. [10] summarizing data up to mid 2021. Articles were not differentiated by AI type or specific degree of pathology. ...
... Attention to variations and subgroup analysis also appear to be very key to assisting to advance personalized intervention approaches. Korneev et al. [9] concluded that there are two problems in the interim in trying to identify preventive orthopedic approaches using AI. The first is related to the insufficient amount, variety and quality of data for training, and validation and testing of AI models. ...
Discusses artificial inteeligence approaches and Knee osteoarthritis and some likely implications and areas for future examination.
... However, as these models continue to develop, they have the potential to revolutionize the way we interact with computers and information [27,28]. Furthermore, insufficient data and its variety and quality are required for training, and validation and testing of AI models is crucial [29]. ...
This study analyses the performance and proficiency of the three Artificial Intelligence (AI) generative chatbots (ChatGPT-3.5, ChatGPT-4.0, Bard Google AI®) and in answering the Multiple Choice Questions (MCQs) of postgraduate (PG) level orthopaedic qualifying examinations.
A series of 120 mock Single Best Answer’ (SBA) MCQs with four possible options named A, B, C and D as answers on various musculoskeletal (MSK) conditions covering Trauma and Orthopaedic curricula were compiled. A standardised text prompt was used to generate and feed ChatGPT (both 3.5 and 4.0 versions) and Google Bard programs, which were then statistically analysed.
Significant differences were found between responses from Chat GPT 3.5 with Chat GPT 4.0 (Chi square = 27.2, P < 0.001) and on comparing both Chat GPT 3.5 (Chi square = 63.852, P < 0.001) with Chat GPT 4.0 (Chi square = 44.246, P < 0.001) with. Bard Google AI® had 100% efficiency and was significantly more efficient than both Chat GPT 3.5 with Chat GPT 4.0 (p < 0.0001).
The results demonstrate the variable potential of the different AI generative chatbots (Chat GPT 3.5, Chat GPT 4.0 and Bard Google) in their ability to answer the MCQ of PG-level orthopaedic qualifying examinations. Bard Google AI® has shown superior performance than both ChatGPT versions, underlining the potential of such large language processing models in processing and applying orthopaedic subspecialty knowledge at a PG level.
... This new tool QUADAS-AI 14 is an AI-specific extension of QUADAS-2 and QUADAS-C, includes four domains in the risk of bias and three domains in applicability concerns, which is more comprehensive and suitable for AI associated studies. Some studies [45][46][47] related to AI models have also employed this new tool. ...
Background
The gold standard to diagnose fatty liver is pathology. Recently, image-based artificial intelligence (AI) has been found to have high diagnostic performance. We systematically reviewed studies of image-based AI in the diagnosis of fatty liver.
Methods
We searched the Cochrane Library, Pubmed, Embase and assessed the quality of included studies by QUADAS-AI. The pooled sensitivity, specificity, negative likelihood ratio (NLR), positive likelihood ratio (PLR), and diagnostic odds ratio (DOR) were calculated using a random effects model. Summary receiver operating characteristic curves (SROC) were generated to identify the diagnostic accuracy of AI models.
Results
15 studies were selected in our meta-analysis. Pooled sensitivity and specificity were 92% (95% CI: 90–93%) and 94% (95% CI: 93–96%), PLR and NLR were 12.67 (95% CI: 7.65–20.98) and 0.09 (95% CI: 0.06–0.13), DOR was 182.36 (95% CI: 94.85-350.61). After subgroup analysis by AI algorithm (conventional machine learning/deep learning), region, reference (US, MRI or pathology), imaging techniques (MRI or US) and transfer learning, the model also demonstrated acceptable diagnostic efficacy.
Conclusion
AI has satisfactory performance in the diagnosis of fatty liver by medical imaging. The integration of AI into imaging devices may produce effective diagnostic tools, but more high-quality studies are needed for further evaluation.
... In addition, very few guiding studies currently pinpoint how predictors of surgical complications, inflammatory correlates, pain attributes and experiences, cognitive, behavioral and muscle influences, including the role of comorbid health conditions and hip joint shape among other factors determine the disease course with any certainty [35]. In addition, even among diagnostically themed publications that are most favored, along with surgical themes of study, Korneev, et al., identified two problems that block the full integration of AI into the routine of an orthopedic physician, including those who are involved in hip osteoarthritis care [36]. The first of these is related to the insufficient amount, variety and quality of data for training and validation and testing of AI models in almost any sphere. ...
Background: Hip joint osteoarthritis remains an incurable disabling health condition. Aim: To examine what trends exist in the realm of Artificial Intelligence [AI] applications to hip osteoarthritis. Methods: An in-depth literature review focusing on hip osteoarthritis and selected artificial intelligence association’s themes was conducted. Results: Artificial intelligence is being widely studied and applied in the realms of hip osteoarthritis diagnoses and surgical factors and approaches, but less so in the clinical, and deterministic spheres. Conclusion: Future expanded research efforts that integrate the features of the whole joint and person-environment factors and their association with favorable and unfavorable hip osteoarthritis outcomes are needed and are likely to prove promising and save immense human and service costs. Keywords: Arthroplasty; Artificial Intelligence; Deep Learning, Diagnosis; Hip Osteoarthritis; Machine Learning; Outcomes; Pathology; Prevention; Surgery
... This phenomenon can be explained by the exponential growth in computing power available to the largest AI training runs. In the literature, AI is classified in different ways as explained by Korneev et al. [21] and there is a certain degree of overlap among the different terms and definitions used. Some of the most notable and continuously evolving AI sub-domains are machine learning, artificial neural networks, computer ...
Although past studies and the performance of prior models have not been assessed, artificial intelligence models have shown great accuracy in distinguishing particular orthopedic implant types from imaging, which is an essential and time-consuming operation. To describe the breadth, approach, and effectiveness of artificial intelligence algorithms in categorizing orthopedic implant models, the authors carried out a comprehensive review. They used the search phrases “artificial intelligence,” “orthopedic,” “implant,” and “arthroplasty” to look at research published up to March 10, 2021 in PubMed, EMBASE, and the Cochrane Library. A modified version of the methodologic index for non-randomized studies was used to evaluate the studies. Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were among the results that were reported. Eleven of the 2689 records found during the search were used in the analysis. Between 2 and 27 implant models were considered.
Background
Trabecular bone texture (TBT) analysis has been identified as an imaging biomarker that provides information on trabecular bone changes due to knee osteoarthritis (KOA). In parallel with the improvement in medical imaging technologies, machine learning methods have received growing interest in the scientific osteoarthritis community to potentially provide clinicians with prognostic data from conventional knee X-ray datasets, in particular from the Osteoarthritis Initiative (OAI) and the Multicenter Osteoarthritis Study (MOST) cohorts.
Patients and methods
This study included 1888 patients from OAI and 683 patients from MOST cohorts. Radiographs were automatically segmented to determine 16 regions of interest. Patients with an early stage of OA risk, with Kellgren and Lawrence (KL) grade of 1 < KL < 4, were selected. The definition of OA progression was an increase in the OARSI medial joint space narrowing (mJSN) grades over 48 months in OAI and 60 months in MOST. The performance of the TBT-CNN model was evaluated and compared to well-known prediction models using logistic regression.
Results
The TBT-CNN model was predictive of the JSN progression with an area under the curve (AUC) up to 0.75 in OAI and 0.81 in MOST. The predictive ability of the TBT-CNN model was invariant with respect to the acquisition modality or image quality. The prediction models performed significantly better with estimated KL (KLprob) grades than those provided by radiologists. TBT-based models significantly outperformed KLprob-based models in MOST and provided similar performances in OAI. In addition, the combined model, when trained in one cohort, was able to predict OA progression in the other cohort.
Conclusion
The proposed combined model provides a good performance in the prediction of mJSN over 4 to 6 years in patients with relevant KOA. Furthermore, the current study presents an important contribution in showing that TBT-based OA prediction models can work with different databases.
Knee Osteoarthritis (ΚΟΑ) is a degenerative joint disease of the knee that results from the progressive loss of cartilage. Due to KOA's multifactorial nature and the poor understanding of its pathophysiology, there is a need for reliable tools that will reduce diagnostic errors made by clinicians. The existence of public databases has facilitated the advent of advanced analytics in KOA research however the heterogeneity of the available data along with the observed high feature dimensionality make this diagnosis task difficult. The objective of the present study is to provide a robust Feature Selection (FS) methodology that could: (i) handle the multidimensional nature of the available datasets and (ii) alleviate the defectiveness of existing feature selection techniques towards the identification of important risk factors which contribute to KOA diagnosis. For this aim, we used multidimensional data obtained from the Osteoarthritis Initiative database for individuals without or with KOA. The proposed fuzzy ensemble feature selection methodology aggregates the results of several FS algorithms (filter, wrapper and embedded ones) based on fuzzy logic. The effectiveness of the proposed methodology was evaluated using an extensive experimental setup that involved multiple competing FS algorithms and several well-known ML models. A 73.55% classification accuracy was achieved by the best performing model (Random Forest classifier) on a group of twenty-one selected risk factors. Explainability analysis was finally performed to quantify the impact of the selected features on the model's output thus enhancing our understanding of the rationale behind the decision-making mechanism of the best model.
Knee osteoarthritis (OA) is one of the most common musculoskeletal disorders. OA diagnosis is currently conducted by assessing symptoms and evaluating plain radiographs, but this process suffers from the subjectivity of doctors. In this study, we retrospectively compared five commonly used machine learning methods, especially the CNN network, to predict the real-world X-ray imaging data of knee joints from two different hospitals using Kellgren-Lawrence (K-L) grade of knee OA to help doctors choose proper auxiliary tools. Furthermore, we present attention maps of CNN to highlight the radiological features affecting the network decision. Such information makes the decision process transparent for practitioners, which builds better trust towards such automatic methods and, moreover, reduces the workload of clinicians, especially for remote areas without enough medical staff.
We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on complete 3D MRI scans. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data and how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences.
There is a growing interest in the application of artificial intelligence (AI) to orthopaedic surgery. This review aims to identify and characterise research in this field, in order to understand the extent, range and nature of this work, and act as springboard to stimulate future studies. A scoping review, a form of structured evidence synthesis, was conducted to summarise the use of AI in orthopaedics. A literature search (1946–2019) identified 222 studies eligible for inclusion. These studies were predominantly small and retrospective. There has been significant growth in the number of papers published in the last three years, mainly from the USA (37%). The majority of research used AI for image interpretation (45%) or as a clinical decision tool (25%). Spine (43%), knee (23%) and hip (14%) were the regions of the body most commonly studied. The application of artificial intelligence to orthopaedics is growing. However, the scope of its use so far remains limited, both in terms of its possible clinical applications, and the sub-specialty areas of the body which have been studied. A standardized method of reporting AI studies would allow direct assessment and comparison. Prospective studies are required to validate AI tools for clinical use.
We compared the prediction efficiency of the multiple-joint space width (JSW) and theminimum-JSW on knee osteoarthritis (KOA) severity and progression by using a deep learningapproach. A convolutional neural network (CNN) with ResU-Net architecture was developed forknee X-ray imaging segmentation and has attained a segmentation efficiency of 98.9% intersectionover union (IoU) on the distal femur and proximal tibia. Later, by leveraging the image segmentation,the minimum and multiple-JSWs in the tibiofemoral joint were estimated and then validated byradiologist measurements in the Osteoarthritis Initiative (OAI) dataset using Pearson correlationand Bland–Altman plots. The agreement between the CNN-based estimation and radiologist’smeasurement of minimum-JSWs reached 0.7801 (p< 0.0001). The estimated JSWs were deployedto predict the radiographic severity and progression of KOA defined by Kellgren-Lawrence (KL)grades using the XGBoost model. The 64-point multiple-JSWs achieved the best performance inpredicting KOA progression within 48 months, with the area-under-receiver operating characteristiccurve (AUC) of 0.621, outperforming the commonly used minimum-JSW with 0.554 AUC. Weprovided a fully automated radiographic assessment tool for KOA with comparable performance tothe radiologists and showed that the fine-grained measurement of multiple-JSWs yields superiorprediction performance for KOA over the minimum-JSW.
Background
The identification of patients with knee osteoarthritis (OA) likely to progress rapidly in terms of structure is critical to facilitate the development of disease-modifying drugs.
Methods
Using 9280 knee magnetic resonance (MR) images (3268 patients) from the Osteoarthritis Initiative (OAI) database , we implemented a deep learning method to predict, from MR images and clinical variables including body mass index (BMI), further cartilage degradation measured by joint space narrowing at 12 months.
Results
Using COR IW TSE images, our classification model achieved a ROC AUC score of 65%. On a similar task, trained radiologists obtained a ROC AUC score of 58.7% highlighting the difficulty of the classification task. Additional analyses conducted in parallel to predict pain grade evaluated by the WOMAC pain index achieved a ROC AUC score of 72%. Attention maps provided evidence for distinct specific areas as being relevant in those two predictive models, including the medial joint space for JSN progression and the intra-articular space for pain prediction.
Conclusions
This feasibility study demonstrates the interest of deep learning applied to OA, with a potential to support even trained radiologists in the challenging task of identifying patients with a high-risk of disease progression.
Background
Prevalence for knee osteoarthritis is rising in both Sweden and globally due to increased age and obesity in the population. This has subsequently led to an increasing demand for knee arthroplasties. Correct diagnosis and classification of a knee osteoarthritis (OA) are therefore of a great interest in following-up and planning for either conservative or operative management. Most orthopedic surgeons rely on standard weight bearing radiographs of the knee. Improving the reliability and reproducibility of these interpretations could thus be hugely beneficial. Recently, deep learning which is a form of artificial intelligence (AI), has been showing promising results in interpreting radiographic images. In this study, we aim to evaluate how well an AI can classify the severity of knee OA, using entire image series and not excluding common visual disturbances such as an implant, cast and non-degenerative pathologies.
Methods
We selected 6103 radiographic exams of the knee taken at Danderyd University Hospital between the years 2002-2016 and manually categorized them according to the Kellgren & Lawrence grading scale (KL). We then trained a convolutional neural network (CNN) of ResNet architecture using PyTorch. We evaluated the results against a test set of 300 exams that had been reviewed independently by two senior orthopedic surgeons who settled eventual interobserver disagreements through consensus sessions.
Results
The CNN yielded an overall AUC of more than 0.87 for all KL grades except KL grade 2, which yielded an AUC of 0.8 and a mean AUC of 0.92. When merging adjacent KL grades, all but one group showed near perfect results with AUC > 0.95 indicating excellent performance.
Conclusion
We have found that we could teach a CNN to correctly diagnose and classify the severity of knee OA using the KL grading system without cleaning the input data from major visual disturbances such as implants and other pathologies.
In the recent era, various diseases have severely affected the lifestyle of individuals, especially adults. Among these, bone diseases, including Knee Osteoarthritis (KOA), have a great impact on quality of life. KOA is a knee joint problem mainly produced due to decreased Articular Cartilage between femur and tibia bones, producing severe joint pain, effusion, joint movement constraints and gait anomalies. To address these issues, this study presents a novel KOA detection at early stages using deep learning-based feature extraction and classification. Firstly, the input X-ray images are preprocessed, and then the Region of Interest (ROI) is extracted through segmentation. Secondly, features are extracted from preprocessed X-ray images containing knee joint space width using hybrid feature descriptors such as Convolutional Neural Network (CNN) through Local Binary Patterns (LBP) and CNN using Histogram of oriented gradient (HOG). Low-level features are computed by HOG, while texture features are computed employing the LBP descriptor. Lastly, multi-class classifiers, that is, Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), are used for the classification of KOA according to the Kellgren–Lawrence (KL) system. The Kellgren–Lawrence system consists of Grade I, Grade II, Grade III, and Grade IV. Experimental evaluation is performed on various combinations of the proposed framework. The experimental results show that the HOG features descriptor provides approximately 97% accuracy for the early detection and classification of KOA for all four grades of KL.
Grading individual knee osteoarthritis (OA) features is a fine-grained knee OA severity assessment. Existing methods ignore following problems: (1) more accurately located knee joints benefit subsequent grades prediction; (2) they do not consider knee joints’ symmetry and semantic information, which help to improve grades prediction performance. To this end, we propose a SE-ResNext50-32x4d-based Siamese network with adaptive gated feature fusion method to simultaneously assess eight tasks. In our method, two cascaded small convolution neural networks are designed to locate more accurate knee joints. Detected knee joints are further cropped and split into left and right patches via their symmetry, which are fed into SE-ResNext50-32x4d-based Siamese network with shared weights, extracting more detailed knee features. The adaptive gated feature fusion method is used to capture richer semantic information for better feature representation here. Meanwhile, knee OA/non-knee OA classification task is added, helping extract richer features. We specially introduce a new evaluation metric (top±1 accuracy) aiming to measure model performance with ambiguous data labels. Our model is evaluated on two public datasets: OAI and MOST datasets, achieving the state-of-the-art results comparing to competing approaches. It has the potential to be a tool to assist clinical decision making.
Knee osteoarthritis (KOA) is an orthopedic disorder with a substantial impact on mobility and quality of life. An accurate assessment of the KOA levels is imperative in prioritizing meaningful patient care. Quantifying osteoarthritis features such as osteophytes and joint space narrowing (JSN) from low-resolution images (i.e., X-ray images) are mostly subjective. We implement an objective assessment and quantification of KOA to aid practitioners. In particular, we developed an interpretable ensemble of convolutional neural network (CNN) models consisting of three modules. First, we developed a scale-invariant and aspect ratio preserving model to localize Knee joints. Second, we created multiple instances of "hyperparameter optimized" CNN models with diversity and build an ensemble scoring system to assess the severity of KOA according to the Kellgren–Lawrence grading (KL) scale. Third, we provided visual explanations of the predictions by the ensemble model. We tested our models using a collection of 37,996 Knee joints from the Osteoarthritis Initiative (OAI) dataset. Our results show a superior (13–27%) performance improvement compared to the state-of-the-art methods.
Objective
To assess the ability of imaging-based deep learning to detect radiographic patellofemoral osteoarthritis (PFOA) from knee lateral view radiographs.
Design
Knee lateral view radiographs were extracted from The Multicenter Osteoarthritis Study (MOST) public use datasets (n = 18,436 knees). Patellar region-of-interest (ROI) was first automatically detected, and subsequently, end-to-end deep convolutional neural networks (CNNs) were trained and validated to detect the status of patellofemoral OA. Patellar ROI was detected using deep-learning-based object detection method. Atlas-guided visual assessment of PFOA status by expert readers provided in the MOST public use datasets was used as a classification outcome for the models. Performance of classification models was assessed using the area under the receiver operating characteristic curve (ROC AUC) and the average precision (AP) obtained from the precision-recall (PR) curve in the stratified 5-fold cross validation setting.
Results
Of the 18,436 knees, 3,425 (19%) had PFOA. AUC and AP for the reference model including age, sex, body mass index (BMI), the total Western Ontario and McMaster Universities Arthritis Index (WOMAC) score, and tibiofemoral Kellgren–Lawrence (KL) grade to detect PFOA were 0.806 and 0.478, respectively. The CNN model that used only image data significantly improved the classifier performance (ROC AUC= 0.958, AP= 0.862).
Conclusion
We present the first machine learning based automatic PFOA detection method. Furthermore, our deep learning based model trained on patella region from knee lateral view radiographs performs better at detecting PFOA than models based on patient characteristics and clinical assessments.
To study and explore the adoption value of magnetic resonance imaging (MRI) in the diagnosis of anterior cruciate ligament (ACL) injuries, a multimodal feature fusion model based on deep learning was proposed for MRI diagnosis. After the related performance of the proposed algorithm was evaluated, it was utilized in the diagnosis of knee joint injuries. Thirty patients with knee joint injuries who came to our hospital for treatment were selected, and all patients were diagnosed with MRI based on deep learning multimodal feature fusion model (MRI group) and arthroscopy (arthroscopy group). The results showed that deep learning-based MRI sagittal plane detection had a great advantage and a high accuracy of 96.28% in the prediction task of ACL tearing. The sensitivity, specificity, and accuracy of MRI in the diagnosis of ACL injury was 96.78%, 90.62%, and 92.17%, respectively, and there was no considerable difference in contrast to the results obtained through arthroscopy (P>0.05). The positive rate of acute ACL patients with bone contusion and medial collateral ligament injury was substantially superior to that of chronic injury. Moreover, the incidence of chronic injury ACL injury with meniscus tear and cartilage injury was notably higher than that of acute injury, with remarkable differences (P
The aim of the present study is to build a software implementation of a previous study and to diagnose discoid lateral menisci on knee joint radiograph images. A total of 160 images from normal individuals and patients who were diagnosed with discoid lateral menisci were included. Our software implementation includes two parts: preprocessing and measurement. In the first phase, the whole radiograph image was analyzed to obtain basic information about the patient. Machine learning was used to segment the knee joint from the original radiograph image. Image enhancement and denoising tools were used to strengthen the image and remove noise. In the second phase, edge detection was used to quantify important features in the image. A specific algorithm was designed to build a model of the knee joint and measure the parameters. Of the test images, 99.65% were segmented correctly. Furthermore, 97.5% of the tested images were segmented correctly and their parameters were measured successfully. There was no significant difference between manual and automatic measurements in the discoid (P=0.28) and control groups (P=0.15). The mean and standard deviations of the ratio of lateral joint space distance to the height of the lateral tibial spine were compared with the results of manual measurement. The software performed well on raw radiographs, showing a satisfying success rate and robustness. Thus, it is possible to diagnose discoid lateral menisci on radiographs with the help of radiograph-image-analyzing software (BM3D, etc.) and artificial intelligence-related tools (YOLOv3). The results of this study can help build a joint database that contains data from patients and thus can play a role in the diagnosis of discoid lateral menisci and other knee joint diseases in the future.
Objectives
Our aim was to assess the ability of semi-automatically extracted magnetic resonance imaging (MRI)–based radiomic features from tibial subchondral bone to distinguish between knees without and with osteoarthritis.
Methods
The right knees of 665 females from the population-based Rotterdam Study scanned with 1.5T MRI were analyzed. A fast imaging employing steady-state acquisition sequence was used for the quantitative bone analyses. Tibial bone was segmented using a method that combines multi-atlas and appearance models. Radiomic features related to the shape and texture were calculated from six volumes of interests (VOIs) in the proximal tibia. Machine learning–based Elastic Net models with 10-fold cross-validation were used to distinguish between knees without and with MRI Osteoarthritis Knee Score (MOAKS)–based tibiofemoral osteoarthritis. Performance of the covariate (age and body mass index), image features, and combined covariate + image features models were assessed using the area under the receiver operating characteristic curve (ROC AUC).
Results
Of 665 analyzed knees, 76 (11.4%) had osteoarthritis. An ROC AUC of 0.68 (95% confidence interval (CI): 0.60–0.75) was obtained using the covariate model. The image features model yielded an ROC AUC of 0.80 (CI: 0.73–0.87). The model that combined image features from all VOIs and covariates yielded an ROC AUC of 0.80 (CI: 0.73–0.87).
Conclusion
Our results suggest that radiomic features are useful imaging biomarkers of subchondral bone for the diagnosis of osteoarthritis. An advantage of assessing bone on MRI instead of on radiographs is that other tissues can be assessed simultaneously.
Key Points
• Subchondral bone plays a role in the osteoarthritis disease processes.
• MRI radiomics is a potential method for quantifying changes in subchondral bone.
• Semi-automatically extracted radiomic features of tibia differ between subjects without and with osteoarthritis.
Today, intelligent systems that offer artificial intelligence capabilities often rely on machine learning. Machine learning describes the capacity of systems to learn from problem-specific training data to automate the process of analytical model building and solve associated tasks. Deep learning is a machine learning concept based on artificial neural networks. For many applications, deep learning models outperform shallow machine learning models and traditional data analysis approaches. In this article, we summarize the fundamentals of machine learning and deep learning to generate a broader understanding of the methodical underpinning of current intelligent systems. In particular, we provide a conceptual distinction between relevant terms and concepts, explain the process of automated analytical model building through machine learning and deep learning, and discuss the challenges that arise when implementing such intelligent systems in the field of electronic markets and networked business. These naturally go beyond technological aspects and highlight issues in human-machine interaction and artificial intelligence servitization.
Background
Fractures around the knee joint are inherently complex in terms of treatment; complication rates are high, and they are difficult to diagnose on a plain radiograph. An automated way of classifying radiographic images could improve diagnostic accuracy and would enable production of uniformly classified records of fractures to be used in researching treatment strategies for different fracture types. Recently deep learning, a form of artificial intelligence (AI), has shown promising results for interpreting radiographs. In this study, we aim to evaluate how well an AI can classify knee fractures according to the detailed 2018 AO-OTA fracture classification system.
Methods
We selected 6003 radiograph exams taken at Danderyd University Hospital between the years 2002–2016, and manually categorized them according to the AO/OTA classification system and by custom classifiers. We then trained a ResNet-based neural network on this data. We evaluated the performance against a test set of 600 exams. Two senior orthopedic surgeons had reviewed these exams independently where we settled exams with disagreement through a consensus session.
Results
We captured a total of 49 nested fracture classes. Weighted mean AUC was 0.87 for proximal tibia fractures, 0.89 for patella fractures and 0.89 for distal femur fractures. Almost ¾ of AUC estimates were above 0.8, out of which more than half reached an AUC of 0.9 or above indicating excellent performance.
Conclusion
Our study shows that neural networks can be used not only for fracture identification but also for more detailed classification of fractures around the knee joint.
The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) statement, published in 2009, was designed to help systematic reviewers transparently report why the review was done, what the authors did, and what they found. Over the past decade, advances in systematic review methodology and terminology have necessitated an update to the guideline. The PRISMA 2020 statement replaces the 2009 statement and includes new reporting guidance that reflects advances in methods to identify, select, appraise, and synthesise studies. The structure and presentation of the items have been modified to facilitate implementation. In this article, we present the PRISMA 2020 27-item checklist, an expanded checklist that details reporting recommendations for each item, the PRISMA 2020 abstract checklist, and the revised flow diagrams for original and updated reviews.
The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) statement, published in 2009, was designed to help systematic reviewers transparently report why the review was done, what the authors did, and what they found. Over the past decade, advances in systematic review methodology and terminology have necessitated an update to the guideline. The PRISMA 2020 statement replaces the 2009 statement and includes new reporting guidance that reflects advances in methods to identify, select, appraise, and synthesise studies. The structure and presentation of the items have been modified to facilitate implementation. In this article, we present the PRISMA 2020 27-item checklist, an expanded checklist that details reporting recommendations for each item, the PRISMA 2020 abstract checklist, and the revised flow diagrams for original and updated reviews.
Aim
In osteoarthritis (OA) there is a need for automated screening systems for early detection of structural progressors. We built a comprehensive machine learning (ML) model that bridges major OA risk factors and serum levels of adipokines/related inflammatory factors at baseline for early prediction of at-risk knee OA patient structural progressors over time.
Methods
The patient- and gender-based model development used baseline serum levels of six adipokines, three related inflammatory factors and their ratios (36), as well as major OA risk factors [age and bone mass index (BMI)]. Subjects (677) were selected from the Osteoarthritis Initiative (OAI) progression subcohort. The probability values of being structural progressors (PVBSP) were generated using our previously published prediction model, including five baseline structural features of the knee, i.e. two X-rays and three magnetic resonance imaging variables. To identify the most important variables amongst the 47 studied in relation to PVBSP, we employed the ML feature classification methodology. Among five supervised ML algorithms, the support vector machine (SVM) demonstrated the best accuracy and use for gender-based classifiers development. Performance and sensitivity of the models were assessed. A reproducibility analysis was performed with clinical trial OA patients.
Results
Feature selections revealed that the combination of age, BMI, and the ratios CRP/MCP-1 and leptin/CRP are the most important variables in predicting OA structural progressors in both genders. Classification accuracies for both genders in the testing stage (OAI) were >80%, with the highest sensitivity of CRP/MCP-1. Reproducibility analysis showed an accuracy ⩾92%; the ratio CRP/MCP-1 demonstrated the highest sensitivity in women and leptin/CRP in men.
Conclusion
This is the first time that such a framework was built for predicting knee OA structural progressors. Using this automated ML patient- and gender-based model, early prediction of knee structural OA progression can be performed with high accuracy using only three baseline serum biomarkers and two risk factors.
Plain language summary
Machine learning model for early knee osteoarthritis structural progression Knee osteoarthritis is a well-known debilitating disease leading to reduced mobility and quality of life – the main causes of chronic invalidity. Disease evolution can be slow and span many years; however, for some individuals, the progression/evolution can be fast. Current treatments are only symptomatic and conventional diagnosis of osteoarthritis is not very effective in early identification of patients who will progress rapidly. To improve therapeutic approaches, we need a robust prediction model to stratify osteoarthritis patients at an early stage according to risk of joint structure disease progression. We hypothesize that a prediction model using a machine learning system would enable such an early identification of individuals for whom osteoarthritis knee structure will degrade rapidly. Data were from the Osteoarthritis Initiative, a National Institute of Health (United States) databank, and the robustness and generalizability of the developed model was further evaluated using osteoarthritis patients from an external cohort. Using the supervised machine learning system (support vector machine), we developed an automated patient- and gender-based model enabling an early clinical prognosis for individuals at high risk of structural progressive osteoarthritis. In brief, this model employed at baseline (when the subject sees a physician) easily obtained features consisting of the two main osteoarthritis risk factors, age and bone mass index (BMI), in addition to the serum levels of three molecules. Two of these molecules belong to a family of factors names adipokines and one to a related inflammatory factor. In brief, the model comprising a combination of age, BMI, and the ratios CRP/MCP-1 and leptin/CRP were found very robust for both genders, and the high accuracy persists when tested with an external cohort conferring the gender-based model generalizability. This study offers a new automated system for identifying early knee osteoarthritis structural progressors, which will significantly improve clinical prognosis with real time patient monitoring.
Prognostic models that aim to improve the prediction of clinical events, individualized treatment and decision-making are increasingly being developed and published. However, relatively few models are externally validated and validation by independent researchers is rare. External validation is necessary to determine a prediction model’s reproducibility and generalizability to new and different patients. Various methodological considerations are important when assessing or designing an external validation study. In this article, an overview is provided of these considerations, starting with what external validation is, what types of external validation can be distinguished and why such studies are a crucial step towards the clinical implementation of accurate prediction models. Statistical analyses and interpretation of external validation results are reviewed in an intuitive manner and considerations for selecting an appropriate existing prediction model and external validation population are discussed. This study enables clinicians and researchers to gain a deeper understanding of how to interpret model validation results and how to translate these results to their own patient population.
Knee osteoarthritis (OA) is the most common musculoskeletal disease in the world. In primary healthcare, knee OA is diagnosed using clinical examination and radiographic assessment. Osteoarthritis Research Society International (OARSI) atlas of OA radiographic features allows performing independent assessment of knee osteophytes, joint space narrowing and other knee features. This provides a fine-grained OA severity assessment of the knee, compared to the gold standard and most commonly used Kellgren–Lawrence (KL) composite score. In this study, we developed an automatic method to predict KL and OARSI grades from knee radiographs. Our method is based on Deep Learning and leverages an ensemble of residual networks with 50 layers. We used transfer learning from ImageNet with a fine-tuning on the Osteoarthritis Initiative (OAI) dataset. An independent testing of our model was performed on the Multicenter Osteoarthritis Study (MOST) dataset. Our method yielded Cohen’s kappa coefficients of 0.82 for KL-grade and 0.79, 0.84, 0.94, 0.83, 0.84 and 0.90 for femoral osteophytes, tibial osteophytes and joint space narrowing for lateral and medial compartments, respectively. Furthermore, our method yielded area under the ROC curve of 0.98 and average precision of 0.98 for detecting the presence of radiographic OA, which is better than the current state-of-the-art.
Aims
The lack of disease-modifying treatments for osteoarthritis (OA) is linked to a shortage of suitable biomarkers. This study combines multi-molecule synovial fluid analysis with machine learning to produce an accurate diagnostic biomarker model for end-stage knee OA (esOA).
Methods
Synovial fluid (SF) from patients with esOA, non-OA knee injury, and inflammatory knee arthritis were analyzed for 35 potential markers using immunoassays. Partial least square discriminant analysis (PLS-DA) was used to derive a biomarker model for cohort classification. The ability of the biomarker model to diagnose esOA was validated by identical wide-spectrum SF analysis of a test cohort of ten patients with esOA.
Results
PLS-DA produced a streamlined biomarker model with excellent sensitivity (95%), specificity (98.4%), and reliability (97.4%). The eight-biomarker model produced a fingerprint for esOA comprising type IIA procollagen N-terminal propeptide (PIIANP), tissue inhibitor of metalloproteinase (TIMP)-1, a disintegrin and metalloproteinase with thrombospondin motifs 4 (ADAMTS-4), monocyte chemoattractant protein (MCP)-1, interferon-γ-inducible protein-10 (IP-10), and transforming growth factor (TGF)-β3. Receiver operating characteristic (ROC) analysis demonstrated excellent discriminatory accuracy: area under the curve (AUC) being 0.970 for esOA, 0.957 for knee injury, and 1 for inflammatory arthritis. All ten validation test patients were classified correctly as esOA (accuracy 100%; reliability 100%) by the biomarker model.
Conclusion
SF analysis coupled with machine learning produced a partially validated biomarker model with cohort-specific fingerprints that accurately and reliably discriminated esOA from knee injury and inflammatory arthritis with almost 100% efficacy. The presented findings and approach represent a new biomarker concept and potential diagnostic tool to stage disease in therapy trials and monitor the efficacy of such interventions. Cite this article: Bone Joint Res 2020;9(9):623–632.
Knee Osteoarthritis (OA) is a common musculoskeletal disorder in the United States. When diagnosed at early stages, lifestyle interventions such as exercise and weight loss can slow OA progression, but at later stages, only an invasive option is available: total knee replacement (TKR). Though a generally successful procedure, only 2/3 of patients who undergo the procedure report their knees feeling “normal” post-operation, and complications can arise that require revision. This necessitates a model to identify a population at higher risk of TKR, particularly at less advanced stages of OA, such that appropriate treatments can be implemented that slow OA progression and delay TKR. Here, we present a deep learning pipeline that leverages MRI images and clinical and demographic information to predict TKR with AUC 0.834 ± 0.036 (p < 0.05). Most notably, the pipeline predicts TKR with AUC 0.943 ± 0.057 (p < 0.05) for patients without OA. Furthermore, we develop occlusion maps for case-control pairs in test data and compare regions used by the model in both, thereby identifying TKR imaging biomarkers. As such, this work takes strides towards a pipeline with clinical utility, and the biomarkers identified further our understanding of OA progression and eventual TKR onset.
Artificial intelligence is emerging as a persuasive tool in the field of medical science. This research work also primarily focuses on the development of a tool to automate the diagnosis of inflammatory diseases of the knee joint. The tool will also assist the physicians and medical practitioners for diagnosis. The diseases considered for this research under inflammatory category are osteoarthritis, rheumatoid arthritis and osteonecrosis. A five-layer adaptive neuro-fuzzy (ANFIS) architecture was used to model the system. The ANFIS system works by mapping input parameters to the input membership functions, input membership functions are mapped to the rules generated by the ANFIS model which are further mapped to the output membership function. A comparative performance analysis of fuzzy system and ANFIS system is also done and results generated shows that the ANFIS system outperformed fuzzy system in terms of testing accuracy, sensitivity and specificity.
Knee osteoarthritis (OA) is the most common musculoskeletal disease without a cure, and current treatment options are limited to symptomatic relief. Prediction of OA progression is a very challenging and timely issue, and it could, if resolved, accelerate the disease modifying drug development and ultimately help to prevent millions of total joint replacement surgeries performed annually. Here, we present a multi-modal machine learning-based OA progression prediction model that utilises raw radiographic data, clinical examination results and previous medical history of the patient. We validated this approach on an independent test set of 3,918 knee images from 2,129 subjects. Our method yielded area under the ROC curve (AUC) of 0.79 (0.78–0.81) and Average Precision (AP) of 0.68 (0.66–0.70). In contrast, a reference approach, based on logistic regression, yielded AUC of 0.75 (0.74–0.77) and AP of 0.62 (0.60–0.64). The proposed method could significantly improve the subject selection process for OA drug-development trials and help the development of personalised therapeutic plans.
Background A multitask deep learning model might be useful in large epidemiologic studies wherein detailed structural assessment of osteoarthritis still relies on expert radiologists' readings. The potential of such a model in clinical routine should be investigated. Purpose To develop a multitask deep learning model for grading radiographic hip osteoarthritis features on radiographs and compare its performance to that of attending-level radiologists. Materials and Methods This retrospective study analyzed hip joints seen on weight-bearing anterior-posterior pelvic radiographs from participants in the Osteoarthritis Initiative (OAI). Participants were recruited from February 2004 to May 2006 for baseline measurements, and follow-up was performed 48 months later. Femoral osteophytes (FOs), acetabular osteophytes (AOs), and joint-space narrowing (JSN) were graded as absent, mild, moderate, or severe according to the Osteoarthritis Research Society International atlas. Subchondral sclerosis and subchondral cysts were graded as present or absent. The participants were split at 80% (n = 3494), 10% (n = 437), and 10% (n = 437) by using split-sample validation into training, validation, and testing sets, respectively. The multitask neural network was based on DenseNet-161, a shared convolutional features extractor trained with multitask loss function. Model performance was evaluated in the internal test set from the OAI and in an external test set by using temporal and geographic validation consisting of routine clinical radiographs. Results A total of 4368 participants (mean age, 61.0 years ± 9.2 [standard deviation]; 2538 women) were evaluated (15 364 hip joints on 7738 weight-bearing anterior-posterior pelvic radiographs). The accuracy of the model for assessing these five features was 86.7% (1333 of 1538) for FOs, 69.9% (1075 of 1538) for AOs, 81.7% (1257 of 1538) for JSN, 95.8% (1473 of 1538) for subchondral sclerosis, and 97.6% (1501 of 1538) for subchondral cysts in the internal test set, and 82.7% (86 of 104) for FOS, 65.4% (68 of 104) for AOs, 80.8% (84 of 104) for JSN, 88.5% (92 of 104) for subchondral sclerosis, and 91.3% (95 of 104) for subchondral cysts in the external test set. Conclusion A multitask deep learning model is a feasible approach to reliably assess radiographic features of hip osteoarthritis. © RSNA, 2020 Online supplemental material is available for this article.
Purpose
The purpose of this study was to create a predictive model utilizing baseline demographic and radiographic characteristics for the likelihood that a patient with subchondral insufficiency fracture of the knee will progress to knee arthroplasty with emphasis on clinical interpretability and usability.
Methods
A retrospective review of baseline and final radiographs in addition to MRIs were reviewed for evaluation of insufficiency fractures and associated injuries. Patient and radiographic factors were used in building predictive models for progression to arthroplasty with Train: Validation: Test subsets. Multiple models were compared with emphasis on clinical utility.
Results
Total of 249 patients with a mean age of 64.6 (SD 10.5) years were included. Knee arthroplasty rate was 27% at mean of 4 years of follow-up. Lasso Regression was non-inferior to other models and was chosen for ease of interpretability. In order of importance, predictors for progression to arthroplasty included lateral meniscus extrusion, Kellgren–Lawrence Grade 4, SIFK on MFC, lateral meniscus root tear, and medial meniscus extrusion. The final SIFK Score stratified patients into low-, medium-, and high-risk categories with arthroplasty rates of 8.8%, 40.4%, and 78.9% (p < 0.001) and an area under the curve of 82.5%.
Conclusion
In this validated model, lateral meniscus extrusion, K-L Grade 4, SIFK on MFC, lateral meniscus root tear, and medial meniscus extrusion were the most important factors in predicting progression to arthroplasty (in that order). This model assists in patient treatment and counseling in providing prognostic information based on patient-specific risk factors by classifying them into a low-, medium-, and high-risk categories. This model can be used both by medical professionals treating musculoskeletal injuries in guiding patient decision making.
Level of evidence
Level III.
The growth of the mobile Internet, smartphones and social networks has brought in huge amounts of picture information, and traditional manual identification is not able to meet the demand well enough. Therefore, the automatical image recognition [1] has been proposed which can help us recognize the image efficiently and get the corresponding information. Although traditional machine learning methods [2] have already been widely used in the field of image recognition, most of these methods are designed to handle one-dimensional vector information. Thus, we should first stretch image matrix to one-dimensional vector or extract features from images to employ traditional image recognition methods, which would lose the adjacent information in images and miss some important features. With the development of computer technology, deep learning [3] is gradually applied to the field of image recognition. It can deal with two-dimensional image data naturally and extract features automatically. Compared with the traditional machine learning methods, deep learning is popular for its good learning ability and low generalization error. In this paper, we compare the differences between SVM [4] and deep learning on image recognition, with an application to handwritten digital images recognition. The results show that the deep learning method is more accurate and more stable in image recognition.
Objective:
To design an automated workflow for hip radiographs focused on joint shape and tests its prognostic value for future hip osteoarthritis.
Design:
We used baseline and eight-year follow-up data from 1002 participants of the CHECK-study. The primary outcome was definite radiographic hip osteoarthritis (rHOA) (Kellgren-Lawrence grade ≥2 or joint replacement) at eight-year follow-up. We designed a method to automatically segment the hip joint from radiographs. Subsequently, we applied machine learning algorithms (elastic net with automated parameter optimization) to provide the Shape-Score, a single value describing the risk for future rHOA based solely on joint shape. We built and internally validated prediction models using baseline demographics, physical examination, and radiologists scores and tested the added prognostic value of the Shape-Score using Area-Under-the-Curve (AUC). Missing data was imputed by multiple imputation by chained equations. Only hips with pain in the corresponding leg were included.
Results:
84% were female, mean age was 56 (±5.1) years, mean BMI 26.3 (±4.2). Of 1044 hips with pain at baseline and complete follow-up, 143 showed radiographic osteoarthritis and 42 were replaced. 91.5% of the hips had follow-up data available. The Shape-Score was a significant predictor of rHOA (odds ratio per decimal increase 5.21, 95%-CI (3.74 - 7.24)). The prediction model using demographics, physical examination, and radiologists scores demonstrated an AUC of 0.795, 95%-CI (0.757 - 0.834). After addition of the Shape-Score the AUC rose to 0.864, 95%-CI (0.833 - 0.895).
Conclusions:
Our Shape-Score, automatically derived from radiographs using a novel machine learning workflow, may strongly improve risk prediction in hip osteoarthritis.
Purpose:
We developed a tool for locating and grading knee osteoarthritis (OA) from digital X-ray images and illustrate the possibility of deep learning techniques to predict knee OA as per the Kellgren-Lawrence (KL) grading system. The purpose of the project is to see how effectively an artificial intelligence (AI)-based deep learning approach can locate and diagnose the severity of knee OA in digital X-ray images.
Methods:
Selection criteria: Patients above 50 years old with OA symptoms (knee joint pain, stiffness, crepitus, and functional limitations) were included in the study. Medical experts excluded patients with post-surgical evaluation, trauma, and infection from the study. We used 3172 Anterior-posterior view knee joint digital X-ray images. We have trained the Faster RCNN architecture to locate the knee joint space width (JSW) region in digital X-ray images and we incorporate ResNet-50 with transfer learning to extract the features. We have used another pre-trained network (AlexNet with transfer learning) for the classification of knee OA severity. We trained the region proposal network (RPN) using manual extract knee area as the ground truth image and the medical experts graded the knee joint digital X-ray images based on the Kellgren-Lawrence score. An X-ray image is an input for the final model, and the output is a Kellgren-Lawrence grading value.
Results:
The proposed model identified the minimal knee JSW area with a maximum accuracy of 98.516%, and the overall knee OA severity classification accuracy was 98.90%.
Conclusions:
Today numerous diagnostic methods are available, but tools are not transparent and automated analysis of OA remains a problem. The performance of the proposed model increases while fine-tuning the network and it is higher than the existing works. We will extend this work to grade OA in MRI data in the future.
Objective
To develop a machine learning-based prediction model for incident radiographic osteoarthritis (OA) of the knee over 8 years using MRI-based cartilage biochemical composition and knee joint structure, demographics, and clinical predictors including muscle strength and symptoms.
Design
Individuals (n=1044) with baseline Kellgren Lawrence (KL) grade 0-1 in the right knee from the Osteoarthritis Initiative database were analyzed. 3T MRI at baseline was used to quantify knee cartilage T2, and Whole-Organ Magnetic Resonance Imaging Scores (WORMS) were obtained for cartilage, meniscus, and bone marrow. The outcome was set as true if a subject developed KL grade 2-4 OA in the right knee over 8 years (n=183) and false if the subject remained at KL 0-1 over 8 years (n=861). We developed and compared three models: Model 1: 112 predictors based on OA risk factors; Model 2: top ten predictors based on feature importance score from Model 1 and clinical relevance; Model 3: Model 2 without the imaging predictors. We compared the models using the area under the R OC curve derived from hold-out data.
Results
The 10-predictor model (Model 2, that includes cartilage and meniscus WORMS scores and cartilage T2) had a slightly lower AUC (0.772) compared to the model with 112 predictors (Model 1: AUC=0.792, p=0.739); and had a significantly higher AUC compared to the model without MR imaging predictors (Model 3, AUC=0.669, p=0.011).
Conclusions
A 10-predictor model including MRI parameters coupled with demographics, symptoms, muscle, and physical activity scores provides good prediction of incident radiographic OA over 8 years.
Purpose
We used convolutional neural network (CNN) technology to improve the accuracy of diagnosis of knee meniscus injury and shorten the diagnosis time.
Method
We propose a meniscus detection method based on Fusion of CNN1 and CNN2 (CNNf), which uses Magnetic Resonance Imaging (MRI) and Computer tomography (CT) to compare the diagnosis results, verifies the proposed method through 2460 images collected from 205 patients in the hospital. We used accuracy, sensitivity, specificity, receiver operating characteristics (ROC), and damage total rate to evaluate performance.
Results
The accuracy of our model was 93.86%, the sensitivity was 91.35%, the specificity was 94.65%, and the area under the receiver operating characteristic curve was 96.78%. The total damage rate of MRI is 91.57%, which is far greater than the total damage rate of CT diagnosis of 80.13%.
Conclusion
CNNf-based MRI technology of knee meniscus injury has high practical value in clinical practice. It can effectively improve the accuracy of diagnosis and reduce the rate of misdiagnosis.
Objectives
To utilise machine learning, unsupervised clustering and multivariate modelling in order to predict severe early joint space narrowing (JSN) from anatomical hip parameters while identifying factors related to joint space width (JSW) in dysplastic and non-dysplastic hips.MethodsA total of 507 hip CT examinations of patients 20–55 years old were retrospectively examined, and JSW, center-edge (CE) angle, alpha angle, anterior acetabular sector angle (AASA), and neck-shaft angle (NSA) were recorded. Dysplasia and severe JSN were defined with CE angle < 25o and JSW< 2 mm, respectively. A random forest classifier was developed to predict severe JSN based on anatomical and demographical data. Multivariate linear regression and two-step unsupervised clustering were performed to identify factors linked to JSW.ResultsIn dysplastic hips, lateral or anterior undercoverage alone was not correlated to JSN. AASA (p < 0.005) and CE angle (p < 0.032) were the only factors significantly correlated with JSN in dysplastic hips. In non-dysplastic hips, JSW was inversely correlated to CE angle, AASA, and age and positively correlated to NSA (p < 0.001). A random forest classifier predicted severe JSN (AUC 69.9%, 95%CI 47.9–91.8%). TwoStep cluster modelling identified two distinct patient clusters one with low and one with normal JSW and different anatomical characteristics.Conclusion
Machine learning predicted severe JSN and identified population characteristics related to normal and abnormal joint space width. Dysplasia in one plane was found to be insufficient to cause JSN, highlighting the need for hip anatomy assessment on multiple planes.Key Points
• Neither anterior nor lateral acetabular dysplasia was sufficient to independently reduce joint space width in a multivariate linear regression model of dysplastic hips.
• A random forest classifier was developed based on measurements and demographic parameters from 507 hip joints, achieving an area under the curve of 69.9% in the external validation set, in predicting severe joint space narrowing based on anatomical hip parameters and age.
• Unsupervised TwoStep cluster analysis revealed two distinct population groups, one with low and one with normal joint space width, characterised by differences in hip morphology
Objective
To develop and evaluate deep learning (DL) risk assessment models for predicting pain progression in subjects with or at risk of knee osteoarthritis (OA).Materials and methodsThe incidence and progression cohorts of the Osteoarthritis Initiative, a multi-center longitudinal study involving 9348 knees in 4674 subjects with or at risk of knee OA that began in 2004 and is ongoing, were used to conduct this retrospective analysis. A subset of knees without and with pain progression (defined as a 9-point or greater increase in pain score between baseline and two or more follow-up time points over the first 48 months) was randomly stratified into training (4200 knees with a mean age of 61.0 years and 60% female) and hold-out testing (500 knees with a mean age of 60.8 years and 60% female) datasets. A DL model was developed to predict pain progression using baseline knee radiographs. An artificial neural network was used to develop a traditional risk assessment model to predict pain progression using demographic, clinical, and radiographic risk factors. A combined model was developed to combine demographic, clinical, and radiographic risk factors with DL analysis of baseline knee radiographs. Area under the curve (AUC) analysis was performed using the hold-out testing dataset to evaluate model performance.ResultsThe traditional model had an AUC of 0.692 (66.9% sensitivity and 64.1% specificity). The DL model had an AUC of 0.770 (76.7% sensitivity and 70.5% specificity), which was significantly higher (p < 0.001) than the traditional model. The combined model had an AUC of 0.807 (72.3% sensitivity and 80.9% specificity), which was significantly higher (p < 0.05) than the traditional and DL models.ConclusionsDL models using baseline knee radiographs had higher diagnostic performance for predicting pain progression than traditional models using demographic, clinical, and radiographic risk factors.
A fully-automated deep learning algorithm matched performance of radiologists in assessment of knee osteoarthritis severity in radiographs using the Kellgren-Lawrence grading system.
Purpose
To develop an automated deep learning-based algorithm that jointly uses Posterior-Anterior (PA) and Lateral (LAT) views of knee radiographs to assess knee osteoarthritis severity according to the Kellgren-Lawrence grading system.
Materials and Methods
We used a dataset of 9739 exams from 2802 patients from Multicenter Osteoarthritis Study (MOST). The dataset was divided into a training set of 2040 patients, a validation set of 259 patients and a test set of 503 patients. A novel deep learning-based method was utilized for assessment of knee OA in two steps: (1) localization of knee joints in the images, (2) classification according to the KL grading system. Our method used both PA and LAT views as the input to the model. The scores generated by the algorithm were compared to the grades provided in the MOST dataset for the entire test set as well as grades provided by 5 radiologists at our institution for a subset of the test set.
Results
The model obtained a multi-class accuracy of 71.90% on the entire test set when compared to the ratings provided in the MOST dataset. The quadratic weighted Kappa coefficient for this set was 0.9066. The average quadratic weighted Kappa between all pairs of radiologists from our institution who took a part of study was 0.748. The average quadratic-weighted Kappa between the algorithm and the radiologists at our institution was 0.769.
Conclusion
The proposed model performed demonstrated equivalency of KL classification to MSK radiologists, but clearly superior reproducibility. Our model also agreed with radiologists at our institution to the same extent as the radiologists with each other. The algorithm could be used to provide reproducible assessment of knee osteoarthritis severity.
Purpose
Evaluation of a deep learning approach for the detection of meniscal tears and their characterization (presence/absence of migrated meniscal fragment).
Methods
A large annotated adult knee MRI database was built combining medical expertise of radiologists and data scientists’ tools. Coronal and sagittal proton density fat suppressed-weighted images of 11,353 knee MRI examinations (10,401 individual patients) paired with their standardized structured reports were retrospectively collected. After database curation, deep learning models were trained and validated on a subset of 8058 examinations. Algorithm performance was evaluated on a test set of 299 examinations reviewed by 5 musculoskeletal specialists and compared to general radiologists’ reports. External validation was performed using the publicly available MRNet database. Receiver Operating Characteristic (ROC) curves results and Area Under the Curve (AUC) values were obtained on internal and external databases.
Results
A combined architecture of meniscal localization and lesion classification 3D convolutional neural networks reached AUC values of 0.93 (95% CI 0.82, 0.95) for medial and 0.84 (95% CI 0.78, 0.89) for lateral meniscal tear detection, and 0.91 (95% CI 0.87, 0.94) for medial and 0.95 (95% CI 0.92, 0.97) for lateral meniscal tear migration detection. External validation of the combined medial and lateral meniscal tear detection models resulted in an AUC of 0.83 (95% CI 0.75, 0.90) without further training and 0.89 (95% CI 0.82, 0.95) with fine tuning.
Conclusion
Our deep learning algorithm demonstrated high performance in knee menisci lesion detection and characterization, validated on an external database.
Background:
MRI is the most commonly used imaging method for diagnosing anterior cruciate ligament (ACL) injuries. However, the interpretation of knee MRI is time-intensive and depends on the clinical experience of the reader. An automated detection system based on a deep-learning algorithm may improve interpretation time and reliability.
Purpose:
To determine the feasibility of using a deep learning approach to detect ACL injuries within the knee joint on MRI.
Study type:
Retrospective.
Population:
In all, 163 subjects with an ACL tear and 245 subjects with an intact ACL. There were 285, 81, and 42 volumes for training, validation, and test sets, respectively.
Field strength/sequence:
2D sagittal proton density-weighted spectral attenuated inversion recovery sequences at 1.5T and 3.0T.
Assessment:
Based on the architecture of 3D DenseNet, we constructed a classification convolutional neural network. We tested this deep learning approach with different inputs and two other algorithms, including VGG16 and ResNet. Then we had both inexperienced radiologists and senior radiologists read the MR images.
Statistical tests:
Using arthroscopic results as the reference standard, the performance of three different inputs and three different algorithms, the residents and senior radiologists assessed the classification accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC).
Results:
The accuracy, sensitivity, specificity, PPV, and NPV of our customized 3D deep learning architecture was 0.957, 0.976, 0.944, 0.940, and 0.976, respectively. The average AUCs were 0.946, 0.859, 0.960 for ResNet, VGG16, and our proposed network, respectively. The diagnostic accuracy of our model, residents, and senior radiologists was 0.957, 0.814, and 0.899, respectively.
Data conclusion:
Our study demonstrated the feasibility of using an automated deep-learning-based detection system to evaluate ACL injury.
Level of evidence:
3 TECHNICAL EFFICACY STAGE: 1 J. MAGN. RESON. IMAGING 2020;52:1745-1752.
Background The methods for assessing knee osteoarthritis (OA) do not provide enough comprehensive information to make robust and accurate outcome predictions. Purpose To develop a deep learning (DL) prediction model for risk of OA progression by using knee radiographs in patients who underwent total knee replacement (TKR) and matched control patients who did not undergo TKR. Materials and Methods In this retrospective analysis that used data from the OA Initiative, a DL model on knee radiographs was developed to predict both the likelihood of a patient undergoing TKR within 9 years and Kellgren-Lawrence (KL) grade. Study participants included a case-control matched subcohort between 45 and 79 years. Patients were matched to control patients according to age, sex, ethnicity, and body mass index. The proposed model used a transfer learning approach based on the ResNet34 architecture with sevenfold nested cross-validation. Receiver operating characteristic curve analysis and conditional logistic regression assessed model performance for predicting probability and risk of TKR compared with clinical observations and two binary outcome prediction models on the basis of radiographic readings: KL grade and OA Research Society International (OARSI) grade. Results Evaluated were 728 participants including 324 patients (mean age, 64 years ± 8 [standard deviation]; 222 women) and 324 control patients (mean age, 64 years ± 8; 222 women). The prediction model based on DL achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (95% confidence interval [CI]: 0.85, 0.90), outperforming a baseline prediction model by using KL grade with an AUC of 0.74 (95% CI: 0.71, 0.77; P < .001). The risk for TKR increased with probability that a person will undergo TKR from the DL model (odds ratio [OR], 7.7; 95% CI: 2.3, 25; P < .001), KL grade (OR, 1.92; 95% CI: 1.17, 3.13; P = .009), and OARSI grade (OR, 1.20; 95% CI: 0.41, 3.50; P = .73). Conclusion The proposed deep learning model better predicted risk of total knee replacement in osteoarthritis than did binary outcome models by using standard grading systems. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Richardson in this issue.
Artificial intelligence (AI) was first described in 1950; however, several limitations in early models prevented widespread acceptance and application to medicine. In the early 2000s, many of these limitations were overcome by the advent of deep learning. Now AI systems are capable of analyzing complex algorithms and self-learning, we enter a new age in medicine where AI can be applied to clinical practice through risk assessment models, improving diagnostic accuracy and improving workflow efficiency. This article presents a brief historical perspective on the evolution of AI over the last several decades and the introduction and development of AI in medicine in recent years. A brief summary of the major applications of AI in gastroenterology and endoscopy are also presented, which will be reviewed in further detail by several other articles in this issue of GIE.
Objective:
To develop and evaluate deep learning (DL) risk assessment models for predicting the progression of radiographic medial joint space loss using baseline knee X-rays.
Methods:
Knees from the Osteoarthritis Initiative without and with progression of radiographic joint space loss (defined as > 0.7mm decrease in medial joint space width measurement between baseline and 48-month follow-up X-rays) were randomly stratified into training (1400 knees) and hold-out testing (400 knees) datasets. A DL network was trained to predict the progression of radiographic joint space loss using the baseline knee X-rays. An artificial neural network was used to develop a traditional model for predicting progression utilizing demographic and radiographic risk factors. A combined joint training model was developed using a DL network to extract information from baseline knee X-rays as a feature vector, which was further concatenated with the risk factor data vector. Area under the curve (AUC) analysis was performed using the hold-out test dataset to evaluate model performance.
Results:
The traditional model had an AUC of 0.660 (61.5% sensitivity and 64.0% specificity) for predicting progression. The DL model had an AUC of 0.799 (78.0% sensitivity and 75.5% specificity), which was significantly higher (p<0.001) than the traditional model. The combined model had an AUC of 0.863 (80.5% sensitivity and specificity), which was significantly higher than the DL (p=0.015) and traditional (P<0.001) models.
Conclusion:
DL models using baseline knee X-rays had higher diagnostic performance for predicting the progression of radiographic joint space loss than the traditional model using demographic and radiographic risk factors.
Purpose:
Knee osteoarthritis (OA) is a common disease that impairs knee function and causes pain. Radiologists usually review knee X-ray images and grade the severity of the impairments according to the Kellgren-Lawrence grading scheme. However, this approach becomes inefficient in hospitals with high throughput as it is time-consuming, tedious and also subjective. This paper introduces a model for automatic diagnosis of knee OA based on an end-to-end deep learning method.
Method:
In order to process the input images with location and classification simultaneously, we use Faster R-CNN as baseline, which consists of region proposal network (RPN) and Fast R-CNN. The RPN is trained to generate region proposals, which contain knee joint and then be used by Fast R-CNN for classification. Due to the localized classification via CNNs, the useless information in X-ray images can be filtered and we can extract clinically relevant features. For the further improvement in the model's performance, we use a novel loss function whose weighting scheme allows us to address the class imbalance. Besides, larger anchors are used to overcome the problem that anchors don't match the object when increasing the input size of X-ray images.
Result:
The performance of the proposed model is thoroughly assessed using various measures. The results show that our adjusted model outperforms the Faster R-CNN, achieving a mean average precision nearly 0.82 with a sensitivity above 78% and a specificity above 94%. It takes 0.33 s to test each image, which achieves a better trade-off between accuracy and speed.
Conclusion:
The proposed end-to-end fully automatic model which is computationally efficient has the potential to achieve the real automatic diagnosis of knee OA and be used as computer-aided diagnosis tools in clinical applications.
Nowadays, deep learning is a current and a stimulating field of machine learning. Deep learning is the most effective, supervised, time and cost efficient machine learning approach. Deep learning is not a restricted learning approach, but it abides
various procedures and topographies which can be applied to an immense speculum of complicated problems. The technique
learns the illustrative and differential features in a very stratified way. Deep learning methods have made a significant breakthrough with appreciable performance in a wide variety of applications with useful security tools. It is considered to be the
best choice for discovering complex architecture in high-dimensional data by employing back propagation algorithm. As
deep learning has made significant advancements and tremendous performance in numerous applications, the widely used
domains of deep learning are business, science and government which further includes adaptive testing, biological image
classification, computer vision, cancer detection, natural language processing, object detection, face recognition, handwriting recognition, speech recognition, stock market analysis, smart city and many more. This paper focuses on the concepts
of deep learning, its basic and advanced architectures, techniques, motivational aspects, characteristics and the limitations.
The paper also presents the major differences between the deep learning, classical machine learning and conventional learning approaches and the major challenges ahead. The main intention of this paper is to explore and present chronologically,
a comprehensive survey of the major applications of deep learning covering variety of areas, study of the techniques and
architectures used and further the contribution of that respective application in the real world. Finally, the paper ends with
the conclusion and future aspects.
Knee osteoarthritis (OA) is one major cause of activity limitation and physical disability in older adults. Early detection and intervention can help slow down the OA degeneration. Physicians' grading based on visual inspection is subjective, varied across interpreters, and highly relied on their experience. In this paper, we successively apply two deep convolutional neural networks (CNN) to automatically measure the knee OA severity, as assessed by the Kellgren-Lawrence (KL) grading system. Firstly, considering the size of knee joints distributed in X-ray images with small variability, we detect knee joints using a customized one-stage YOLOv2 network. Secondly, we fine-tune the most popular CNN models, including variants of ResNet, VGG, and DenseNet as well as InceptionV3, to classify the detected knee joint images with a novel adjustable ordinal loss. To be specific, motivated by the ordinal nature of the knee KL grading task, we assign higher penalty to misclassification with larger distance between the predicted KL grade and the real KL grade. The baseline X-ray images from the Osteoarthritis Initiative (OAI) dataset are used for evaluation. On the knee joint detection, we achieve mean Jaccard index of 0.858 and recall of 92.2% under the Jaccard index threshold of 0.75. On the knee KL grading task, the fine-tuned VGG-19 model with the proposed ordinal loss obtains the best classification accuracy of 69.7% and mean absolute error (MAE) of 0.344. Both knee joint detection and knee KL grading achieve state-of-the-art performance. The code, dataset, and models are released at https://github.com/PingjunChen/KneeAnalysis.
Nowadays, deep learning is a current and a stimulating field of machine learning. Deep learning is the most effective, supervised, time and cost efficient machine learning approach. Deep learning is not a restricted learning approach, but it abides various procedures and topographies which can be applied to an immense speculum of complicated problems. The technique learns the illustrative and differential features in a very stratified way. Deep learning methods have made a significant breakthrough with appreciable performance in a wide variety of applications with useful security tools. It is considered to be the best choice for discovering complex architecture in high-dimensional data by employing back propagation algorithm. As deep learning has made significant advancements and tremendous performance in numerous applications, the widely used domains of deep learning are business, science and government which further includes adaptive testing, biological image classification, computer vision, cancer detection, natural language processing, object detection, face recognition, handwriting recognition, speech recognition, stock market analysis, smart city and many more. This paper focuses on the concepts of deep learning, its basic and advanced architectures, techniques, motivational aspects, characteristics and the limitations. The paper also presents the major differences between the deep learning, classical machine learning and conventional learning approaches and the major challenges ahead. The main intention of this paper is to explore and present chronologically, a comprehensive survey of the major applications of deep learning covering variety of areas, study of the techniques and architectures used and further the contribution of that respective application in the real world. Finally, the paper ends with the conclusion and future aspects.