Infrared thermography (IRT) is a non-invasive, radiation-free imaging technique that uses an infrared (IR) camera to record and produce an image using IR radiation emitted from the body. IRT imaging has shown promise as a screening method for breast cancer, diabetic foot ulcers, and dry eye disease, among other medical disorders. The aim of this systematic review is to present a complete overview of the applications of artificial intelligence (AI) techniques with IRT imaging for medical decision support systems over the course of the last ten years (2013–2024). Several scientific databases, including PubMed, IEEE, and Google Scholar, were searched using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. After meeting the requirements for inclusion, 131 papers were selected. The reviewed studies demonstrated how various AI techniques, including deep learning and classical machine learning, can be used to develop automated diagnosis systems using IRT images. The efficacy of these AI systems differed depending on the medical field; for example, they could identify dry eye disease with 90–100% accuracy, classify diabetic foot ulcers with 85–95% accuracy, and detect breast cancer with 80–100% accuracy. This review highlights the value of IRT imaging in early disease detection, especially when combined with AI techniques. This work discusses challenges in using deep learning (DL) models in healthcare, including data scarcity and ethical considerations. It also, proposes three main recommendations: dataset standardization for ethical data management, clear governance models for ethical practices, and the use of Multimodal Large Language Models (MLLMs) to address explainability issues.

Infrared thermography (IRT) is a non-invasive, radiation-free imaging technique that uses an infrared (IR) camera to record and produce an image using IR radiation emitted from the body. IRT imaging has shown promise as a screening method for breast cancer, diabetic foot ulcers, and dry eye disease, among other medical disorders. The aim of this systematic review is to present a complete overview of the applications of artificial intelligence (AI) techniques with IRT imaging for medical decision support systems over the course of the last ten years (2013-2024). Several scientific databases, including PubMed, IEEE, and Google Scholar, were searched using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. After meeting the requirements for inclusion, 131 papers were selected. The reviewed studies demonstrated how various AI techniques, including deep learning and classical machine learning, can be used to develop automated diagnosis systems using IRT images. The efficacy of these AI systems differed depending on the medical field; for example, they could identify dry eye disease with 90-100% accuracy, classify diabetic foot ulcers with 85-95% accuracy, and detect breast cancer with 80-100% accuracy. This review highlights the value of IRT imaging in early disease detection, especially when combined with AI techniques. This work discusses challenges in using deep learning (DL) models in healthcare, including data scarcity and ethical considerations. It also, proposes three main recommendations: dataset standardization for ethical data management, clear governance models for ethical practices, and the use of Multimodal Large Language Models (MLLMs) to address explainability issues.

Infrared thermography (IRT) is a non-invasive, radiation-free imaging technique that uses an infrared (IR) camera to record and produce an image using IR radiation emitted from the body. IRT imaging has shown promise as a screening method for breast cancer, diabetic foot ulcers, and dry eye disease, among other medical disorders. The aim of this systematic review is to present a complete overview of the applications of artificial intelligence (AI) techniques with IRT imaging for medical decision support systems over the course of the last ten years (2013–2024). Several scientific databases, including PubMed, IEEE, and Google Scholar, were searched using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. After meeting the requirements for inclusion, 131 papers were selected. The reviewed studies demonstrated how various AI techniques, including deep learning and classical machine learning, can be used to develop automated diagnosis systems using IRT images. The efficacy of these AI systems differed depending on the medical field; for example, they could identify dry eye disease with 90–100% accuracy, classify diabetic foot ulcers with 85–95% accuracy, and detect breast cancer with 80–100% accuracy. This review highlights the value of IRT imaging in early disease detection, especially when combined with AI techniques. This work discusses challenges in using deep learning (DL) models in healthcare, including data scarcity and ethical considerations. It also, proposes three main recommendations: dataset standardization for ethical data management, clear governance models for ethical practices, and the use of Multimodal Large Language Models (MLLMs) to address explainability issues.

Fibromyalgia is a soft tissue rheumatism with significant qualitative and quantitative impact on sleep macro and micro architecture. The primary objective of this study is to analyze and identify automatically healthy individuals and those with fibromyalgia using sleep electroencephalography (EEG) signals. The study focused on the automatic detection and interpretation of EEG signals obtained from fibromyalgia patients. In this work, the sleep EEG signals are divided into 15-s and a total of 5358 (3411 healthy control and 1947 fibromyalgia) EEG segments are obtained from 16 fibromyalgia and 16 normal subjects. Our developed model has advanced multilevel feature extraction architecture and hence, we used a new feature extractor called GluPat, inspired by the glucose chemical, with a new pooling approach inspired by the D’hondt selection system. Furthermore, our proposed method incorporated feature selection techniques using iterative neighborhood component analysis and iterative Chi2 methods. These selection mechanisms enabled the identification of discriminative features for accurate classification. In the classification phase, we employed a support vector machine and k-nearest neighbor algorithms to classify the EEG signals with leave-one-record-out (LORO) and tenfold cross-validation (CV) techniques. All results are calculated channel-wise and iterative majority voting is used to obtain generalized results. The best results were determined using the greedy algorithm. The developed model achieved a detection accuracy of 100% and 91.83% with a tenfold and LORO CV strategies, respectively using sleep stage (2 + 3) EEG signals. Our generated model is simple and has linear time complexity.

Chronic kidney disease (CKD) is a continuing loss of kidney function, and early detection of this disease is fundamental to halting its progression to end-stage disease. Numerous methods have been proposed to detect CKD, mainly focusing on classification based upon peripheral clinical parameters and quantitative ultrasound parameters that must be manually calculated, or on shear wave elastography. No studies have been found that detect the presence or absence of CKD based solely from one B-mode ultrasound image. In this work, we propose an automated system to detect chronic kidney disease utilizing only the automatic extraction of features from a B-mode ultrasound image of the kidney, with a database of 405 images. Higher-order bispectrum and cumulants, and elongated quinary patterns, are extracted from each image to provide a final total of 24,480 features per image. These features were subjected to a locality sensitive discriminant analysis (LSDA) technique, which provides 30 LSDA coefficients. The coefficients were arranged according to theirtvalue and inserted into various classifiers, to yield the best diagnostic accuracy using the least number of features. The best performance was obtained using a support vector machine and a radial basis function, utilizing only five features, resulting in an accuracy of 99.75%, a sensitivity of 100%, and a specificity of 99.57%. Based upon these findings, it is evident that the technique accurately and automatically identifies subjects with and without CKD from B-mode ultrasound images.

The diagnosis of glaucoma plays a critical role in the management and treatment of this vision-threatening disease. Glaucoma is a group of eye diseases that cause blindness by damaging the optic nerve at the back of the eye. Often called "silent thief of sight", it exhibits no symptoms during the early stages. Therefore, early detection is crucial to prevent vision loss. With the rise of Artificial Intelligence (AI), particularly Deep Learning (DL) techniques, Computer-Aided Diagnosis (CADx) systems have emerged as promising tools to assist clinicians in accurately diagnosing glaucoma early. This paper aims to provide a comprehensive overview of AI techniques utilized in CADx systems for glaucoma diagnosis. Through a detailed analysis of current literature, we identify key gaps and challenges in these systems, emphasizing the need for improved safety, reliability, interpretability, and explainability. By identifying research gaps, we aim to advance the field of CADx systems especially for the early diagnosis of glaucoma, in order to prevent any potential loss of vision.

Computer-Aided Diagnosis (CADx) systems are safety-critical systems that provide automated medical diagnoses based on their input data. They are Artificial Intelligence based systems which make use of Machine Learning or Deep Learning techniques to differentiate between healthy and unhealthy medical images, as well as, physiological signals acquired from patients. Although current CADx systems offer many advantages in diagnostics, validation is still a challenge, i.e. ensuring that no false negative happens while limiting the occurrence of false positives. This is a major concern since such safety-critical systems have to be verified before deployment into a clinical environment. For that reason, this paper aims to improve the reliability of the CADx systems by adding a Human Machine Interface (HMI) component to enhance the data acquisition process and providing a safety-related framework which includes the HMI/CADx system life cycle to bridge the identified gaps.

Deep learning (DL) is seen as an inevitable building block for perceiving the environment with sufficient detail and accuracy as required by automated driving functions. Despite this, its black-box nature and the therewith intertwined unpredictability still hinders its use in safety-critical systems. As such, this work addresses the problem of making this seemingly unpredictable nature measurable by providing a risk-based verification strategy, such as required by ISO 21448. In detail, a method is developed to break down acceptable risk into quantitative performance targets of individual DL-based components along the perception architecture. To verify these targets, the DL input space is split into areas according to the dimensions of a fine-grained operational design domain $(\mu \mathbf{ODD})$ . As it is not feasible to reach full test coverage, the strategy suggests to distribute test efforts across these areas according to the associated risk. Moreover, the testing approach provides answers with respect to how much test coverage and confidence in the test result is required and how these figures relate to safety integrity levels (SILs).

Machine Learnt Models (MLMs) are now commonly used in self-driving cars, particularly for tasks such as object detection and classification within the perception pipeline. The failure of such models to perform as intended could lead to hazardous events such as failing to stop for a pedestrian at a crossing. It is therefore crucial that the safety of the MLM can be proactively assured and should be driven by explicit and concrete safety requirements. In our previous work, we defined a process that integrates the development and assurance activities for MLMs within safety-related systems. This is used to incrementally generate the safety argument and evidence. In this paper, we apply the approach to pedestrian detection at crossings and provide an evaluation using the publicly available JAAD data set. In particular, we focus on the elicitation and analysis of ML safety requirements and how such requirements should drive the assurance activities within the data management and model learning phases. We explain the benefits of the approach and identify outstanding challenges in the context of self-driving cars.

The thyroid is the chief hormonal gland that controls the growth, metabolism, and maturation of the body. However, the function of the thyroid gland could be disrupted if it produces too much or too little hormones. Furthermore, there could be abnormal growth in thyroid cell tissue, leading to the formation of a benign or malignant thyroid lesion. Ultrasound is a typical non-invasive diagnosis approach to check for cancerous thyroid lesions. However, the visual interpretation of the ultrasound thyroid images is challenging and time-consuming. Hence, a feature engineering model is proposed to overcome these challenges. We propose to transform image pixel intensity values into high dimensional structured data set before fitting a Regression analysis framework to estimate kernel parameters for an image filter model. We then adopt a Bayesian network inference to estimate a subset for the textural features with a significant conditional dependency in the classification of thyroid lesions. The analysis of the proposed feature engineering model showed that the classification performance had an overall significant improvement over other image filter models. We achieve 96.00% classification accuracy with a sensitivity and specificity of 99.64% and 90.23% respectively for a filter size of 13 x 13. The analysis of results indicate that the diagnosis of ultrasound images thyroid nodules is significantly boosts by adaptively learning filter parameters for feature engineering model. (C) 2020 Elsevier B.V. All rights reserved.

The increased demand of Deep Neural Networks (DNNs) in safety-critical systems, such as autonomous vehicles, leads to increasing importance of training data suitability. Firstly, we focus on how to extract the relevant data content for ensuring DNN reliability. Then, we identify error categories and propose mitigation measures with emphasis on data suitability. Despite all efforts to boost data suitability, not all possible variations of a real application can be identified. Hence, we analyse the case of unknown out-of-distribution data. In this case, we suggest to complement data suitability with online anomaly detection using FACER that supervises the behaviour of the DNN.

Epilepsy is a chronic illness of the brain characterized by recurring seizure attacks. Electroencephalogram (EEG) can record the electrical activity of the brain and is extensively used to analyze and diagnose epileptic seizures. However, the EEG signals are highly non-linear and chaotic and are difficult to analyze due to their small magnitude. Hence, empirical mode decomposition (EMD), a non-linear technique, has been widely adopted to capture the subtle changes present in the EEG signals. Hence, it is an added advantage to develop an automated computer-aided diagnostic (CAD) system to detect the different brain activities from the EEG signals using machine learning approaches. In this paper, we focus on the previous works which have used the EMD technique in the automated detection of normal or epileptic EEG signals.

Electroencephalography (EEG) is the graphical recording of electrical activity along the scalp. The EEG signal monitors brain activity noninvasively with a high accuracy of milliseconds and provides valuable discernment about the brain’s state. It is also sensitive in detecting spikes in epilepsy. Computer-aided diagnosis (CAD) tools allow epilepsy to be diagnosed by evading invasive methods. This paper presents a novel CAD system for epilepsy using other linear features together with Hjorth’s nonlinear features such as mobility, complexity, activity and Kolmogorov complexity. The proposed method uses MATLAB software to extract the nonlinear features from the EEG data. The optimal features are selected using the statistical analysis, ANOVA (analysis of variance) test for classification. Once selected, they are fed into the decision tree (DT) for the classification of the different epileptic classes. The proposed method affirms that four nonlinear features, Kolmogorov complexity, singular value decomposition, mobility and permutation entropy are sufficient to provide the highest accuracy of 93%, sensitivity of 97%, specificity of 88% and positive predictive value (PPV) of 94%, with the DT classifier. The mean value is the highest in the ictal stage for the Kolmogorov complexity proving it to have the best variation. It also has the highest [Formula: see text]-value of 300.439 portraying it to be the best parameter that is favourable for the clinical diagnosis of epilepsy, when used together with the DT classifier, for a duration of 23.6[Formula: see text]s of EEG data.

Celiac disease is a common immune response when gluten is ingested. Over time, this response will impair the lining of the small intestine and result in malabsorption. This could bring about critical health complications. However, the symptoms of celiac disease vary and hence, it is relatively challenging to make an accurate diagnosis. This results in a high percentage of misdiagnoses. Therefore, a computer-aided detection (CAD) system is proposed to overcome the challenges. Hence, this study employed the discrete wavelet transform (DWT) to decompose the video images, after which textural and nonlinear features were extracted. Thereafter, the particle swarm optimization (PSO) was performed to choose 30 optimal features for classification. An accuracy level of 86.47%, and sensitivity and specificity of 88.43% and 84.60%, respectively, was achieved with the 10-fold cross-validation strategy. Moreover, an accuracy of 85.91% was attained with the leave-one-out cross-validation (LOOCV) technique. This methodology demonstrates potential for accurately identifying celiac disease. It can therefore be noted that the developed CAD system may improve the diagnostic performance in the detection of celiac disease, and thus reduce the number of misdiagnoses.

Congestive heart failure (CHF) is a chronic heart condition associated with debilitating symptoms that result in increased mortality, morbidity, healthcare expenditure and decreased quality of life. Electrocardiogram (ECG) is a noninvasive and simple diagnostic method that may demonstrate detectable changes in CHF. However, manual diagnosis of ECG signal is often subject to errors due to the small amplitude and duration of the ECG signals, and in isolation, is neither sensitive nor specific for CHF diagnosis. An automated computer-aided system may enhance the diagnostic objectivity and reliability of ECG signals in CHF. We present an 11-layer deep convolutional neural network (CNN) model for CHF diagnosis herein. This proposed CNN model requires minimum pre-processing of ECG signals, and no engineered features or classification are required. Four different sets of data (A, B, C and D) were used to train and test the proposed CNN model. Out of the four sets, Set B attained the highest accuracy of 98.97%, specificity and sensitivity of 99.01% and 98.87% respectively. The proposed CNN model can be put into practice and serve as a diagnostic aid for cardiologists by providing more objective and faster interpretation of ECG signals.

Epilepsy is a common neurological condition that can occur in anyone at any age. Electroencephalogram (EEG) signals of non-focal (NF) and focal (F) types contain brain activity information that can be used to identify areas affected by seizures. Generally, F EEG signals are recorded from the epileptic part of the brain, while NF EEG signals are recorded from brain regions unaffected by epilepsy. It is essential to correctly detect F EEG signals, when and where they occur, as focal epilepsy can be successfully treated by surgical means. However, all EEG signals are complex and require highly trained personnel for right interpretation. To overcome the associated challenges, in this study a computer-aided detection (CAD) system to aid in the detection of F EEG signals has been developed, and the performance of nonlinear features for differentiating F and NF EEG signals is compared. Moreover, it is noted that nonlinear features can effectively capture concealed patterns and rhythms contained in the EEG signals. Overall, it was found that the CAD system will be useful to clinicians in providing an accurate and objective paradigm for localization of the epileptogenic area.

Fibromyalgia is an intense musculoskeletal pain causing sleep, fatigue, and mood problems. Sleep studies have suggested that 70%-80% of fibromyalgia patients complain of non-restorative sleep. The abnormalities in sleep have been implicated as both a cause and effect of the disease. In this paper, the electroencephalogram (EEG) signals of sleep stages 2 and 3 are used to classify the normal and fibromyalgia classes automatically. We have used various nonlinear parameters, namely sample entropy (SampEn), fractal dimension (FD), higher order spectra (HOS), largest Lyapunov exponent (LLE), Kolmogorov complexity (KC), Hurst exponent (HE), energy, and power in various frequency bands from the EEG signals. Then these features are subjected to Student's t-test to select the clinically significant features, and are classified using the support vector machine (SVM) classifier. Our proposed method can classify normal and fibromyalgia subjects using the stage 2 sleep EEG signals with an accuracy of 96.15%, sensitivity and specificity of 96.88% and 95.65%, respectively. Performance of the developed system can be improved further by adding more subjects in each class, and can be employed for clinical use.

Coronary artery disease (CAD) is the most common cause of heart disease globally. This is because there is no symptom exhibited in its initial phase until the disease progresses to an advanced stage. The electrocardiogram (ECG) is a widely accessible diagnostic tool to diagnose CAD that captures abnormal activity of the heart. However, it lacks diagnostic sensitivity. One reason is that, it is very challenging to visually interpret the ECG signal due to its very low amplitude. Hence, identification of abnormal ECG morphology by clinicians may be prone to error. Thus, it is essential to develop a software which can provide an automated and objective interpretation of the ECG signal. This paper proposes the implementation of long short-term memory (LSTM) network with convolutional neural network (CNN) to automatically diagnose CAD ECG signals accurately. Our proposed deep learning model is able to detect CAD ECG signals with a diagnostic accuracy of 99.85% with blindfold strategy. The developed prototype model is ready to be tested with an appropriate huge database before the clinical usage.

Higher-order spectra (HOS) is an efficient feature extraction method used in various biomedical applications such as stages of sleep, epilepsy detection, cardiac abnormalities, and affective computing. The motive of this work was to explore the application of HOS for an automated diagnosis of Parkinson's disease (PD) using electroencephalography (EEG) signals. Resting-state EEG signals collected from 20 PD patients with medication and 20 age-matched normal subjects were used in this study. HOS bispectrum features were extracted from the EEG signals. The obtained features were ranked using t value, and highly ranked features were used in order to develop the PD Diagnosis Index (PDDI). The PDDI is a single value, which can discriminate the two classes. Also, the ranked features were fed one by one to the various classifiers, namely decision tree (DT), fuzzy K-nearest neighbor (FKNN), K-nearest neighbor (KNN), naive bayes (NB), probabilistic neural network (PNN), and support vector machine (SVM), to choose the best classifier using minimum number of features. We have obtained an optimum mean classification accuracy of 99.62%, mean sensitivity and specificity of 100.00 and 99.25%, respectively, using the SVM classifier. The proposed PDDI can aid the clinicians in their diagnosis and help to test the efficacy of drugs.

Diabetic foot is the most common problem among diabetic patients, mainly due to peripheral vascular and neuropathy induced capillary perfusion changes. These pathogenic factors cause superficial temperature changes that can be qualitatively and visually documented using infrared thermography (IRT). Hence, IRT can potentially be used to evaluate the diabetic foot. However, it is tedious to manually interpret these subtle temperature variations by inspecting the feet thermal image. Therefore, an automated system to detect diabetic foot with and without neuropathy is proposed. In this study, 51 healthy individuals and 66 diabetic patients (33 with and 33 without neuropathy) are considered. The segmented plantar foot thermograms are decomposed into coefficients using double density-dual tree-complex wavelet transform (DD-DT-CWT). Several entropy and texture features are extracted from the decomposed images of left, right and bilateral foot. These features are reduced using various dimensionality reduction techniques and subsequently ranked using F-values. The ranked features are fed individually into the different classifiers one by one. The developed system yielded 93.16% accuracy, 90.91% sensitivity and 98.04% specificity using only four locality sensitive discriminant analysis (LSDA) features obtained from bilateral foot thermal images with k-nearest neighbour (kNN) classifier. This automated diabetic foot detection system can be introduced in polyclinics and hospitals to clinically support the clinicians to confirm their manual diabetic foot diagnosis.