Ultrasound-Based Image Analysis for Predicting Carotid Artery Stenosis Risk: A Comprehensive Review of the Problem, Techniques, Datasets, and Future Directions.

The carotid artery is a major blood vessel that supplies blood to the brain. Plaque buildup in the arteries can lead to cardiovascular diseases such as atherosclerosis, stroke, ruptured arteries, and even death. Both invasive and non-invasive methods are used to detect plaque buildup in the arteries, with ultrasound imaging being the first line of diagnosis. This paper presents a comprehensive review of the existing literature on ultrasound image analysis methods for detecting and characterizing plaque buildup in the carotid artery. The review includes an in-depth analysis of datasets; image segmentation techniques for the carotid artery plaque area, lumen area, and intima-media thickness (IMT); and plaque measurement, characterization, classification, and stenosis grading using deep learning and machine learning. Additionally, the paper provides an overview of the performance of these methods, including challenges in analysis, and future directions for research.

Electroencephalography Signal Processing: A Comprehensive Review and Analysis of Methods and Techniques.

The electroencephalography (EEG) signal is a noninvasive and complex signal that has numerous applications in biomedical fields, including sleep and the brain-computer interface. Given its complexity, researchers have proposed several advanced preprocessing and feature extraction methods to analyze EEG signals. In this study, we analyze a comprehensive review of numerous articles related to EEG signal processing. We searched the major scientific and engineering databases and summarized the results of our findings. Our survey encompassed the entire process of EEG signal processing, from acquisition and pretreatment (denoising) to feature extraction, classification, and application. We present a detailed discussion and comparison of various methods and techniques used for EEG signal processing. Additionally, we identify the current limitations of these techniques and analyze their future development trends. We conclude by offering some suggestions for future research in the field of EEG signal processing.

Deep Survival Analysis With Clinical Variables for COVID-19.

OBJECTIVE: Millions of people have been affected by coronavirus disease 2019 (COVID-19), which has caused millions of deaths around the world. Artificial intelligence (AI) plays an increasing role in all areas of patient care, including prognostics. This paper proposes a novel predictive model based on one dimensional convolutional neural networks (1D CNN) to use clinical variables in predicting the survival outcome of COVID-19 patients. METHODS AND PROCEDURES: We have considered two scenarios for survival analysis, 1) uni-variate analysis using the Log-rank test and Kaplan-Meier estimator and 2) combining all clinical variables ([Formula: see text]=44) for predicting the short-term from long-term survival. We considered the random forest (RF) model as a baseline model, comparing to our proposed 1D CNN in predicting survival groups. RESULTS: Our experiments using the univariate analysis show that nine clinical variables are significantly associated with the survival outcome with corrected p < 0.05. Our approach of 1D CNN shows a significant improvement in performance metrics compared to the RF and the state-of-the-art techniques (i.e., 1D CNN) in predicting the survival group of patients with COVID-19. CONCLUSION: Our model has been tested using clinical variables, where the performance is found promising. The 1D CNN model could be a useful tool for detecting the risk of mortality and developing treatment plans in a timely manner. CLINICAL IMPACT: The findings indicate that using both Heparin and Exnox for treatment is typically the most useful factor in predicting a patient's chances of survival from COVID-19. Moreover, our predictive model shows that the combination of AI and clinical data can be applied to point-of-care services through fast-learning healthcare systems.

Survey of Explainable AI Techniques in Healthcare.

Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the medical field, any judgment or decision is fraught with risk. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient's symptoms and/or an examination. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.

Robust Brain Age Estimation Based on sMRI via Nonlinear Age-Adaptive Ensemble Learning.

Precise prediction on brain age is urgently needed by many biomedical areas including mental rehabilitation prognosis as well as various medicine or treatment trials. People began to realize that contrasting physical (real) age and predicted brain age can help to highlight brain issues and evaluate if patients' brains are healthy or not. Such age prediction is often challenging for single model-based prediction, while the conditions of brains vary drastically over age. In this work, we present an age-adaptive ensemble model that is based on the combination of four different machine learning algorithms, including a support vector machine (SVR), a convolutional neural network (CNN) model, and the popular GoogLeNet and ResNet deep networks. The ensemble model proposed here is nonlinearly adaptive, where age is taken as a key factor in the nonlinear combination of various single-algorithm-based independent models. In our age-adaptive ensemble method, the weights of each model are learned automatically as nonlinear functions over age instead of fixed values, while brain age estimation is based on such an age-adaptive integration of various single models. The quality of the model is quantified by the mean absolute errors (MAE) and spearman correlation between the predicted age and the actual age, with the least MAE and the highest Spearman correlation representing the highest accuracy in age prediction. By testing on the Predictive Analysis Challenge 2019 (PAC 2019) dataset, our novel ensemble model has achieved a MAE down to 3.19, which is a significantly increased accuracy in this brain age competition. If deployed in the real world, our novel ensemble model having an improved accuracy could potentially help doctors to identify the risk of brain diseases more accurately and quickly, thus helping pharmaceutical companies develop drugs or treatments precisely, and potential offer a new powerful tool for researchers in the field of brain science.

Gaze Estimation Approach Using Deep Differential Residual Network.

Gaze estimation, which is a method to determine where a person is looking at given the person's full face, is a valuable clue for understanding human intention. Similarly to other domains of computer vision, deep learning (DL) methods have gained recognition in the gaze estimation domain. However, there are still gaze calibration problems in the gaze estimation domain, thus preventing existing methods from further improving the performances. An effective solution is to directly predict the difference information of two human eyes, such as the differential network (Diff-Nn). However, this solution results in a loss of accuracy when using only one inference image. We propose a differential residual model (DRNet) combined with a new loss function to make use of the difference information of two eye images. We treat the difference information as auxiliary information. We assess the proposed model (DRNet) mainly using two public datasets (1) MpiiGaze and (2) Eyediap. Considering only the eye features, DRNet outperforms the state-of-the-art gaze estimation methods with angular-error of 4.57 and 6.14 using MpiiGaze and Eyediap datasets, respectively. Furthermore, the experimental results also demonstrate that DRNet is extremely robust to noise images.

Efficient Quantum Image Classification Using Single Qubit Encoding.

The domain of image classification has been seen to be dominated by high-performing deep-learning (DL) architectures. However, the success of this field, as seen over the past decade, has resulted in the complexity of modern methodologies scaling exponentially, commonly requiring millions of parameters. Quantum computing (QC) is an active area of research aimed toward greatly reducing problems of complexity faced in classical computing. With growing interest toward quantum machine learning (QML) for applications of image classification, many proposed algorithms require usage of numerous qubits. In the noisy intermediate-scale quantum (NISQ) era, these circuits may not always be feasible to execute effectively; therefore, we should aim to use each qubit as effectively and efficiently as possible, before adding additional qubits. This article proposes a new single-qubit-based deep quantum neural network for image classification that mimics traditional convolutional neural network (CNN) techniques, resulting in a reduced number of parameters compared with previous works. Our aim is to prove the concept of the initial proposal by demonstrating classification performance of the single-qubit-based architecture, as well as to provide a tested foundation for further development. To demonstrate this, our experiments were conducted using various datasets including MNIST, Fashion-MNIST, and ORL face datasets. To further our proposal in the context of the NISQ era, our experiments were intentionally conducted in noisy simulation environments. Initial test results appear promising, with classification accuracies of 94.6%, 89.5%, and 82.5% achieved on the subsets of MNIST, FMNIST, and ORL face datasets, respectively. In addition, proposals for further investigation and development were considered, where it is hoped that these initial results can be improved.

Private Facial Prediagnosis as an Edge Service for Parkinson's DBS Treatment Valuation.

Facial phenotyping for medical prediagnosis has recently been successfully exploited as a novel way for the preclinical assessment of a range of rare genetic diseases, where facial biometrics is revealed to have rich links to underlying genetic or medical causes. In this paper, we aim to extend this facial prediagnosis technology for a more general disease, Parkinson's Diseases (PD), and proposed an Artificial-Intelligence-of-Things (AIoT) edge-oriented privacy-preserving facial prediagnosis framework to analyze the treatment of Deep Brain Stimulation (DBS) on PD patients. In the proposed framework, a novel edge-based privacy-preserving framework is proposed to implement private deep facial diagnosis as a service over an AIoT-oriented information theoretically secure multi-party communication scheme, while data privacy has been a primary concern toward a wider exploitation of Electronic Health and Medical Records (EHR/EMR) over cloud-based medical services. In our experiments with a collected facial dataset from PD patients, for the first time, we proved that facial patterns could be used to evaluate the facial difference of PD patients undergoing DBS treatment. We further implemented a privacy-preserving information theoretical secure deep facial prediagnosis framework that can achieve the same accuracy as the non-encrypted one, showing the potential of our facial prediagnosis as a trustworthy edge service for grading the severity of PD in patients.

Convolutional Neural Network-Based Automatic Classification of Colorectal and Prostate Tumor Biopsies Using Multispectral Imagery: System Development Study.

BACKGROUND: Colorectal and prostate cancers are the most common types of cancer in men worldwide. To diagnose colorectal and prostate cancer, a pathologist performs a histological analysis on needle biopsy samples. This manual process is time-consuming and error-prone, resulting in high intra- and interobserver variability, which affects diagnosis reliability. OBJECTIVE: This study aims to develop an automatic computerized system for diagnosing colorectal and prostate tumors by using images of biopsy samples to reduce time and diagnosis error rates associated with human analysis. METHODS: In this study, we proposed a convolutional neural network (CNN) model for classifying colorectal and prostate tumors from multispectral images of biopsy samples. The key idea was to remove the last block of the convolutional layers and halve the number of filters per layer. RESULTS: Our results showed excellent performance, with an average test accuracy of 99.8% and 99.5% for the prostate and colorectal data sets, respectively. The system showed excellent performance when compared with pretrained CNNs and other classification methods, as it avoids the preprocessing phase while using a single CNN model for the whole classification task. Overall, the proposed CNN architecture was globally the best-performing system for classifying colorectal and prostate tumor images. CONCLUSIONS: The proposed CNN architecture was detailed and compared with previously trained network models used as feature extractors. These CNNs were also compared with other classification techniques. As opposed to pretrained CNNs and other classification approaches, the proposed CNN yielded excellent results. The computational complexity of the CNNs was also investigated, and it was shown that the proposed CNN is better at classifying images than pretrained networks because it does not require preprocessing. Thus, the overall analysis was that the proposed CNN architecture was globally the best-performing system for classifying colorectal and prostate tumor images.

Iterative Bayesian denoising based on variance stabilization using Contourlet Transform with Sharp Frequency Localization: application to EFTEM images.

BACKGROUND: Due to the presence of high noise level in tomographic series of energy filtered transmission electron microscopy (EFTEM) images, alignment and 3D reconstruction steps become so difficult. To improve the alignment process which will in turn allow a more accurate and better three dimensional tomography reconstructions, a preprocessing step should be applied to the EFTEM data series. RESULTS: Experiments with real EFTEM data series at low SNR, show the feasibility and the accuracy of the proposed denoising approach being competitive with the best existing methods for Poisson image denoising. The effectiveness of the proposed denoising approach is thanks to the use of a nonparametric Bayesian estimation in the Contourlet Transform with Sharp Frequency Localization Domain (CTSD) and variance stabilizing transformation (VST). Furthermore, the optimal inverse Anscome transformation to obtain the final estimate of the denoised images, has allowed an accurate tomography reconstruction. CONCLUSION: The proposed approach provides qualitative information on the 3D distribution of individual chemical elements on the considered sample.

Automatic Detection and Classification of Audio Events for Road Surveillance Applications.

This work investigates the problem of detecting hazardous events on roads by designing an audio surveillance system that automatically detects perilous situations such as car crashes and tire skidding. In recent years, research has shown several visual surveillance systems that have been proposed for road monitoring to detect accidents with an aim to improve safety procedures in emergency cases. However, the visual information alone cannot detect certain events such as car crashes and tire skidding, especially under adverse and visually cluttered weather conditions such as snowfall, rain, and fog. Consequently, the incorporation of microphones and audio event detectors based on audio processing can significantly enhance the detection accuracy of such surveillance systems. This paper proposes to combine time-domain, frequency-domain, and joint time-frequency features extracted from a class of quadratic time-frequency distributions (QTFDs) to detect events on roads through audio analysis and processing. Experiments were carried out using a publicly available dataset. The experimental results conform the effectiveness of the proposed approach for detecting hazardous events on roads as demonstrated by 7% improvement of accuracy rate when compared against methods that use individual temporal and spectral features.

Unsupervised Learning for Monaural Source Separation Using Maximization⁻Minimization Algorithm with Time⁻Frequency Deconvolution.

This paper presents an unsupervised learning algorithm for sparse nonnegative matrix factor time⁻frequency deconvolution with optimized fractional ß-divergence. The ß-divergence is a group of cost functions parametrized by a single parameter ß. The Itakura⁻Saito divergence, Kullback⁻Leibler divergence and Least Square distance are special cases that correspond to ß=0, 1, 2, respectively. This paper presents a generalized algorithm that uses a flexible range of ß that includes fractional values. It describes a maximization⁻minimization (MM) algorithm leading to the development of a fast convergence multiplicative update algorithm with guaranteed convergence. The proposed model operates in the time⁻frequency domain and decomposes an information-bearing matrix into two-dimensional deconvolution of factor matrices that represent the spectral dictionary and temporal codes. The deconvolution process has been optimized to yield sparse temporal codes through maximizing the likelihood of the observations. The paper also presents a method to estimate the fractional ß value. The method is demonstrated on separating audio mixtures recorded from a single channel. The paper shows that the extraction of the spectral dictionary and temporal codes is significantly more efficient by using the proposed algorithm and subsequently leads to better source separation performance. Experimental tests and comparisons with other factorization methods have been conducted to verify its efficacy.

Exploration of unsupervised feature selection methods to predict chronological age of individuals by utilising CpG dinucleotics from whole blood.

Identification of the age of individuals from epigenetic biomarkers can reveal vital information for criminal investigation, disease prevention, and extension of life. DNA methylation changes are highly associated with chronological age and the process of disease development. Computational methods such as clustering, feature selection and regression can be utilised to construct quantitative model of aging. In this study, we utilised 473034 CpG biomarkers from whole blood of 656 individuals aged 19 to 101 to construct predictive models and we treat the development of this age predictive model as extremely high-dimensional regression problem that is relatively understudied. Unlike semi-supervised and supervised feature selection methods, unsupervised feature selection methods are generally good at removing irrelevant features that can act as noise. In this study, along with the entire feature set, four different unsupervised feature selection methods (USFSMs) are therefore considered for the quantitative prediction of human ages. Since USFSMs are independent of any predictive method, support vector regression is then used to evaluate the prediction performances of the unsupervised feature selection methods. We proposed a novel k-means based unsupervised feature selection method to predict human ages by utilising CpG dinucleotides. Experimental results have validated the effectiveness of the proposed method as the optimum number of the CpG dinucleotides is found to be only 41 that corresponds to only 0.0087% of the entire feature space. To the best of our knowledge, this is the first study that presents exploration and comprehensive comparison of USFSMs in very high dimensional regression problems, particularly in epigenetic biomedical domain for the prediction of chronological age from changes in DNA methylation.

Role for 2D image generated 3D face models in the rehabilitation of facial palsy.

The outcome for patients diagnosed with facial palsy has been shown to be linked to rehabilitation. Dense 3D morphable models have been shown within the computer vision to create accurate representations of human faces even from single 2D images. This has the potential to provide feedback to both the patient and medical expert dealing with the rehabilitation plan. It is proposed that a framework for the creation and measuring of patient facial movement consisting of a hybrid 2D facial landmark fitting technique which shows better accuracy in testing than current methods and 3D model fitting.

Multi Texture Analysis of Colorectal Cancer Continuum Using Multispectral Imagery.

PURPOSE: This paper proposes to characterize the continuum of colorectal cancer (CRC) using multiple texture features extracted from multispectral optical microscopy images. Three types of pathological tissues (PT) are considered: benign hyperplasia, intraepithelial neoplasia and carcinoma. MATERIALS AND METHODS: In the proposed approach, the region of interest containing PT is first extracted from multispectral images using active contour segmentation. This region is then encoded using texture features based on the Laplacian-of-Gaussian (LoG) filter, discrete wavelets (DW) and gray level co-occurrence matrices (GLCM). To assess the significance of textural differences between PT types, a statistical analysis based on the Kruskal-Wallis test is performed. The usefulness of texture features is then evaluated quantitatively in terms of their ability to predict PT types using various classifier models. RESULTS: Preliminary results show significant texture differences between PT types, for all texture features (p-value < 0.01). Individually, GLCM texture features outperform LoG and DW features in terms of PT type prediction. However, a higher performance can be achieved by combining all texture features, resulting in a mean classification accuracy of 98.92%, sensitivity of 98.12%, and specificity of 99.67%. CONCLUSIONS: These results demonstrate the efficiency and effectiveness of combining multiple texture features for characterizing the continuum of CRC and discriminating between pathological tissues in multispectral images.

Unsupervised selection of RV144 HIV vaccine-induced antibody features correlated to natural killer cell-mediated cytotoxic reactions.

HIV-1 vaccine injection has been shown less effective due to the diversity of antigens. Increasing the knowledge of the associations between immune system and virus would ultimately result in producing effective vaccines against HIV-1 virus. To increase the understanding of immunological information, computational models can be utilised to construct predictive models. The aim of this study is, therefore, to predict the effect of antibody features (IgGs) and primary Natural Killing (NK) cells' cytotoxic activities on RV144 vaccine recipients and to disclose the functional relationship between immune system and HIV virus. The RV144 vaccine data set contains 100 data samples in which 20 of them are the placebo samples and 80 of them are the vaccine injected samples. Each data sample has twenty antibody features that consist of features related to IgG subclass and antigen specificity. In this paper, five different unsupervised feature selection methods (USFSMs) are utilised in order to identify the discriminating antibody features as USFSMs are regarded as unbiased approach. Then, the support vector based methods are utilised to assess association between cellular cytotoxicity by Natural Killer (NK) cells and cells that release glycoprotein (gp)120 antibody. The results yield high correlation coefficient as much as 0.48 and 0.65 for classificationthe support vector regression (SVR) and classification (SVM) predictive models, respectively.

Pigment network-based skin cancer detection.

Diagnosing skin cancer in its early stages is a challenging task for dermatologists given the fact that the chance for a patient's survival is higher and hence the process of analyzing skin images and making decisions should be time efficient. Therefore, diagnosing the disease using automated and computerized systems has nowadays become essential. This paper proposes an efficient system for skin cancer detection on dermoscopic images. It has been shown that the statistical characteristics of the pigment network, extracted from the dermoscopic image, could be used as efficient discriminating features for cancer detection. The proposed system has been assessed on a dataset of 200 dermoscopic images of the `Hospital Pedro Hispano' [1] and the results of cross-validation have shown high detection accuracy.

Texture analysis for colorectal tumour biopsies using multispectral imagery.

Colorectal cancer is one of the most common cancers in the world. As part of its diagnosis, a histological analysis is often run on biopsy samples. Multispecral imagery taken from cancer tissues can be useful to capture more meaningful features. However, the resulting data is usually very large having a large number of varying feature types. This papers aims to investigate and compare the performances of multispectral imagery taken from colorectal biopsies using different techniques for texture feature extraction inclduing local binary patterns, Haraclick features and local intensity order patterns. Various classifiers such as Support Vector Machine and Random Forest are also investigated. The results show the superiority of multispectral imaging over the classical panchromatic approach. In the multispectral imagery's analysis, the local binary patterns combined with Support Vector Machine classifier gives very good results achieving an accuracy of 91.3%.

Comparison of unsupervised feature selection methods for high-dimensional regression problems in prediction of peptide binding affinity.

Identification of robust set of predictive features is one of the most important steps in the construction of clustering, classification and regression models from many thousands of features. Although there have been various attempts to select predictive feature sets from high-dimensional data sets in classification and clustering, there is a limited attempt to study it in regression problems. As semi-supervised and supervised feature selection methods tend to identify noisy features in addition to discriminative variables, unsupervised feature selection methods (USFSMs) are generally regarded as more unbiased approach. Therefore, in this study, along with the entire feature set, four different USFSMs are considered for the quantitative prediction of peptide binding affinities being one of the most challenging post-genome regression problems of very high-dimension comparted to extremely small size of samples. As USFSMs are independent of any predictive method, support vector regression was then utilised to assess the quality of prediction. Given three different peptide binding affinity data sets, the results suggest that the regression performance of USFMs depends generally on the datasets. There is no particular method that yields the best performance compared to their performances in the classification problems. However, a closer investigation of the results appears to suggest that the spectral regression-based approach yields slightly better performance. To the best of our knowledge, this is the first study that presents comprehensive comparison of USFSMs in such high-dimensional regression problems, particularly in biological domain with an application in the prediction of peptide binding affinity, and provides a number of practical suggestions for future practitioners.

Efficient invariant features for sensor variability compensation in speaker recognition.

In this paper, we investigate the use of invariant features for speaker recognition. Owing to their characteristics, these features are introduced to cope with the difficult and challenging problem of sensor variability and the source of performance degradation inherent in speaker recognition systems. Our experiments show: (1) the effectiveness of these features in match cases; (2) the benefit of combining these features with the mel frequency cepstral coefficients to exploit their discrimination power under uncontrolled conditions (mismatch cases). Consequently, the proposed invariant features result in a performance improvement as demonstrated by a reduction in the equal error rate and the minimum decision cost function compared to the GMM-UBM speaker recognition systems based on MFCC features.