No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Introduction to image-assisted disease screening
Abstract
Disease occurrence rates in humans are rapidly rising for various reasons and so timely detection and treatment implementation are necessary to ensure successful cures. The disease diagnosis procedure varies based on the type and severity of the disease. Further, this scheme also depends on the infected area under examination. In most cases, verification by a doctor, followed by signal-based prescreening and image-based postscreening is widely recommended to confirm the disease and its severity. This chapter provides a detailed overview of image-supported disease screening procedures adopted in hospitals to examine the various internal organs, such as the breasts, heart, and brain. The various imaging modalities considered to examine the abnormalities in these organs are examined and the advantages and disadvantages of the considered imaging schemes are discussed. Compared to other imaging methods, magnetic resonance imaging is confirmed as one of the most widely adopted radiological procedures to identify disease in these organs with improved visibility.
ResearchGate has not been able to resolve any citations for this publication.
Background
The number of people with lifestyle-related diseases continues to increase worldwide. Improving lifestyle behavior with health literacy may be the key to address lifestyle-related diseases. The delivery of educational videos using mobile health (mHealth) services can replace the conventional way of educating individuals, and visualization can replace the provision of health checkup data.
Objective
This paper aimed to describe the development of educational content for MIRAMED, a mobile app aimed at improving users’ lifestyle behaviors and health literacy for lifestyle-related diseases.
Methods
All videos were based on a single unified framework to provide users with a consistent flow of information. The framework was later turned into a storyboard. The final video contents were created based on this storyboard and further discussions with leading experts and specialist physicians on effective communication with app users about lifestyle-related diseases.
Results
The app uses visualization of personal health checkup data and educational videos on lifestyle-related diseases based on the current health guidelines, scientific evidence, and expert opinions of leading specialist physicians in the respective fields. A total of 8 videos were created for specific lifestyle-related diseases affecting 8 organs: (1) brain–cerebrovascular disorder, (2) eyes–diabetic retinopathy, (3) lungs–chronic obstructive pulmonary disease, (4) heart–ischemic heart disease, (5) liver–fatty liver, (6) kidneys–chronic kidney disease (diabetic kidney disease), (7) blood vessels–peripheral arterial disease, and (8) nerves–diabetic neuropathy.
Conclusions
Providing enhanced mHealth education using novel digital technologies to visualize conventional health checkup data and lifestyle-related diseases is an innovative strategy. Future studies to evaluate the efficacy of the developed content are planned.
The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.
Internet of Things (IoT) plays a vital role in the field of healthcare. The development of smart sensors, smart devices, advanced lightweight communication protocols made the possibility of interconnecting medical things to monitor biomedical signals and diagnose the diseases of patients without human intervention and termed as Internet of Medical Things (IoMT). This paper portrays an overview of Internet of Medical Things based remote healthcare, tracking ingestible sensors, mobile health, smart hospitals, enhanced chronic disease treatment.
The aim of this work is to develop a Computer-Aided-Brain-Diagnosis (CABD) system that can determine if a brain scan shows signs of Alzheimer’s disease. The method utilizes Magnetic Resonance Imaging (MRI) for classification with several feature extraction techniques. MRI is a non-invasive procedure, widely adopted in hospitals to examine cognitive abnormalities. Images are acquired using the T2 imaging sequence. The paradigm consists of a series of quantitative techniques: filtering, feature extraction, Student’s t-test based feature selection, and k-Nearest Neighbor (KNN) based classification. Additionally, a comparative analysis is done by implementing other feature extraction procedures that are described in the literature. Our findings suggest that the Shearlet Transform (ST) feature extraction technique offers improved results for Alzheimer’s diagnosis as compared to alternative methods. The proposed CABD tool with the ST + KNN technique provided accuracy of 94.54%, precision of 88.33%, sensitivity of 96.30% and specificity of 93.64%. Furthermore, this tool also offered an accuracy, precision, sensitivity and specificity of 98.48%, 100%, 96.97% and 100%, respectively, with the benchmark MRI database.
The human brain is considered to be the anatomical seat of intelligence, comprehensively supervising conscious and autonomous functions responsible for monitoring and control operations. Although neural homeostasis can be disrupted, early signs of disease should be recognized to save the patient from permanent disability and even a preventable death. The record of World Health Organization (WHO) lists various brain diseases, such as aneurism, stroke and tumor, which affect humans irrespective of their age, sex and province, all of which affect diagnosis, prognosis and treatment options. Since clinically significant diagnosis of brain abnormality is generally performed using dedicated imaging procedures and also under the supervision of an experienced radiologist, more accurate tools can make this process even more precise. The usual protocol involves a radiologist who records the three-dimensional (3D) image which provides initial insight on the type of brain disease, followed by doctor examination of the 3D/2D image that determines the treatment plan. This article proposes a tool and associated procedure to examine a clinical brain image with improved accuracy in order to provide early insight on ideal treatment procedure. In summary, this tool gives the treatment team unprecedented assessment capability before an operation by integrating all the possible image processing procedures to enhance the result in brain image analysis.
Examination of the brain's condition with the Electroencephalogram (EEG) can be helpful to predict abnormality and cerebral activities. The purpose of this study was to develop an Automated Diagnostic Tool (ADT) to investigate and classify the EEG signal patterns into normal and schizophrenia classes. The ADT implements a sequence of events, such as EEG series splitting, non-linear features mining, t-test assisted feature selection, classification and validation. The proposed ADT is employed to evaluate a 19-channel EEG signal collected from normal and schizophrenia class volunteers. A dataset was created by splitting the raw 19-channel EEG into a sequence of 6250 sample points, which was helpful to produce 1142 features of normal and schizophrenia class patterns. Non-linear feature extraction was then implemented to mine 157 features from each EEG pattern, from which 14 of the principal features were identified based on significance. Finally, a signal classification practice with Decision-Tree (DT), Linear-Discriminant analysis (LD), k-Nearest-Neighbour (KNN), Probabilistic-Neural-Network (PNN), and Support-Vector-Machine (SVM) with various kernels was implemented. The experimental outcome showed that the SVM with Radial-Basis-Function (SVM-RBF) offered a superior average performance value of 92.91% on the considered EEG dataset, as compared to other classifiers implemented in this work.
Wearable devices, wireless networks and body area networks have become an effective way to solve the problem of human health monitoring and care. However, the radiation problems of wireless devices, the power supply problems of wearable devices and the deployment of body area networks have become obstacles to their wide application in the field of health care. In order to solve the above problems, this paper studies and designs a wearable health medical body area network which is convenient for human health monitoring and medical care, starting from low-cost deployment of wireless wearable devices and active control of wireless radiation. Firstly, in order to avoid replacing equipment batteries, improve the relay and data aggregation capabilities of wireless body area network, and reduce the communication and computing load of edge devices, a deployment scheme of wireless medical health wearable devices is designed based on the optimal segmentation algorithm of Steiner spanning tree. Then, in order to minimize the charging cost and maximize the global charging utility of single source and multiple points in a finite time slot, an approximate algorithm for the optimal charging sequence based on 01 knapsack problem, i.e., the access path of wireless wearable devices, is designed. Then, an active radiation control algorithm for wearable medical health body area network is proposed, which can actively control the transmission power and radiation status of these wireless devices. Finally, simulation results show that the proposed algorithm is better than battery-powered wireless body area network and wireless rechargeable body area network, 16% and 44% reduction of devices, 25%和13% reduction of energy consumption, 26% reduction of radiation, and 5.18 and 1.13 times improvement of signal quality.
Objectives
Histopathological tissue analysis by a pathologist determines the diagnosis and prognosis of most tumors, such as breast cancer. To estimate the aggressiveness of cancer, a pathologist evaluates the microscopic appearance of a biopsied tissue sample based on morphological features which have been correlated with patient outcome.
Data description
This paper introduces a dataset of 162 breast cancer histopathology images, namely the breast cancer histopathological annotation and diagnosis dataset (BreCaHAD) which allows researchers to optimize and evaluate the usefulness of their proposed methods. The dataset includes various malignant cases. The task associated with this dataset is to automatically classify histological structures in these hematoxylin and eosin (H&E) stained images into six classes, namely mitosis, apoptosis, tumor nuclei, non-tumor nuclei, tubule, and non-tubule. By providing this dataset to the biomedical imaging community, we hope to encourage researchers in computer vision, machine learning and medical fields to contribute and develop methods/tools for automatic detection and diagnosis of cancerous regions in breast cancer histology images.
As the life expectancy of individuals increases with recent advancements in medicine and quality of living, it is important to monitor the health of patients and healthy individuals on a daily basis. This is not possible with the current health care system in North America, and thus there is a need for wireless devices that can be used from home. These devices are called biomedical wearables, and they have become popular in the last decade. There are several reasons for that, but the main ones are: expensive health care, longer wait times, and an increase in public awareness about improving quality of life. With this, it is vital for anyone working on wearables to have an overall understanding of how they function, how they were designed, their significance, and what factors were considered when the hardware was designed. Therefore, this study attempts to investigate the hardware components that are required to design wearable devices that are used in the emerging context of the Internet of Medical Things (IoMT). This means that they can be used, to an extent, for disease monitoring through biosignal capture. In particular, this review study covers the basic components that are required for the front-end of any biomedical wearable, and the limitations that these wearable devices have. Furthermore, there is a discussion of the opportunities that they create, and the direction that the wearable industry is heading in.
Because of the vast availability of data, there has been an additional focus on the health industry and an increasing number of studies that aim to leverage the data to improve healthcare have been conducted. The health data is growing increasingly large, more complex and its sources have increased tremendously to include Computerized Physician Order Entry (CPOE), Electronic Medical Records (EMR), clinical notes, medical images, Cyber-Physical Systems (CPA) and medical Internet of Things(mIoT), genomic data, and Clinical Decision Support Systems (CDSS). New types of data from sources like Social Network Services (SNS) and genomic data are used to build personalized healthcare systems, hence health data are obtained in various forms, from varied sources, contexts, technologies, and their nature can impede a proper analysis. Any analytical research must overcome these obstacles to mine data and produce meaningful insights to save lives. In this study, we investigate the key challenges, data sources, techniques, technologies, as well as future directions in the field of big data analytics in healthcare. We provide a do-it-yourself review that delivers a holistic, simplified and easily understandable view of various technologies that are used to develop an integrated health analytic application.
Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims to address this problem of comparability. ISLES 2016 and 2017 focused on lesion outcome prediction after ischemic stroke: By providing a uniformly pre-processed data set, researchers from all over the world could apply their algorithm directly. A total of nine teams participated in ISLES 2015, and 15 teams participated in ISLES 2016. Their performance was evaluated in a fair and transparent way to identify the state-of-the-art among all submissions. Top ranked teams almost always employed deep learning tools, which were predominately convolutional neural networks (CNNs). Despite the great efforts, lesion outcome prediction persists challenging. The annotated data set remains publicly available and new approaches can be compared directly via the online evaluation system, serving as a continuing benchmark (www.isles-challenge.org).
In medical domain, diseases in critical internal organs are generally inspected using invasive/non-invasive imaging techniques. Magnetic resonance imaging (MRI) is one of the commonly considered imaging approaches to confirm the abnormality in various internal organs. After recording the MRI, an appropriate image processing exercise is to be implemented to investigate and infer the severity of the disease and its location. This paper proposes a semi-automated tool to investigate the medical MRI captured with contrast improved T1 modality (T1C). This technique considers the integration of Bat algorithm (BA) and Tsallis based thresholding along with region growing (RG) segmentation. Proposed approach is tested on RGB/gray scale images of brain and breast MRI recorded along with a contrast agent. After mining the infected region, its texture features are extracted with Haralick function to assess the surface details of abnormal section. Performance of RG is confirmed against other segmentation methods, such as level set (LS), principal component analysis (PCA) and watershed. The clinical significance of the proposed technique is also validated using the brain images of BRATS recorded using T1C modality. The experiment outcome confirms that, the implemented procedure provides better values of Jaccard (87.41%), Dice (90.36%), sensitivity (98.27%), specificity (97.72%), accuracy (97.53%) and precision (95.85%) for the considered BRATS brain MRI.
Implementation experts suggest tailoring strategies to the intended context may enhance outcomes. However, it remains unclear which strategies are best suited to address specific barriers to implementation, in part because few measurement methods exist that adhere to recommendations for reporting. In the context of a dynamic cluster randomized trial comparing a standardized to tailored approach to implementing measurement-based care (MBC), this study aimed to (a) describe a method for tracking implementation strategies, (b) demonstrate the method by tracking strategies generated by teams tasked with implementing MBC at their clinics in the tailored condition, and (c) conduct preliminary examinations of the relation between strategy use and implementation outcomes (i.e., self-reported fidelity to MBC). The method consisted of a coding form based on Proctor, Powell, and McMillen (2013) implementation strategy reporting guidelines and Powell et al.'s (2012) taxonomy to facilitate specification of the strategies. A trained research specialist coded digitally recorded implementation team meetings. The method allowed for the following characterization of strategy use. Each site generated 39 unique strategies across an average of six meetings in five months. There was little variability in the use of types of implementation strategies across sites with the following order of prevalence: quality management (50.00%), restructuring (16.53%), communication (15.68%), education (8.90%), planning (7.20%), and financing (1.69%). We identified a new category of strategies not captured by the existing taxonomy, labeled "communication." There was no evidence that number of implementation strategies enacted was statistically significantly associated with changes in self-reported fidelity to MBC-however, financing strategies were associated with increased fidelity. This method has the capacity to yield rich data that will inform investigations into tailored implementation approaches.
Wireless technology development has increased rapidly due to it’s convenience and cost effectiveness compared to wired applications, particularly considering the advantages offered by Wireless Sensor Network (WSN) based applications. Such applications exist in several domains including healthcare, medical, industrial and home automation. In the present study, a home-based wireless ECG monitoring system using Zigbee technology is considered. Such systems can be useful for monitoring people in their own home as well as for periodic monitoring by physicians for appropriate healthcare, allowing people to live in their home for longer. Health monitoring systems can continuously monitor many physiological signals and offer further analysis and interpretation. The characteristics and drawbacks of these systems may affect the wearer’s mobility during monitoring the vital signs. Real-time monitoring systems record, measure, and monitor the heart electrical activity while maintaining the consumer’s comfort. Zigbee devices can offer low-power, small size, and a low-cost suitable solution for monitoring the ECG signal in the home, but such systems are often designed in isolation, with no consideration of existing home control networks and smart home solutions. The present study offers a state of the art review and then introduces the main concepts and contents of the wireless ECG monitoring systems. In addition, models of the ECG signal and the power consumption formulas are highlighted. Challenges and future perspectives are also reported. The paper concludes that such mass-market health monitoring systems will only be prevalent when implemented together with home environmental monitoring and control systems.
In the era when the market segment of Internet of Things (IoT) tops the chart in various business reports, it is apparently envisioned that the field of medicine expects to gain a large benefit from the explosion of wearables and internet-connected sensors that surround us to acquire and communicate unprecedented data on symptoms, medication, food intake, and daily-life activities impacting one's health and wellness. However, IoT-driven healthcare would have to overcome many barriers, such as: 1) There is an increasing demand for data storage on cloud servers where the analysis of the medical big data becomes increasingly complex, 2) The data, when communicated, are vulnerable to security and privacy issues, 3) The communication of the continuously collected data is not only costly but also energy hungry, 4) Operating and maintaining the sensors directly from the cloud servers are non-trial tasks. This book chapter defined Fog Computing in the context of medical IoT. Conceptually, Fog Computing is a service-oriented intermediate layer in IoT, providing the interfaces between the sensors and cloud servers for facilitating connectivity, data transfer, and queryable local database. The centerpiece of Fog computing is a low-power, intelligent, wireless, embedded computing node that carries out signal conditioning and data analytics on raw data collected from wearables or other medical sensors and offers efficient means to serve telehealth interventions. We implemented and tested an fog computing system using the Intel Edison and Raspberry Pi that allows acquisition, computing, storage and communication of the various medical data such as pathological speech data of individuals with speech disorders, Phonocardiogram (PCG) signal for heart rate estimation, and Electrocardiogram (ECG)-based Q, R, S detection.
With the widespread adoption of population-based breast cancer screening, ductal carcinoma in situ (DCIS) has come to represent 20?25% of all breast neoplastic lesions diagnosed. Current treatment aims at preventing invasive breast cancer, but the majority of DCIS lesions will never progress to invasive disease. Still, DCIS is treated by surgical excision, followed by radiotherapy as part of breast conserving treatment, and/or endocrine therapy. This implies over-treatment of the majority of DCIS, as less than 1% of DCIS patients will go on to develop invasive breast cancer annually. If we are able to identify which DCIS is likely to progress or recur as invasive breast cancer and which DCIS would remain indolent, we can treat the first group intensively, while sparing the second group from such unnecessary treatment (surgery, radiotherapy, endocrine therapy) preserving the quality of life of these women. This review summarizes our current knowledge on DCIS and the risks involved regarding progression into invasive breast cancer. It also shows current knowledge gaps, areas where profound research is highly necessary for women with DCIS to prevent their over-treatment in case of a harmless DCIS, but provide optimal treatment for potentially hazardous DCIS.
Ischemic stroke is the most common cerebrovascular disease, and its diagnosis, treatment, and study relies on non-invasive imaging. Algorithms for stroke lesion segmentation from magnetic resonance imaging (MRI) volumes are intensely researched, but the reported results are largely incomparable due to different datasets and evaluation schemes. We approached this urgent problem of comparability with the Ischemic Stroke Lesion Segmentation (ISLES) challenge organized in conjunction with the MICCAI 2015 conference. In this paper we propose a common evaluation framework, describe the publicly available datasets, and present the results of the two sub-challenges: Sub-Acute Stroke Lesion Segmentation (SISS) and Stroke Perfusion Estimation (SPES). A total of 16 research groups participated with a wide range of state-of-the-art automatic segmentation algorithms. A thorough analysis of the obtained data enables a critical evaluation of the current state-of-the-art, recommendations for further developments, and the identification of remaining challenges. The segmentation of acute perfusion lesions addressed in SPES was found to be feasible. However, algorithms applied to sub-acute lesion segmentation in SISS still lack accuracy. Overall, no algorithmic characteristic of any method was found to perform superior to the others. Instead, the characteristics of stroke lesion appearances, their evolution, and the observed challenges should be studied in detail. The annotated ISLES image datasets continue to be publicly available through an online evaluation system to serve as an ongoing benchmarking resource (www.isles-challenge.org).
Infectious diseases emerging throughout history have included some of the most feared plagues of the past. New infections continue to emerge today, while many of the old plagues are with us still. These are global problems (William Foege, former CDC director now at the Carter Center, terms them global infectious disease threats). As demonstrated by influenza epidemics, under suitable circumstances, a new infection first appearing anywhere in the world could traverse entire continents within days or weeks.
Medical body area network is a human-centric application of wireless sensor network which has recently gained much significance. The application includes both wearable and implantable sensors for continuous monitoring of patients in hospitals, old houses or at any remote location. These sensor nodes in medical body area network possess all the characteristics of nodes in wireless sensor network. In this paper a survey of medical wireless body area network, its architectural design issues and challenges have been discussed.
Early prediction of breast density is clinically significant as there is an association between the risk of breast cancer development and breast density. In the present work, the performance of two computer aided diagnostic (CAD) systems has been compared for classification of breast tissue density. The work has been carried out on MIAS dataset with 322 mammographic images consisting of 106 fatty and 216 dense images. The ROIs have been selected from densest region (i.e., the center of each image, ignoring the pectoral muscle) of each mammogram. The total dataset consisted of 322 ROIs (106 fatty ROIs and 216 dense ROIs). Five statistical texture features namely, mean, standard deviation, entropy, kurtosis and skewness are evaluated from Laws’ texture energy images resulting from Laws’ masks of length 5, 7 and 9. The texture feature vectors computed from Laws’ masks of different lengths are then subjected to principal component analysis (PCA) for reduction in feature space dimensionality. The SVM and PNN classifiers are used for the classification task. It is observed that the highest classification accuracy of 92.5 % is achieved with first four principal components derived from texture features computed with Laws’ masks of length 7 by using PNN classifier and the highest classification accuracy of 94.4 % is achieved with first four principal components derived from texture features computed with Laws’ masks of length 5 by using SVM classifier. It can be concluded that the first four principal components derived from Laws’ texture energy images resulting from Laws’ masks of length 5 are sufficient to account for textural changes exhibited by fatty and dense mammograms. The promising results obtained by the proposed CAD design indicate its usefulness to assist radiologists for breast density classification.
Authentication is very important in validating a medical content in the domain of telemedicine; however, there are many challenges. Accurate verification is paramount, and any misuse of personal information may have serious consequences. Many authentication processes tried to design various methods to minimise such discrepancies. In this current work, we propose a new approach to design a robust biomedical content authentication system by embedding logo of the hospital within the electrocardiogram signal by means of both discrete wavelet transformation and cuckoo search CS. An adaptive meta-heuristic cuckoo search is used to find the optimal scaling factor settings for logo embedding. Results show that the proposed method can serve as a secure and accurate authentication system.
The acknowledged potential of using mobile phones for improving healthcare in low-resource environments of developing countries has yet to translate into significant mHealth policy investment. The low uptake of mHealth in policy agendas may stem from a lack of evidence of the scalable, sustainable impact on health indicators. The mHealth literature in low- and middle-income countries reveals a burgeoning body of knowledge; yet, existing reviews suggest that the projects yield mixed results. This article adopts a stage-based approach to understand the varied contributions to mHealth research. The heuristic of inputs-mechanism-outputs is proposed as a tool to categorize mHealth studies. This review (63 articles comprising 53 studies) reveals that mHealth studies in developing countries tend to concentrate on specific stages, principally on pilot projects that adopt a deterministic approach to technological inputs (n = 32), namely introduction and implementation. Somewhat less studied were research designs that demonstrate evidence of outputs (n = 15), such as improvements in healthcare processes and public health indicators. The review finds a lack of emphasis on studies that provide theoretical understanding (n = 6) of adoption and appropriation of technological introduction that produces measurable health outcomes. As a result, there is a lack of dominant theory, or measures of outputs relevant to making policy decisions. Future work needs to aim for establishing theoretical and measurement standards, particularly from social scientific perspectives, in collaboration with researchers from the domains of information technology and public health. Priorities should be set for investments and guidance in evaluation disseminated by the scientific community to practitioners and policymakers.
The National Institutes of Health have placed significant emphasis on sharing of research data to support secondary research. Investigators have been encouraged to publish their clinical and imaging data as part of fulfilling their grant obligations. Realizing it was not sufficient to merely ask investigators to publish their collection of imaging and clinical data, the National Cancer Institute (NCI) created the open source National Biomedical Image Archive software package as a mechanism for centralized hosting of cancer related imaging. NCI has contracted with Washington University in Saint Louis to create The Cancer Imaging Archive (TCIA)-an open-source, open-access information resource to support research, development, and educational initiatives utilizing advanced medical imaging of cancer. In its first year of operation, TCIA accumulated 23 collections (3.3 million images). Operating and maintaining a high-availability image archive is a complex challenge involving varied archive-specific resources and driven by the needs of both image submitters and image consumers. Quality archives of any type (traditional library, PubMed, refereed journals) require management and customer service. This paper describes the management tasks and user support model for TCIA.
The biological basis of psychopathy has not yet been fully elucidated. Few studies deal with structural neuroimaging in psychopaths. The aim of this article is to review these studies in order to contribute to our understanding of the biological basis of psychopathy. Data in the literature report a reduction in prefrontal gray matter volume, gray matter loss in the right superior temporal gyrus, amygdala volume loss, a decrease in posterior hippocampal volume, an exaggerated structural hippocampal asymmetry, and an increase in callosal white matter volume in psychopathic individuals. These findings suggest that psychopathy is associated with brain abnormalities in a prefrontal–temporo-limbic circuit—i.e. regions that are involved, among others, in emotional and learning processes. Additionally, data indicate that psychopathic individuals cannot be seen as a homogeneous group.
The associations between structural changes and psychopathic characteristics do not enable causal conclusions to be drawn, but point rather to the important role of biological brain abnormalities in psychopathy. To gain a comprehensive understanding of this, psychopathy must be viewed as a multifactorial process involving neurobiological, genetic, epidemiological and sociobiographical factors. Copyright
Brain image segmentation is one of the most important parts of clinical diagnostic tools. Brain images mostly contain noise, inhomogeneity and sometimes deviation. Therefore, accurate segmentation of brain images is a very difficult task. However, the process of accurate segmentation of these images is very important and crucial for a correct diagnosis by clinical tools. We presented a review of the methods used in brain segmentation. The review covers imaging modalities, magnetic resonance imaging and methods for noise reduction, inhomogeneity correction and segmentation. We conclude with a discussion on the trend of future research in brain segmentation.
This research developed and empirically validated a multidimensional hierarchical scale for measuring health service quality and investigated the scale's ability to predict important service outcomes, namely, service satisfaction and behavioral intentions. Data were collected from a qualitative study and three different field studies of health care patients in two different health care contexts: oncology clinics and a general medical practice. Service quality was found to conform to the structure of the hierarchical model in all three samples. The research identified nine subdimensions driving four primary dimensions, which in turn were found to drive service quality perceptions. The primary dimensions were interpersonal quality, technical quality, environment quality, and administrative quality. The subdimensions were interaction, relationship, outcome, expertise, atmosphere, tangibles, timeliness, operation, and support. The findings also support the hypothesis that service quality has a significant impact on service satisfaction and behavioral intentions and that service quality mediates the relationship between the dimensions and intentions.
In medical domain, the detection of the acute diseases based on the medical data plays a vital role in identifying the nature, cause, and the severity of the disease with suitable accuracy; this information supports the doctor during the decision making and treatment planning procedures. The research aims to develop a framework for preserving the disease-evidence-information (DEvI) to support the automated disease detection process. Various phases of DEvI include (1) data collection, (2) data pre- and post-processing, (3) disease information mining, and (4) implementation of a deep-neural-network (DNN) architecture to detect the disease. To demonstrate the proposed framework, assessment of lung nodule (LN) is presented, and the attained result confirms that this framework helps to attain better segmentation as well as classification result. This technique is clinically significant and helps to reduce the diagnostic burden of the doctor during the malignant LN detection.
Pneumonia is one of the major illnesses in children and aged humans due to the Infection in the lungs. Early analysis of pneumonia is necessary to prepare for a possible treatment procedure to regulate and cure the disease. This research aspires to develop a Deep-Learning System (DLS) to diagnose the lung abnormality using chest X-ray (radiograph) images. The proposed work is implemented using; (i) Conventional chest radiographs and (ii) Chest radiograph treated with a threshold filter. The initial experimental evaluation is carried out using the traditional DLS, such as AlexNet, VGG16, VGG19 and ResNet50 with a SoftMax classifier. The results confirmed that, VGG19 provides better classification accuracy (86.97%) compared to other methods. Later, a customized VGG19 network is proposed using the Ensemble Feature Scheme (EFS), which combines the handcrafted features attained with CWT, DWT and GLCM with the Deep-Features (DF) achieved using Transfer-Learning (TL) practice. The performance of customized VGG19 is tested using different classifiers, such as SVM-linear, SVM-RBF, KNN classifier, Random-Forest (RF) and Decision-Tree (DT). The result confirms that VGG19 with RF classifier offers better accuracy (95.70%). When the similar experiment is repeated using threshold filter treated chest radiographs, the VGG19 with RF classifier offered superior classification accuracy (97.94%). This result confirms that, proposed DLS will work well on the benchmark images and in the future, it can be considered to diagnose clinical grade chest radiographs.
Magnetic Resonance Imaging (MRI) is a common
imaging procedure widely adopted in hospitals to examine the
disease in internal organs. Compared to other imaging
techniques, MRI can be recorded with a variety of modalities,
such as Flair, T1, T1C, T2, Diffused Weighting (DW) and fMRI.
Further, it can provide a reconstructed Three-Dimensional (3D)
view of the internal organ under study. In this work, a hybrid
approach based on the combination of thresholding and
segmentation is implemented to examine the congenital heart
defect using the Heart MRI (HMRI) recorded using T2
modality. The thresholding is implemented with Differential
Evolution (DE) based Shannon’s Entropy (SE) and the
segmentation are implemented using the Level Set (LS). In this
work, the axial view of the HMRI images of the HVSMR
2016 benchmark dataset is considered for the analysis. The main
aim of this work is to extract the Region Of Interest (ROI) from
the HMRI and compare the extracted section with the Ground
Truth (GT) images. The experimental investigation of the
proposed work confirms that, proposed work offers enhanced
average image similarity values (> 88%) on the considered
dataset.
Index Terms—Heart MRI, axial view, differential evolution,
Shannon’s entropy, level set
Medical image assessment is an essential practice in most of the disease identification events. A recent imaging procedure, infrared thermal imaging, has attracted wide consumers due to its noninvasive nature, cost, and accuracy. This paper considers the inspection of breast malignancy. This paper presents a hybrid framework with a heuristic algorithm-driven preprocessing practice and a semi/fully automated postprocessing. The result of the proposed technique is also validated against other existing segmentation methods.
The process of segmenting tumor from MRI image of a brain is one of the highly focused areas in the community of medical science as MRI is noninvasive imaging. This paper discusses a thorough literature review of recent methods of brain tumor segmentation from brain MRI images. It includes the performance and quantitative analysis of state-of-the-art methods. Different methods of image segmentation are briefly explained with the recent contribution of various researchers. Here, an effort is made to open new dimensions for readers to explore the concerned area of research. Through the entire review process, it has been observed that the combination of Conditional Random Field (CRF) with Fully Convolutional Neural Network (FCNN) and CRF with DeepMedic or Ensemble are more effective for the segmentation of tumor from the brain MRI images.
Internet of things provides interaction with billions of objects across the world using the Internet. In Internet of thing era, Healthcare Industry has grown-up from 1.0 to 4.0 generation. Healthcare 3.0 was hospital centric, where patients of long-lasting sickness suffered a lot due to multiple hospital visits for their routine checkups. This in turn, prolonged the treatment of such patients along with an increase in the overall expenditure on treatment of patients. However, with recent technological advancements such as fog and cloud computing, these problems are mitigated with a minimum capital investment on computing and storage facilities related to the data of the patients. Motivated from these facts, this paper provide an analysis of the role of fog computing, cloud computing, and Internet of things to provide uninterrupted context-aware services to the end users as and when required. We propose a three layer patient-driven Healthcare architecture for real-time data collection, processing and transmission. It gives insights to the end users for the applicability of fog devices and gateways in Healthcare 4.0 environment for current and future applications.
This paper proposes a hybrid approach with the integration of a pre-processing and a post-processing technique to examine Magnetic Resonance Angiography (MRA) images. In pre-processing stage, a tri-level thresholding is implemented on the 2D MRA test image using the Chaotic Firefly Algorithm (CFA) and Tsallis entropy in order to improve the contrast enhanced regions by grouping the similar pixel levels. During post-processing stage, contrast enhanced regions of test image is extracted using the Active Contour (AC) procedure known as the deformable snake. Finally, the texture property of extracted aneurysm region is then computed using Minkowski distance function. The advantage of AC is validated using other segmentation procedures, such as watershed algorithm, level set, and Markov random field procedure existing in the literature. Further, the effectiveness of the proposed technique is validated using the TIC, Flair and T2 modality brain images existing in the BraTS MRI dataset. The experimental study established that the proposed two stage approach extracted efficiently the contrast enhanced regions from the MRA and T1C brain images. The segmentation result on - T1C confirmed that the proposed methodology achieved superior values of 89.65%, 93.05%, 98.16%, 98.36%, 98.17% and 90.88% for the Jaccard, dice, sensitivity, specificity, accuracy and precision respectively.
Stroke is one of the widespread causes of morbidity worldwide and is also the foremost reason for attained disability in human community. Ischemic stroke can be confirmed by investigating the interior brain regions. Magnetic resonance image (MRI) is one of the noninvasive imaging techniques widely adopted in medical discipline to record brain malformations. In this paper, a hybrid semi-automated image processing methodology is proposed to inspect the ischemic stroke lesion using the MRI recorded with flair and diffusion-weighted modality. The proposed approach consists of two sections, namely the preprocessing based on the social group optimization monitored Fuzzy-Tsallis entropy and post-processing technique, which consists of a segmentation algorithm to extract the ISL from preprocessed image in order to estimate the stroke severity and also to plan for further treatment process. The proposed hybrid approach is experimentally investigated using the ischemic stroke lesion segmentation challenge database. This work also presents a detailed investigation among well-known segmentation approaches, like watershed algorithm, region growing technique, principal component analysis, Chan–Vese active contour, and level set approaches, existing in the literature. The results of the experimental work executed using ISLES 2015 challenge dataset confirm that proposed methodology offers superior average values for image similarity indices like Jaccard (78.60%), Dice (88.54%), false positive rate (3.69%), and false negative rate (11.78%). This work also helps to achieve improved value of sensitivity (99.65%), specificity (78.05%), accuracy (91.17%), precision (98.11%), BCR (90.19%), and BER (6.09%).
Breast cancer is one of the common cancers in women community and the early diagnosis of breast cancer will improve the survival rate. Thermography is one of the non-invasive and most efficient screening modality for the breast cancer detection. Extracting the cancerous region/tumor from breast thermal image is widely preferred to have a clear idea about the disease and the infected section. The success of disease prediction and analysis depends mainly on the segmented tool considered to analyse thermograms. In this work, a two stage approach combining the Firefly Algorithm (FA) assisted Kapur's thresholding and Hidden Markov Random Field (HMRF) based segmentation is proposed for the extraction of the region of interest from breast thermal images. The results obtained from the HMRF are then validated with the results of Distance Regularized Level Set (DRLS). From the result, it is observed that, HMRF provides better tumor mass compared to the DRLS with better values of image similarity index.
Image processing is extensively considered in medical field for computer-supported disease assessment. Brain tumor is one of the deadliest cancers for the human community and requires image/signal processing approaches to record and analyze the disease-affected regions. In this work, Cuckoo Search Algorithm (CA) assisted approach is proposed to segment tumor from a two-dimensional Magnetic Resonance Image (MRI). Primarily, Tsallis entropy-monitored multilevel thresholding is implemented for the brain MRI dataset based on CA. Afterward, the skull section is detached by means of an image filtering approach. The skull stripped image is then treated using the image morphological function in order to obtain a smooth image exterior. Lastly, the tumor section is mined using the regularized level set technique. The efficiency and the clinical importance of presented method are confirmed based on the image similarity measures and the statistical measures. Experimental results of the proposed approach offer better values of Jaccard, Dice, precision, sensitivity, and accuracy values. Hence the proposed approach is clinically significant and in future, it can be used to diagnose the brain tumor images.
Automatic and accurate whole-heart and great vessel segmentation from 3D cardiac magnetic resonance (MR) images plays an important role in the computer-assisted diagnosis and treatment of cardiovascular disease. However, this task is very challenging due to ambiguous cardiac borders and large anatomical variations among different subjects. In this paper, we propose a novel densely-connected volumetric convolutional neural network, referred as DenseVoxNet, to automatically segment the cardiac and vascular structures from 3D cardiac MR images. The DenseVoxNet adopts the 3D fully convolutional architecture for effective volume-to-volume prediction. From the learning perspective, our DenseVoxNet has three compelling advantages. First, it preserves the maximum information flow between layers by a densely-connected mechanism and hence eases the network training. Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data. Third, we add auxiliary side paths to strengthen the gradient propagation and stabilize the learning process. We demonstrate the effectiveness of DenseVoxNet by comparing it with the state-of-the-art approaches from HVSMR 2016 challenge in conjunction with MICCAI, and our network achieves the best dice coefficient. We also show that our network can achieve better performance than other 3D ConvNets but with fewer parameters.
Image processing plays an important role in various medical applications to support the computerized disease examination. Brain tumor, such as glioma is one of the life threatening cancers in humans and the premature diagnosis will improve the survival rate. Magnetic Resonance Image (MRI) is the widely considered imaging practice to record the glioma for the clinical study. Due to its complexity and varied modality, brain MRI needs the automated assessment technique. In this paper, a novel methodology based on meta-heuristic optimization approach is proposed to assist the brain MRI examination. This approach enhances and extracts the tumor core and edema sector from the brain MRI integrating the Teaching Learning Based Optimization (TLBO), entropy value, and level set / active contour based segmentation. The proposed method is tested on the images acquired using the Flair, T1C and T2 modalities. The experimental work is implemented and is evaluated using the CEREBRIX and BRAINIX dataset. Further, TLBO assisted approach is validated on the MICCAI brain tumor segmentation (BRATS) challenge 2012 dataset and achieved better values of Jaccard index, dice co-efficient, precision, sensitivity, specificity and accuracy. Hence the proposed segmentation approach is clinically significant.
This paper proposes a fully automatic supervised segmentation technique for segmenting the great vessel and blood pool of pediatric cardiac MRIs of children with Congenital Heart Defects (CHD). CHD affects the overall anatomy of heart, rendering model-based segmentation framework infeasible, unless a large dataset of annotated images is available. However, the cardiac anatomy still retains distinct appearance patterns, which has been exploited in this work. In particular, Total Variation (TV) is introduced for solving the 3D disparity and noise removal problem. This results in homogeneous appearances within anatomical structures which is exploited further in a Random Forest framework. Context-aware appearance models are learnt using Random Forest (RF) for appearance-based prediction of great vessel and blood pool of an unseen subject during testing. We have obtained promising results on the HVSMR16 training dataset in a leave-one-out cross-validation.
The computer-aided diagnosis (CAD) of breast cancer is becoming increasingly a necessity given the exponential growth of performed mammograms. In particular, the breast mass diagnosis and classification arouse nowadays a great interest. Breast cancer is the most common type of cancer and the second leading cause of cancer deaths (after lung cancer) in women and survival rates critically depend on detection in the initial stages. CAD systems are based on three main steps: segmentation, feature extraction and then classification in order to have a final decision. CAD systems are usually characterized by the large volume of the acquired data that must be labelled in a specific way. However, it is not easy to collect labeled patient records. It takes at least 5 years to label a patient record as 'survived' or 'not survived.' What leads to a major problem which is the necessity of an expert to make the labelling operation. That is why the community of statistical learning has attempted to respond to these practical needs by introducing the Semi-Supervised Learning (SSL). For this reason, we have proposed a computer assisted detection system for the diagnosis of this disease based on a particular way on the use of the semi-supervised learning technique using S3VM (Semi Supervised Support Vector Machine) with these different kernel functions. We have made several empirical tests to adapt the parameters of S3VM classifier for better interpretation of mammogram images by changing in each iteration the proportion of labelled data during the training stage and we opted for three different proportions (rarely, low and moderately). Experiments validated DDSM (Digital Database for Screening Mammography ) dataset are very encouraging.
Recently, wireless medical body area network (WMBAN) plays an important role in remote cardiac patient monitoring, intelligent emergency care management system, and ubiquitous mobile healthcare applications. The wearable cardiac monitoring devices used in WMBAN system collect and transmit the vital signs of cardiac patients continuously. Generally, the use of WMBAN technology is restricted by size, power consumption, transmission capacity (bandwidth), and computational loads. Therefore, there is a great demand for low-complexity cardiac signal processing algorithms that can combat some of technical challenges related to pervasive healthcare computing with WMBAN technologies. In this paper, we present low complexity automatic QRS detection algorithm for long-term wearable cardiac monitoring device. The proposed QRS detection method first derives a smooth Shannon energy envelogram (SEE) of the first-derivative of the filtered ECG at the preprocessing stage. The major local maxima (LM) in the smooth SEE indicate the approximate locations of the R-peaks. In the second stage, the proposed HT-based peak-finding logic identifies the locations of the LM by detecting the positive zero-crossings in the HT of the SEE. Finally, the locations of the LM are used as guides to find the accurate locations of the R-peaks in the ECG signal. The proposed method is validated using the standard MIT-BIH arrhythmia database, and achieves an overall sensitivity of 99.86% and positive predictivity of 99.95%. Various experimental results show that the proposed algorithm significantly outperforms other well-known algorithms in case of noisy or pathological signals.
Automatic segmentation of multiple sclerosis (MS) lesions in brain MRI has been widely investigated in recent years with the goal of helping MS diagnosis and patient follow-up. However, the performance of most of the algorithms still falls far below expert expectations. In this paper, we review the main approaches to automated MS lesion segmentation. The main features of the segmentation algorithms are analysed and the most recent important techniques are classified into different strategies according to their main principle, pointing out their strengths and weaknesses and suggesting new research directions. A qualitative and quantitative comparison of the results of the approaches analysed is also presented. Finally, possible future approaches to MS lesion segmentation are discussed.
Sleep apnoea is a very common sleep disorder which can cause symptoms such as daytime sleepiness, irritability and poor concentration. To monitor patients with this sleeping disorder we measured the electrical activity of the heart. The resulting electrocardiography (ECG) signals are both non-stationary and nonlinear. Therefore, we used nonlinear parameters such as approximate entropy, fractal dimension, correlation dimension, largest Lyapunov exponent and Hurst exponent to extract physiological information. This information was used to train an artificial neural network (ANN) classifier to categorize ECG signal segments into one of the following groups: apnoea, hypopnoea and normal breathing. ANN classification tests produced an average classification accuracy of 90%; specificity and sensitivity were 100% and 95%, respectively. We have also proposed unique recurrence plots for the normal, hypopnea and apnea classes. Detecting sleep apnea with this level of accuracy can potentially reduce the need of polysomnography (PSG). This brings advantages to patients, because the proposed system is less cumbersome when compared to PSG.
Details of a proposed new classification for ductal carcinoma in situ (DCIS) are presented. This is based, primarily, on cytonuclear differentiation and, secondarily, on architectural differentiation (cellular polarisation). Three categories are defined. First is poorly differentiated DCIS composed of cells with very pleomorphic, irregularly spaced nuclei, with coarse, clumped chromatin, prominent nucleoli, and frequent mitoses. Architectural differentiation is absent or minimal. The growth pattern is solid or pseudo-cribriform and -micropapillary (without cellular polarisation). Necrosis is usually present. Calcification, when present, is amorphous. Second, at the other end of the spectrum is well-differentiated DCIS, composed of cells with monomorphic, regularly spaced nuclei containing fine chromatin, inconspicuous nucleoli, and few mitoses. The cells show pronounced polarisation with orientation of their apical border towards intercellular spaces usually resulting in cribriform, micropapillary and clinging patterns, although a solid pattern of well-differentiated DCIS also occurs. Necrosis is uncommon. Calcifications, when present, are usually psammomatous. The third category, intermediately differentiated DCIS, is composed of cells showing some pleomorphism but not so marked as in the poorly differentiated group. There is, however, always evidence of polarization around intercellular spaces, although this is not so pronounced as in the well-differentiated group. These two criteria, cytonuclear differentiation and architectural differentiation, have been found to be more consistent throughout a DCIS lesion than previously employed criteria of architectural pattern or the presence or absence of necrosis.
The purpose of this paper is to demonstrate the diagnostic efficacy and therapeutic relevance of video-EEG monitoring in an large patient population with long-term follow-up.
Between October 1990 and May 1997, 400 patients were monitored at the Epilepsy Monitoring Unit (EMU) of the University Hospital in Gent. In all patients, the following parameters were retrospectively examined: reason for referral, tentative diagnosis, prescribed antiepileptic drugs (AEDs), seizure frequency, number of admission days, number of recorded seizures, ictal and interictal EEG, clinical and electroencephalographic diagnosis following the monitoring session. During follow-up visits at the Epilepsy Clinic, we prospectively collected data on different types of treatment and post-monitoring seizure control.
255/400 (64%) patients were referred for refractory epilepsy. 145/400 (36%) patients were evaluated for attacks of uncertain origin. Mean follow-up, available in 225 patients, was 28 months (range: 6-80 months). Mean duration of a single monitoring session was 4 days (range: 2-7 days). Prolonged interictal EEG was recorded in all patients and ictal EEG in 258 (65%) patients. Following the monitoring session, the diagnosis of epilepsy was confirmed in 217 patients. Pseudoseizures were diagnosed in 31 patients (8%). AEDs were started in 19 patients, stopped in 6 and left unchanged in 110. The type and/or number of AEDs was changed in 111 patients. Sixty patients underwent epilepsy surgery. In 48 surgery patients, follow-up data were available, 29 of whom became seizure-free, and 16 of whom experienced a greater than 90% seizure reduction. Vagus nerve stimulation was performed in 11 patients, 2 became seizure-free, and 7 improved markedly. Of the non-invasively treated patients in whom follow-up was available (n = 135), 70 became seizure-free or experienced a greater than 50% reduction in seizure frequency; 51 patients experienced no change in seizure frequency. Outcome was unrelated to the availability of ictal video-EEG recording. In patients with complex partial seizures, seizure control was significantly improved when a well-defined ictal onset zone could be defined during video-EEG monitoring.
Prolonged interictal EEG monitoring is mandatory in the successful management of patients with refractory epilepsy. Ictal video-EEG monitoring is very helpful but not indispensable, except in patients enrolled for presurgical evaluation or suspected of having pseudoseizures.