Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Types of machine learning algorithms: supervised learning-task driven (classification); unsupervised learning-data driven (clustering); and reinforcement learning-algorithm learns from trial and error.
Source publication
In the gastroenterology field, the impact of artificial intelligence was investigated for the purposes of diagnostics, risk stratification of patients, improvement in quality of endoscopic procedures and early detection of neoplastic diseases, implementation of the best treatment strategy, and optimization of patient prognosis. Computer-assisted di...
Context in source publication
Context 1
... main types of learning methodologies are recognized, namely, supervised learning, in which the computer learns from familiar patterns; unsupervised learning, in which the computer discovers the common aspects in unknown patterns; and, finally, reinforcement learning, in which the computer has the ability to learn from trial and error [13,14] (Figure 1). Clustering algorithms are based on unsupervised learning, in which unlabeled data self organizes to predict outcomes (e.g., clustering). ...
Similar publications
Purpose of review
Given the poor outcomes associated with esophageal cancer, there is increasing interest in the use of artificial intelligence (AI) for early detection of esophageal neoplasia and its precursors. In this review, we examine the use of AI in the endoscopic detection of Barrett’s esophagus (BE)-related neoplasia, esophageal adenocarci...
Background:
Probebased confocal laser endomicroscopy (pCLE) is a novel diagnostic technique for endoscopy which enables a microscopic view at a cellular resolution in realtime. Endoscopic detection of early neoplasia in the distal esophagus is difficult and often these lesions can be missed. The aim of the pilot study was to obtain characteristic...
Citations
... Nakashima et al. [32] established an AI diagnosing system employing GoogLeNet to predict the status of Helicobacter pylori using endoscopic images. Additionally, some studies have focused on the application of AI in detecting and diagnosing esophageal cancer [33][34][35][36][37][38][39] and gastric cancers [40][41][42]. ...
The intricate architecture of gastric anatomy coupled with the complexities inherent in esophagogastroduodenoscopy (EGD) procedures can lead to blind spots during examinations. These blind spots refer to anatomical locations not visualized during EGD examinations, potentially impacting timely diagnoses and treatments, and exacerbating patient conditions. Therefore, developing artificial intelligence (AI) for monitoring and reducing blind spots in EGD examinations is crucial. This study introduces MMCNet, a novel deep-learning model for classifying anatomical locations in EGD images. The model-based AI system can promptly alert the physician when it fails to recognize all anatomical locations in real-time EGD examinations, thereby enabling the monitoring and reduction of blind spots. To validate its efficacy, comprehensive experimental assessments compared MMCNet with established deep learning models. The results confirm MMCNet’s high accuracy rate of 97.25% in recognizing anatomical locations in EGD images. Moreover, its notably compact memory size of 4.16M contributes to reduced memory requirements. With its accuracy and small model size, the model demonstrates significant potential as an effective tool for computer-assisted blind spot detection. Additionally, this study presents a comprehensive workflow for applying deep learning models to address practical issues, which can be easily adapted for similar tasks.
... In unsupervised learning problems such as clustering and association, a model learns from unlabelled input data and discovers common aspects in unknown patterns (Abrahart et al., 2008;Borzooei et al., 2020;Zhu and Zabaras, 2018). Algorithms such as "Rewards and Recommendations" (Sutton and Barto, 2018) are based on reinforcement learning, where the model or agent learns using trial and error or through rewarding the desired behaviour and/or punishing undesired ones (Lazȃr et al., 2020). We recommend Mitchell (2014) for a more comprehensive discussion of data-driven methods. ...
... The low survival rate of patients with esophageal carcinoma and the disabling nature of the specific paraneoplastic syndrome obliges the scientific community to a prompt systemic response to combat the phenomenon, which requires major efforts regarding Life 2022, 12, 1705 2 of 12 early identification and reduction of risk factors, focusing on the problem through the appropriate allocation of material and human resources, as well as the development of effective methods of prediction and prophylaxis by monitoring the categories of patients with predisposing factors [9]. ...
Systemic changes often send signals to the skin, and certain neoplastic diseases of the internal organs can also trigger skin manifestations. In this article, the authors make clinical photography presentations of the patients seen at our clinic with dermatologic paraneoplastic syndromes within pharyngeal–esophageal malignancies, describe several paraneoplastic dermatoses, and also review high-quality scientific literature in order to be able to highlight the dermatological signs of pharyngoesophageal malignant tumors. The majority of our patients with paraneoplastic dermatoses, filtering for pharyngoesophageal malignancies, had esophageal neoplasms, out of whom seven were female and two were male, making esophageal cancer more common within the paraneoplastic dermatoses within pharyngoesophageal malignancies. An early recognition of paraneoplastic dermatoses can diagnose neoplasms and sequentially contribute to a better prognosis for the patient. This matter is also useful for front-line medical personnel in order to improve early diagnosis of the underlying malignancy, curative interventions with prompt therapy administration and good prognosis.
... The exclusion criteria were as follows: (1) patients had undergone gynecological surgery and/or chemotherapy before MRI scanning, (2) patients did not have a clear histopathological diagnosis, and (3) patients have poor MRI quality (images with artifacts failing to outline tumor ROI regions). After exclusion and screening, a total of 305 patients were enrolled in this multicenter study, and the specific clinical information of 5 Occupational Therapy International the enrolled patients can be found in Table 2 [19]. Of these 294 patients, 144 patients from clinical centers A-B were classified as the training set, the remaining 75 patients were classified as the internal test set, and 75 patients from clinical centers C-H 75 patients were classified as the external test set. ...
With the continuous updating and advancement of artificial intelligence technology, it gradually begins to shine in various industries, especially playing an increasingly important role in incremental music teaching and assisted therapy systems. This study designs artificial intelligence models from the perspectives of attention mechanism, contextual information guidance, and distant dependencies combined with incremental music teaching for the segmentation of MS (multiple sclerosis) lesions and achieves the automatic and accurate segmentation of MS lesions through the multidimensional analysis of multimodal magnetic resonance imaging data, which provides a basis for physicians to quantitatively analyze MS lesions, thus assisting them in the diagnosis and treatment of MS. To address the highly variable characteristics of MS lesion location, size, number, and shape, this paper firstly designs a 3D context-guided module based on Kronecker convolution to integrate lesion information from different fields of view, starting from lesion contextual information capture. Then, a 3D spatial attention module is introduced to enhance the representation of lesion features in MRI images. The experiments in this paper confirm that the context-guided module, cross-dimensional cross-attention module, and multidimensional feature similarity module designed for the characteristics of MS lesions are effective, and the proposed attentional context U-Net and multidimensional cross-attention U-Net have greater advantages in the objective evaluation index of lesion segmentation, while being combined with the incremental music teaching approach to assist treatment, which provides a new idea for the intelligent assisted treatment approach. In this paper, from algorithm design to experimental validation, both in terms of accuracy, the operational difficulty of the experiment, consumption of arithmetic power, and time cost, the unique superiority of the artificial intelligence attention-based combined with incremental music teaching adjunctive therapy system proposed in this paper can be seen in the MS lesion segmentation task.
... For unsupervised learning problems, such as clustering and association, a model learns from unlabelled input data and discovers common aspects in unknown patterns (Abrahart et al. 2008;Zhu et al. 2018;Borzooei et al. 2020). Reinforcement learning (Sutton & Barto 2018), where the model or agent learns using trial and error or through a reward-punishment process, has found favour more recently as a more knowledge-based and adaptive method for plant control (Hernández-del-Olmo et al. 2012;Pang et al. 2019;Lazaȓ et al. 2020). We recommend, for example, Mitchell (1997) for a more comprehensive discussion of data-driven methods. ...
Mathematical modelling is an indispensable tool to support water resource recovery facility (WRRF) operators and engineers with the ambition of creating a truly circular economy and assuring a sustainable future. Despite the successful application of mechanistic models in the water sector, they show some important limitations and do not fully profit from the increasing digitalisation of systems and processes. Recent advances in data-driven methods have provided options for harnessing the power of Industry 4.0, but they are often limited by the lack of interpretability and extrapolation capabilities. Hybrid modelling (HM) combines these two modelling paradigms and aims to leverage both the rapidly increasing volumes of data collected, as well as the continued pursuit of greater process understanding. Despite the potential of HM in a sector that is undergoing a significant digital and cultural transformation, the application of hybrid models remains vague. This article presents an overview of HM methodologies applied to WRRFs and aims to stimulate the wider adoption and development of HM. We also highlight challenges and research needs for HM design and architecture, good modelling practice, data assurance, and software compatibility. HM is a paradigm for WRRF modelling to transition towards a more resource-efficient, resilient, and sustainable future. HIGHLIGHTS
HM combines mechanistic and data-driven models.;
WRRFs are too sensitive to rely only on data-driven techniques; HM is an alternative.;
Hybrid models have a high predictive power at low computational cost, proving them useful for online optimisation and control.;
Major challenges for more widespread implementation of HM are discussed.;
HM supports the transition towards a digital and resource-efficient water sector.;
... Using these features, the program is able to label abnormalities as either benign or malignant. AI may therefore help to increase the diagnostic accuracy of EEAC using widely available white light endoscopy [8][9][10][11]. ...
Introduction
Barret’s esophagus (BE) is a precursor of adenocarcinoma of the esophagus. The detection of high-grade
dysplasia and adenocarcinoma at an early stage can improve survival but is very challenging. Artificial
intelligence (AI)-based models have been claimed to improve diagnostic accuracy. The aim of the current
study was to carry out a meta-analysis of papers reporting the results of artificial intelligence-based models
used in real-time white light endoscopy of patients with BE to detect early esophageal adenocarcinoma
(EEAC).
Methods
This meta-analysis was registered with the International Prospective Register of Systematic Reviews
(PROSPERO; Reg No. CRD42021246148) and its conduction and reporting followed the Preferred Reporting
Items for Systematic Review and Meta-Analysis of Diagnostic Test Accuracy (PRISMA-DTA) statement
guidelines. All peer-reviewed and preprint original articles that reported the sensitivity and specificity of AIbased
models on white light endoscopic imaging as an index test against the standard criterion of
histologically proven early oesophageal cancer on the background of Barret's esophagus reported as perpatient
analysis were considered for inclusion. There was no restriction on type and year of publication,
however, articles published in the English language were searched. The search engines used included
Medline, PubMed, EMBASE, EMCARE, AMED, BNI, and HMIC. The search strategy included the following
keywords for all search engines: ("Esophageal Cancer" OR "Esophageal Neoplasms" OR " Oesophageal
Cancer" OR "Oesophageal Neoplasms” OR "Barrett's Esophagus" OR "Barrett's Oesophagus") And ("Artificial
Intelligence" OR "Deep Learning" OR "Machine Learning" OR "Convolutional Network"). This search was
conducted on November 30, 2020. Duplicate studies were excluded. Studies that reported more than one
dataset per patient for the diagnostic accuracy of the AI-based model were included twice. Quantitative and
qualitative data, including first author, year of publication, true positives (TP), false negatives (FN), false
positives (FP), true negatives (TN), the threshold of the index test, and country where the study was
conducted, were extracted using a data extraction sheet. The Quality Appraisal for Diverse Studies 2
(QUADS-2) tool was used to assess the quality of each study. Data were analyzed using MetaDTA, interactive
online software for meta-analysis of diagnostic studies. The diagnostic performance of the meta-analysis
was assessed by a summary receiver operating characteristics (sROC) plot. A meta-analysis tree was
constructed using MetaDTA software to determine the effect of cumulative sensitivity and specificity on
surveillance of patients with BE in terms of miss rate and overdiagnosis.
Results
The literature search revealed 171 relevant records. After removing duplicates, 117 records were screened.
Full-text articles of 28 studies were assessed for eligibility. Only three studies reporting four datasets met
the inclusion criteria. The summary sensitivity and specificity of AI-based models were 0.90 (95% CI, 0.83-
0.944) and 0.86 (95% CI, 0.781-0.91), respectively. The area under the curve for all the available evidence was
0.88.
Conclusion
Collective evidence for the routine usage of AI-based models in the detection of EEAC is encouraging but is
limited by the low number of studies. Further prospective studies reporting the patient-based diagnostic
accuracy of such models are required.
... 7 Recently, the application of AI-assisted models has been gradually extended to the endoscopic assessment of esophageal diseases. 8 AI models have been found to be accurate in detecting early esophageal cancer via endoscopic images, some of them are even more effective than experienced endoscopists. In this systematic review and meta-analysis, we aimed to investigate systematically the accuracy of AI-assisted diagnostic models in the detection of esophageal neoplasms on endoscopic images so as to provide scientific evidence for their effectiveness. ...
Objective
We performed a meta‐analysis to systematically summarize previous studies on the accuracy of AI in the detection of esophageal cancer and neoplasms in endoscopic images, so as to provide scientific evidence for the effectiveness of AI‐assisted diagnostic models.
Methods
We searched the databases of PubMed, Embase and Cochrane for studies on AI‐assisted esophageal cancer and neoplasms in endoscopic images. We used a bivariate mixed‐effects binary regression model to calculate the pooled diagnostic efficacy of AI. Subgroup analyses and meta‐regression were performed to explore the sources of heterogeneity. We also compared the effectiveness of AI with that of endoscopists.
Result
A total of 16 studies were included in our meta‐analysis. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio and AUC were 0.94 (95%CI: 0.92‐0.96), 0.85 (95%CI: 0.73‐0.92), 6.397 (95%CI: 3.380‐12.106), 0.065 (95%CI: 0.041‐0.102), 98.881 (95%CI: 39.446‐247.865) and 0.97 (95%CI: 0.95‐0.98), respectively. AI‐based models showed a better performance than endoscopists in terms of the pooled sensitivity (0.94; 95%CI: 0.84‐0.98 vs. 0.82; 95%CI: 0.77‐0.86, p < 0.01).
Conclusion
The use of AI was shown to achieve a high accuracy in the detection of early esophageal cancer. However, most of the studies were based on retrospective review of selected images, further validation in prospective trials is expected.
... Convolutional Neural Network (CNN) is an example of the specific class of ANN (Lazar et al., 2020). CNN is composed of several convolutional and pooling layers, which have a role of 'feature extraction' and fully connected layers that execute the task of the classification (Lazar et al., 2020). ...
... Convolutional Neural Network (CNN) is an example of the specific class of ANN (Lazar et al., 2020). CNN is composed of several convolutional and pooling layers, which have a role of 'feature extraction' and fully connected layers that execute the task of the classification (Lazar et al., 2020). CNN architectures are based on the principle of the human brain, formed of billions of neurons (Haque and Abdelgawad, 2020). ...
Artificial intelligence (AI) is present in many aspects of our daily life. The use of AI has also became popular in various medical fields, particularly in radiology. This paper analyses research papers published at the beginning of COVID-19 pandemic. Deep learning algorithms have been utilised by various research teams globally to aid detection of COVID-19 on chest radiographs. The results from majority of authors were promising with high sensitivity and specificity in detection of COVID-19 on chest radiographs. Nevertheless, limitations were also identified such as limited data set of COVID-19 chest radiographs used to train the deep learning algorithms.
... Dies betrifft vor allem das Erkennen früher Anzeichen von Darmkrebs wäh-rend Koloskopien in endoskopischen Bilddaten [27] und der Segmentierung von radiologischen Bilddaten [26]. Diese Assistenzsysteme sollen einerseits den Aufwand von arbeitsintensiven Eingriffen verringern und andererseits medizinische Experten unterschiedlicher Kompetenzstufen in der Diagnostik unterstützen [11]. Sogenannte tiefe neuronale Netze sind in der Lage, Polypen in Echtzeit zu erkennen [7]. ...
Background
Medical robotics has the potential to improve surgical and endoluminal procedures by enabling high-precision movements and superhuman perception.Objectives
To present historical, existing and future robotic assistants for surgery and to highlight their characteristics and advantages for keyhole surgery and endoscopy.Methods
In particular, historical medical robots and conventional telemanipulators are presented and compared with minimally invasive continuum robots and novel robotic concepts from practice and research. In addition, a perspective for future generations of surgical and endoluminal robots is offered.Conclusion
Robot-assisted medicine offers great added value for quality of intervention as well as safety for surgeons and patients. In the future, more surgical steps will be performed (semi-)autonomously and in cooperation with the experts.
The use of Artificial intelligence (AI) has evolved from its mid-20th century origins to playing a pivotal tool in modern medicine. It leverages digital data and computational hardware for diverse applications, including diagnosis, prognosis, and treatment responses in gastrointestinal and hepatic conditions. AI has had an impact in diagnostic techniques, particularly endoscopy, ultrasound, and histopathology. AI encompasses machine learning, natural language processing, and robotics, with machine learning being central. This involves sophisticated algorithms capable of managing complex datasets, far surpassing traditional statistical methods. These algorithms, both supervised and unsupervised, are integral for interpreting large datasets. In liver diseases, AI's non-invasive diagnostic applications, particularly in non-alcoholic fatty liver disease, and its role in characterizing hepatic lesions is promising. AI aids in distinguishing between normal and cirrhotic livers and improves the accuracy of lesion characterization and prognostication of hepatocellular carcinoma. AI enhances lesion identification during endoscopy, showing potential in the diagnosis and management of early-stage esophageal carcinoma. In peptic ulcer disease, AI technologies influence patient management strategies. AI is useful in colonoscopy, particularly in detecting smaller colonic polyps. However, its applicability in non-academic settings requires further validation. Addressing these issues is vital for harnessing the potential of AI. In conclusion, while AI offers transformative possibilities in gastroenterology, careful integration and balancing of technical possibilities with ethical and practical application, is essential for optimal use.
