Symptomatic vs. Asymptomatic Plaque Classification in Carotid Ultrasound

Radiomics and artificial intelligence: General notions and applications in the carotid vulnerable plaque

Carotid atherosclerosis plays a substantial role in cardiovascular morbidity and mortality. Given the multifaceted impact of this disease, there has been increasing interest in harnessing artificial intelligence (AI) and radiomics as complementary tools for the quantitative analysis of medical imaging data. This integrated approach holds promise not only in refining medical imaging data analysis but also in optimizing the utilization of radiologists' expertise. By automating time consuming tasks, AI allows radiologists to focus on more pertinent responsibilities. Simultaneously, the capacity of AI in radiomics to extract nuanced patterns from raw data enhances the exploration of carotid atherosclerosis, advancing efforts in terms of (1) early detection and diagnosis, (2) risk stratification and predictive modeling, (3) improving workflow efficiency, and (4) contributing to advancements in research. This review provides an overview of general concepts related to radiomics and AI, along with their application in the field of carotid vulnerable plaque. It also offers insights into various research studies conducted on this topic across different imaging techniques.

Predictive stroke risk model with vision transformer-based Doppler features

BACKGROUND

Acute stroke is the leading cause of death and disability globally, with an estimated 16 million cases each year. The progression of carotid stenosis reduces blood flow to the intracranial vasculature, causing stroke. Early recognition of ischemic stroke is crucial for disease treatment and management.

PURPOSE

A computer-aided diagnosis (CAD) system was proposed in this study to rapidly evaluate ischemic stroke in carotid color Doppler (CCD).

METHODS

Based on the ground truth from the clinical examination report, the vision transformer (ViT) features extracted from all CCD images (513 stroke and 458 normal images) were combined in machine learning classifiers to generate the likelihood of ischemic stroke for each image. The pretrained weights from ImageNet reduced the time-consuming training process. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were calculated to evaluate the stroke prediction model. The chi-square test, DeLong test, and Bonferroni correction for multiple comparisons were applied to deal with the type-I error. Only p values equal to or less than 0.00125 were considered to be statistically significant.

RESULTS

The proposed CAD system achieved an accuracy of 89%, a sensitivity of 94%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.95, outperforming the convolutional neural networks AlexNet (82%, p < 0.001), Inception-v3 (78%, p < 0.001), ResNet101 (84%, p < 0.001), and DenseNet201 (85%, p < 0.01). The computational time in model training was only 30 s, which would be efficient and practical in clinical use.

CONCLUSIONS

The experiment shows the promising use of CCD images in stroke estimation. Using the pretrained ViT architecture, the image features can be automatically and efficiently generated without human intervention. The proposed CAD system provides a rapid and reliable suggestion for diagnosing ischemic stroke.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Machine Learning-Based Detection of Dengue from Blood Smear Images Utilizing Platelet and Lymphocyte Characteristics

Dengue fever, also known as break-bone fever, can be life-threatening. Caused by DENV, an RNA virus from the Flaviviridae family, dengue is currently a globally important public health problem. The clinical methods available for dengue diagnosis require skilled supervision. They are manual, time-consuming, labor-intensive, and not affordable to common people. This paper describes a method that can support clinicians during dengue diagnosis. It is proposed to automate the peripheral blood smear (PBS) examination using Artificial Intelligence (AI) to aid dengue diagnosis. Nowadays, AI, especially Machine Learning (ML), is increasingly being explored for successful analyses in the biomedical field. Digital pathology coupled with AI holds great potential in developing healthcare services. The automation system developed incorporates a blob detection method to detect platelets and thrombocytopenia from the PBS images. The results achieved are clinically acceptable. Moreover, an ML-based technique is proposed to detect dengue from the images of PBS based on the lymphocyte nucleus. Ten features are extracted, including six morphological and four Gray Level Spatial Dependance Matrix (GLSDM) features, out of the lymphocyte nucleus of normal and dengue cases. Features are then subjected to various popular supervised classifiers built using a ten-fold cross-validation policy for automated dengue detection. Among all the classifiers, the best performance was achieved by Support Vector Machine (SVM) and Decision Tree (DT), each with an accuracy of 93.62%. Furthermore, 1000 deep features extracted using pre-trained MobileNetV2 and 177 textural features extracted using Local binary pattern (LBP) from the lymphocyte nucleus are subjected to feature selection. The ReliefF selected 100 most significant features are then fed to the classifiers. The best performance was attained using an SVM classifier with 95.74% accuracy. With the obtained results, it is evident that this proposed approach can efficiently contribute as an adjuvant tool for diagnosing dengue from the digital microscopic images of PBS.

Feasibility of using AI to auto-catch responsible frames in ultrasound screening for breast cancer diagnosis

The research of AI-assisted breast diagnosis has primarily been based on static images. It is unclear whether it represents the best diagnosis image.To explore the method of capturing complementary responsible frames from breast ultrasound screening by using artificial intelligence. We used feature entropy breast network (FEBrNet) to select responsible frames from breast ultrasound screenings and compared the diagnostic performance of AI models based on FEBrNet-recommended frames, physician-selected frames, 5-frame interval-selected frames, all frames of video, as well as that of ultrasound and mammography specialists. The AUROC of AI model based on FEBrNet-recommended frames outperformed other frame set based AI models, as well as ultrasound and mammography physicians, indicating that FEBrNet can reach level of medical specialists in frame selection.FEBrNet model can extract video responsible frames for breast nodule diagnosis, whose performance is equivalent to the doctors selected responsible frames.

HRU-Net: A Transfer Learning Method for Carotid Artery Plaque Segmentation in Ultrasound Images

Carotid artery stenotic plaque segmentation in ultrasound images is a crucial means for the analysis of plaque components and vulnerability. However, segmentation of severe stenotic plaques remains a challenging task because of the heterogeneities of inter-plaques and intra-plaques, and obscure boundaries of plaques. In this paper, we propose an automated HRU-Net transfer learning method for segmenting carotid plaques, using the limited images. The HRU-Net is based on the U-Net encoder−decoder paradigm, and cross-domain knowledge is transferred for plaque segmentation by fine-tuning the pretrained ResNet-50. Moreover, a cropped-blood-vessel image augmentation is customized for the plaque position constraint during training only. Moreover, hybrid atrous convolutions (HACs) are designed to derive diverse long-range dependences for refined plaque segmentation that are used on high-level semantic layers to exploit the implicit discrimination features. The experiments are performed on 115 images; Firstly, the 10-fold cross-validation, using 40 images with severe stenosis plaques, shows that the proposed method outperforms some of the state-of-the-art CNN-based methods on Dice, IoU, Acc, and modified Hausdorff distance (MHD) metrics; the improvements on metrics of Dice and MHD are statistically significant (p < 0.05). Furthermore, our HRU-Net transfer learning method shows fine generalization performance on 75 new images with varying degrees of plaque stenosis, and it may be used as an alternative for automatic noisy plaque segmentation in carotid ultrasound images clinically.

Multicenter Study on COVID-19 Lung Computed Tomography Segmentation with varying Glass Ground Opacities using Unseen Deep Learning Artificial Intelligence Paradigms: COVLIAS 1.0 Validation

Variations in COVID-19 lesions such as glass ground opacities (GGO), consolidations, and crazy paving can compromise the ability of solo-deep learning (SDL) or hybrid-deep learning (HDL) artificial intelligence (AI) models in predicting automated COVID-19 lung segmentation in Computed Tomography (CT) from unseen data leading to poor clinical manifestations. As the first study of its kind, “COVLIAS 1.0-Unseen” proves two hypotheses, (i) contrast adjustment is vital for AI, and (ii) HDL is superior to SDL. In a multicenter study, 10,000 CT slices were collected from 72 Italian (ITA) patients with low-GGO, and 80 Croatian (CRO) patients with high-GGO. Hounsfield Units (HU) were automatically adjusted to train the AI models and predict from test data, leading to four combinations—two Unseen sets: (i) train-CRO:test-ITA, (ii) train-ITA:test-CRO, and two Seen sets: (iii) train-CRO:test-CRO, (iv) train-ITA:test-ITA. COVILAS used three SDL models: PSPNet, SegNet, UNet and six HDL models: VGG-PSPNet, VGG-SegNet, VGG-UNet, ResNet-PSPNet, ResNet-SegNet, and ResNet-UNet. Two trained, blinded senior radiologists conducted ground truth annotations. Five types of performance metrics were used to validate COVLIAS 1.0-Unseen which was further benchmarked against MedSeg, an open-source web-based system. After HU adjustment for DS and JI, HDL (Unseen AI) > SDL (Unseen AI) by 4% and 5%, respectively. For CC, HDL (Unseen AI) > SDL (Unseen AI) by 6%. The COVLIAS-MedSeg difference was < 5%, meeting regulatory guidelines.Unseen AI was successfully demonstrated using automated HU adjustment. HDL was found to be superior to SDL.

Stratification of risk of atherosclerotic plaque using Hu’s moment invariants of segmented ultrasonic images

Myocardial infarction is one of the major life-threatening diseases. The cause is atherosclerosis i.e. the occlusion of the coronary artery by deposition of plaque on its walls. The severity of plaque deposition in the artery depends on the characteristics of the plaque. Hence, the classification of the type of plaque is crucial for assessing the risk of atherosclerosis and predicting the chances of myocardial infarction. This paper proposes prediction of atherosclerotic risk by non-invasive ultrasound image segmentation and textural feature extraction. The intima-media complex is segmented using a snakes-based segmentation algorithm on the arterial wall in the ultrasound images. Then, the plaque is extracted from the segmented intima-media complex. The features of the plaque are obtained by computing Hu’s moment invariants. Visual pattern recognition independent of position, size, orientation and parallel projection could be done using these moment invariants. For the classification of the features of the plaque, an SVM classifier is used. The performance shows improvement in accuracy using lesser number of features than previous works. The reduction in feature size is achieved by incorporating segmentation in the pre-processing stage. Tenfold cross-validation protocol is used for training and testing the classifier. An accuracy of 97.9% is obtained with only two features. This proposed technique could work as an adjunct tool in quick decision-making for cardiologists and radiologists. The segmentation step introduced in the preprocessing stage improved the feature extraction technique. An improvement in performance is achieved with much less number of features.

Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0

BACKGROUND

COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization.

METHOD

ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted.

RESULTS

Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p < 0.0001) on CroMed and > 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions.

CONCLUSIONS

Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

Role of Artificial Intelligence in Radiogenomics for Cancers in the Era of Precision Medicine

Simple Summary

Recently, radiogenomics has played a significant role and offered a new understanding of cancer’s biology and behavior in response to standard therapy. It also provides a more precise prognosis, investigation, and analysis of the patient’s cancer. Over the years, Artificial Intelligence (AI) has provided a significant strength in radiogenomics. In this paper, we offer computational and oncological prospects of the role of AI in radiogenomics, as well as its offers, achievements, opportunities, and limitations in the current clinical practices.

Abstract

Radiogenomics, a combination of “Radiomics” and “Genomics,” using Artificial Intelligence (AI) has recently emerged as the state-of-the-art science in precision medicine, especially in oncology care. Radiogenomics syndicates large-scale quantifiable data extracted from radiological medical images enveloped with personalized genomic phenotypes. It fabricates a prediction model through various AI methods to stratify the risk of patients, monitor therapeutic approaches, and assess clinical outcomes. It has recently shown tremendous achievements in prognosis, treatment planning, survival prediction, heterogeneity analysis, reoccurrence, and progression-free survival for human cancer study. Although AI has shown immense performance in oncology care in various clinical aspects, it has several challenges and limitations. The proposed review provides an overview of radiogenomics with the viewpoints on the role of AI in terms of its promises for computational as well as oncological aspects and offers achievements and opportunities in the era of precision medicine. The review also presents various recommendations to diminish these obstacles.

COVLIAS 1.0Lesion vs. MedSeg: An Artificial Intelligence Framework for Automated Lesion Segmentation in COVID-19 Lung Computed Tomography Scans

Background: COVID-19 is a disease with multiple variants, and is quickly spreading throughout the world. It is crucial to identify patients who are suspected of having COVID-19 early, because the vaccine is not readily available in certain parts of the world. Methodology: Lung computed tomography (CT) imaging can be used to diagnose COVID-19 as an alternative to the RT-PCR test in some cases. The occurrence of ground-glass opacities in the lung region is a characteristic of COVID-19 in chest CT scans, and these are daunting to locate and segment manually. The proposed study consists of a combination of solo deep learning (DL) and hybrid DL (HDL) models to tackle the lesion location and segmentation more quickly. One DL and four HDL models—namely, PSPNet, VGG-SegNet, ResNet-SegNet, VGG-UNet, and ResNet-UNet—were trained by an expert radiologist. The training scheme adopted a fivefold cross-validation strategy on a cohort of 3000 images selected from a set of 40 COVID-19-positive individuals. Results: The proposed variability study uses tracings from two trained radiologists as part of the validation. Five artificial intelligence (AI) models were benchmarked against MedSeg. The best AI model, ResNet-UNet, was superior to MedSeg by 9% and 15% for Dice and Jaccard, respectively, when compared against MD 1, and by 4% and 8%, respectively, when compared against MD 2. Statistical tests—namely, the Mann−Whitney test, paired t-test, and Wilcoxon test—demonstrated its stability and reliability, with p < 0.0001. The online system for each slice was <1 s. Conclusions: The AI models reliably located and segmented COVID-19 lesions in CT scans. The COVLIAS 1.0Lesion lesion locator passed the intervariability test.

Object-Specific Four-Path Network for Stroke Risk Stratification of Carotid Arteries in Ultrasound Images

Atherosclerotic carotid plaques have been shown to be closely associated with the risk of stroke. Since patients with symptomatic carotid plaques have a greater risk for stroke, stroke risk stratification based on the classification of carotid plaques into symptomatic or asymptomatic types is crucial in diagnosis, treatment planning, and medical treatment monitoring. A deep learning technique would be a good choice for implementing classification. Usually, to acquire a high-accuracy classification, a specific network architecture needs to be designed for a given classification task. In this study, we propose an object-specific four-path network (OSFP-Net) for stroke risk assessment by integrating ultrasound carotid plaques in both transverse and longitudinal sections of the bilateral carotid arteries. Each path of the OSFP-Net comprises of a feature extraction subnetwork (FE) and a feature downsampling subnetwork (FD). The FEs in the four paths use the same network structure to automatically extract features from ultrasound images of carotid plaques. The FDs use different object-specific pooling strategies for feature downsampling based on the observation that the sizes and shapes in the feature maps obtained from FEs should be different. The object-specific pooling strategies enable the network to accept arbitrarily sized carotid plaques as input and to capture a more informative context for improving the classification accuracy. Extensive experimental studies on a clinical dataset consisting of 333 subjects with 1332 carotid plaques show the superiority of our OSFP-Net against several state-of-the-art deep learning-based methods. The experimental results demonstrate better clinical agreement between the ground truth and the prediction, which indicates its great potential for use as a risk stratification and as a monitoring tool in the management of patients at risk for stroke.

Texture analysis imaging "what a clinical radiologist needs to know"

Texture analysis has arisen as a tool to explore the amount of data contained in images that cannot be explored by humans visually. Radiomics is a method that extracts a large number of features from radiographic medical images using data-characterisation algorithms. These features, termed radiomic features, have the potential to uncover disease characteristics. The goal of both radiomics and texture analysis is to go beyond size or human-eye based semantic descriptors, to enable the non-invasive extraction of quantitative radiological data to correlate them with clinical outcomes or pathological characteristics. In the latest years there has been a flourishing sub-field of radiology where texture analysis and radiomics have been used in many settings. It is difficult for the clinical radiologist to cope with such amount of data in all the different radiological sub-fields and to identify the most significant papers. The aim of this review is to provide a tool to better understand the basic principles underlining texture analysis and radiological data mining and a summary of the most significant papers of the latest years.

Ten Fast Transfer Learning Models for Carotid Ultrasound Plaque Tissue Characterization in Augmentation Framework Embedded with Heatmaps for Stroke Risk Stratification

Background and Purpose: Only 1-2% of the internal carotid artery asymptomatic plaques are unstable as a result of >80% stenosis. Thus, unnecessary efforts can be saved if these plaques can be characterized and classified into symptomatic and asymptomatic using non-invasive B-mode ultrasound. Earlier plaque tissue characterization (PTC) methods were machine learning (ML)-based, which used hand-crafted features that yielded lower accuracy and unreliability. The proposed study shows the role of transfer learning (TL)-based deep learning models for PTC. Methods: As pertained weights were used in the supercomputer framework, we hypothesize that transfer learning (TL) provides improved performance compared with deep learning. We applied 11 kinds of artificial intelligence (AI) models, 10 of them were augmented and optimized using TL approaches-a class of Atheromatic™ 2.0 TL (AtheroPoint™, Roseville, CA, USA) that consisted of (i-ii) Visual Geometric Group-16, 19 (VGG16, 19); (iii) Inception V3 (IV3); (iv-v) DenseNet121, 169; (vi) XceptionNet; (vii) ResNet50; (viii) MobileNet; (ix) AlexNet; (x) SqueezeNet; and one DL-based (xi) SuriNet-derived from UNet. We benchmark 11 AI models against our earlier deep convolutional neural network (DCNN) model. Results: The best performing TL was MobileNet, with accuracy and area-under-the-curve (AUC) pairs of 96.10 ± 3% and 0.961 (p < 0.0001), respectively. In DL, DCNN was comparable to SuriNet, with an accuracy of 95.66% and 92.7 ± 5.66%, and an AUC of 0.956 (p < 0.0001) and 0.927 (p < 0.0001), respectively. We validated the performance of the AI architectures with established biomarkers such as greyscale median (GSM), fractal dimension (FD), higher-order spectra (HOS), and visual heatmaps. We benchmarked against previously developed Atheromatic™ 1.0 ML and showed an improvement of 12.9%. Conclusions: TL is a powerful AI tool for PTC into symptomatic and asymptomatic plaques.

Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography

Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.

COVLIAS 1.0: Lung Segmentation in COVID-19 Computed Tomography Scans Using Hybrid Deep Learning Artificial Intelligence Models

BACKGROUND

COVID-19 lung segmentation using Computed Tomography (CT) scans is important for the diagnosis of lung severity. The process of automated lung segmentation is challenging due to (a) CT radiation dosage and (b) ground-glass opacities caused by COVID-19. The lung segmentation methodologies proposed in 2020 were semi- or automated but not reliable, accurate, and user-friendly. The proposed study presents a COVID Lung Image Analysis System (COVLIAS 1.0, AtheroPoint™, Roseville, CA, USA) consisting of hybrid deep learning (HDL) models for lung segmentation.

METHODOLOGY

The COVLIAS 1.0 consists of three methods based on solo deep learning (SDL) or hybrid deep learning (HDL). SegNet is proposed in the SDL category while VGG-SegNet and ResNet-SegNet are designed under the HDL paradigm. The three proposed AI approaches were benchmarked against the National Institute of Health (NIH)-based conventional segmentation model using fuzzy-connectedness. A cross-validation protocol with a 40:60 ratio between training and testing was designed, with 10% validation data. The ground truth (GT) was manually traced by a radiologist trained personnel. For performance evaluation, nine different criteria were selected to perform the evaluation of SDL or HDL lung segmentation regions and lungs long axis against GT.

RESULTS

Using the database of 5000 chest CT images (from 72 patients), COVLIAS 1.0 yielded AUC of ~0.96, ~0.97, ~0.98, and ~0.96 (p-value < 0.001), respectively within 5% range of GT area, for SegNet, VGG-SegNet, ResNet-SegNet, and NIH. The mean Figure of Merit using four models (left and right lung) was above 94%. On benchmarking against the National Institute of Health (NIH) segmentation method, the proposed model demonstrated a 58% and 44% improvement in ResNet-SegNet, 52% and 36% improvement in VGG-SegNet for lung area, and lung long axis, respectively. The PE statistics performance was in the following order: ResNet-SegNet > VGG-SegNet > NIH > SegNet. The HDL runs in <1 s on test data per image.

CONCLUSIONS

The COVLIAS 1.0 system can be applied in real-time for radiology-based clinical settings.

Multimodality carotid plaque tissue characterization and classification in the artificial intelligence paradigm: a narrative review for stroke application

Cardiovascular disease (CVD) is one of the leading causes of morbidity and mortality in the United States of America and globally. Carotid arterial plaque, a cause and also a marker of such CVD, can be detected by various non-invasive imaging modalities such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US). Characterization and classification of carotid plaque-type in these imaging modalities, especially into symptomatic and asymptomatic plaque, helps in the planning of carotid endarterectomy or stenting. It can be challenging to characterize plaque components due to (I) partial volume effect in magnetic resonance imaging (MRI) or (II) varying Hausdorff values in plaque regions in CT, and (III) attenuation of echoes reflected by the plaque during US causing acoustic shadowing. Artificial intelligence (AI) methods have become an indispensable part of healthcare and their applications to the non-invasive imaging technologies such as MRI, CT, and the US. In this narrative review, three main types of AI models (machine learning, deep learning, and transfer learning) are analyzed when applied to MRI, CT, and the US. A link between carotid plaque characteristics and the risk of coronary artery disease is presented. With regard to characterization, we review tools and techniques that use AI models to distinguish carotid plaque types based on signal processing and feature strengths. We conclude that AI-based solutions offer an accurate and robust path for tissue characterization and classification for carotid artery plaque imaging in all three imaging modalities. Due to cost, user-friendliness, and clinical effectiveness, AI in the US has dominated the most.

A Novel Block Imaging Technique Using Nine Artificial Intelligence Models for COVID-19 Disease Classification, Characterization and Severity Measurement in Lung Computed Tomography Scans on an Italian Cohort

Computer Tomography (CT) is currently being adapted for visualization of COVID-19 lung damage. Manual classification and characterization of COVID-19 may be biased depending on the expert's opinion. Artificial Intelligence has recently penetrated COVID-19, especially deep learning paradigms. There are nine kinds of classification systems in this study, namely one deep learning-based CNN, five kinds of transfer learning (TL) systems namely VGG16, DenseNet121, DenseNet169, DenseNet201 and MobileNet, three kinds of machine-learning (ML) systems, namely artificial neural network (ANN), decision tree (DT), and random forest (RF) that have been designed for classification of COVID-19 segmented CT lung against Controls. Three kinds of characterization systems were developed namely (a) Block imaging for COVID-19 severity index (CSI); (b) Bispectrum analysis; and (c) Block Entropy. A cohort of Italian patients with 30 controls (990 slices) and 30 COVID-19 patients (705 slices) was used to test the performance of three types of classifiers. Using K10 protocol (90% training and 10% testing), the best accuracy and AUC was for DCNN and RF pairs were 99.41 ± 5.12%, 0.991 (p < 0.0001), and 99.41 ± 0.62%, 0.988 (p < 0.0001), respectively, followed by other ML and TL classifiers. We show that diagnostics odds ratio (DOR) was higher for DL compared to ML, and both, Bispecturm and Block Entropy shows higher values for COVID-19 patients. CSI shows an association with Ground Glass Opacities (0.9146, p < 0.0001). Our hypothesis holds true that deep learning shows superior performance compared to machine learning models. Block imaging is a powerful novel approach for pinpointing COVID-19 severity and is clinically validated.

3-D optimized classification and characterization artificial intelligence paradigm for cardiovascular/stroke risk stratification using carotid ultrasound-based delineated plaque: Atheromatic™ 2.0

BACKGROUND AND PURPOSE

Atherosclerotic plaque tissue rupture is one of the leading causes of strokes. Early carotid plaque monitoring can help reduce cardiovascular morbidity and mortality. Manual ultrasound plaque classification and characterization methods are time-consuming and can be imprecise due to significant variations in tissue characteristics. We report a novel artificial intelligence (AI)-based plaque tissue classification and characterization system.

METHODS

We hypothesize that symptomatic plaque is hypoechoic due to its large lipid core and minimal collagen, as well as its heterogeneous makeup. Meanwhile, asymptomatic plaque is hyperechoic due to its small lipid core, abundant collagen, and the fact that it is often calcified. We designed a computer-aided diagnosis (CADx) system consisting of three kinds of deep learning (DL) classification paradigms: Deep Convolutional Neural Network (DCNN), Visual Geometric Group-16 (VGG16), and transfer learning, (tCNN). DCNN was 3-D optimized by varying the number of CNN layers and data augmentation frameworks. The DL systems were benchmarked against four types of machine learning (ML) classification systems, and the CADx system was characterized using two novel strategies consisting of DL mean feature strength (MFS) and a bispectrum model using higher-order spectra.

RESULTS

After balancing symptomatic and asymptomatic plaque classes, a five-fold augmentation process was applied, yielding 1000 carotid scans in each class. Then, using a K10 protocol (trained to test the ratio of 90%-10%), tCNN and DCNN yielded accuracy (area under the curve (AUC)) pairs of 83.33%, 0.833 (p < 0.0001) and 95.66%, 0.956 (p < 0.0001), respectively. DCNN was superior to ML by 7.01%. As part of the characterization process, the MFS of the symptomatic plaque was found to be higher compared to the asymptomatic plaque by 17.5% (p < 0.0001). A similar pattern was seen in the bispectrum, which was higher for symptomatic plaque by 5.4% (p < 0.0001). It took <2 s to perform the online CADx process on a supercomputer.

CONCLUSIONS

The performance order of the three AI systems was DCNN > tCNN > ML. Bispectrum-based on higher-order spectra proved a powerful paradigm for plaque tissue characterization. Overall, the AI-based systems offer a powerful solution for plaque tissue classification and characterization.

Uses of ultrasound in stroke prevention

Ultrasound methods are useful in stroke prevention in several ways. Measurement of carotid plaque burden, as either total plaque area (TPA) or total plaque volume (TPV) are strong predictors of cardiovascular risk: much stronger than intima-media thickness, which does not represent true atherosclerosis, but a biologically and genetically distinct phenotype. Measurement of plaque burden is also useful for the study of genetics, and of new risk factors such as toxic products of the intestinal microbiome. Carotid plaque burden is highly correlated with and as predictive of risk as coronary calcium scores, but is less costly and does not require radiation. Furthermore, because carotid plaques change in time over a period of months, they can be used for a new approach to vascular prevention: "Treating arteries instead of treating risk factors". In high-risk patients with asymptomatic carotid stenosis (ACS), this approach, implemented in 2003 in our clinics, was associated with a >80% reduction of stroke and myocardial infarction over 2 years. "Treating arteries without measuring plaque would be like treating hypertension without measuring blood pressure". Ultrasound methods can also be used to assess plaque vulnerability, by detecting echolucency, ulceration and plaque inhomogeneity on assessment of plaque texture. Transcranial Doppler (TCD) embolus detection is useful for risk stratification in patients with ACS; patients with two or more microemboli in an hour of monitoring have a 1-year risk of 15.6%, vs. 1% without microemboli, so this very clearly distinguishes which patients with ACS could benefit from intervention. TCD saline studies are more sensitive than trans-esophageal echocardiography for detection of patent foramen ovale, and more predictive of recurrent stroke. These methods should be more widely used, to reduce the increasing burden of stroke in our aging populations.

Choosing the right therapy for a patient with asymptomatic carotid stenosis

Introduction: Most patients with asymptomatic carotid stenosis (ACS) now have a lower risk with intensive medical therapy than with stenting (CAS) or endarterectomy (CEA); the annual risk of stroke or death with intensive medical therapy is ~ 0.5%, vs. a periprocedural risk with CAS of ~ 2.5-4.1% with CAS, and ~ 1.4-1.8% with CEA. The excess risk of CAS is greater in older patients.Areas covered: Discussed are the need for intensive medical therapy, the nature of intensive medical therapy, approaches to identifying the few patients with ACS who could benefit from CEA or CAS, and which patients would be better suited to CEA vs. CAS.Expert opinion: All patients with ACS are at high risk of cardiovascular events, soshould receive intensive medical therapy including lifestyle modification, intensive lipid-lowering, B vitamins to lower homocysteine (using methylcobalamin rather than cyanocobalamin), and appropriate antithrombotic therapy. High-risk patients who could benefit from intervention can be identified by clinical and imaging features including transcranial Doppler embolus detection, ulceration, intraplaque hemorrhage, reduced cerebrovascular reserve, plaque echolucency, silent infarction on brain imaging, and progression of stenosis. Most patients whose risk of stroke warrants intervention would be better treated with CEA than with CAS.

Automated plaque classification using computed tomography angiography and Gabor transformations

Cardiovascular diseases are the primary cause of death globally. These are often associated with atherosclerosis. This inflammation process triggers important variations in the coronary arteries (CA) and can lead to coronary artery disease (CAD). The presence of CA calcification (CAC) has recently been shown to be a strong predictor of CAD. In this clinical setting, computed tomography angiography (CTA) has begun to play a crucial role as a non-intrusive imaging method to characterize and study CA plaques. Herein, we describe an automated algorithm to classify plaque as either normal, calcified, or non-calcified using 2646 CTA images acquired from 73 patients. The automated technique is based on various features that are extracted from the Gabor transform of the acquired CTA images. Specifically, seven features are extracted from the Gabor coefficients : energy, and Kapur, Max, Rényi, Shannon, Vajda, and Yager entropies. The features were then ordered based on the F-value and input to numerous classification methods to achieve the best classification accuracy with the least number of features. Moreover, two well-known feature reduction techniques were employed, and the features acquired were also ranked according to F-value and input to several classifiers. The best classification results were obtained using all computed features without the employment of feature reduction, using a probabilistic neural network. An accuracy, positive predictive value, sensitivity, and specificity of 89.09%, 91.70%, 91.83% and 83.70% was obtained, respectively. Based on these results, it is evident that the technique can be helpful in the automated classification of plaques present in CTA images, and may become an important tool to reduce procedural costs and patient radiation dose. This could also aid clinicians in plaque diagnostics.

Classification of Carotid Artery Intima Media Thickness Ultrasound Images with Deep Learning

Cerebrovascular accident due to carotid artery disease is the most common cause of death in developed countries following heart disease and cancer. For a reliable early detection of atherosclerosis, Intima Media Thickness (IMT) measurement and classification are important. A new method for decision support purpose for the classification of IMT was proposed in this study. Ultrasound images are used for IMT measurements. Images are classified and evaluated by experts. This is a manual procedure, so it causes subjectivity and variability in the IMT classification. Instead, this article proposes a methodology based on artificial intelligence methods for IMT classification. For this purpose, a deep learning strategy with multiple hidden layers has been developed. In order to create the proposed model, convolutional neural network algorithm, which is frequently used in image classification problems, is used. 501 ultrasound images from 153 patients were used to test the model. The images are classified by two specialists, then the model is trained and tested on the images, and the results are explained. The deep learning model in the study achieved an accuracy of 89.1% in the IMT classification with 89% sensitivity and 88% specificity. Thus, the assessments in this paper have shown that this methodology performs reasonable results for IMT classification.

A Special Report on Changing Trends in Preventive Stroke/Cardiovascular Risk Assessment Via B-Mode Ultrasonography

PURPOSE OF REVIEW

Cardiovascular disease (CVD) and stroke risk assessment have been largely based on the success of traditional statistically derived risk calculators such as Pooled Cohort Risk Score or Framingham Risk Score. However, over the last decade, automated computational paradigms such as machine learning (ML) and deep learning (DL) techniques have penetrated into a variety of medical domains including CVD/stroke risk assessment. This review is mainly focused on the changing trends in CVD/stroke risk assessment and its stratification from statistical-based models to ML-based paradigms using non-invasive carotid ultrasonography.

RECENT FINDINGS

In this review, ML-based strategies are categorized into two types: non-image (or conventional ML-based) and image-based (or integrated ML-based). The success of conventional (non-image-based) ML-based algorithms lies in the different data-driven patterns or features which are used to train the ML systems. Typically these features are the patients' demographics, serum biomarkers, and multiple clinical parameters. The integrated (image-based) ML-based algorithms integrate the features derived from the ultrasound scans of the arterial walls (such as morphological measurements) with conventional risk factors in ML frameworks. Even though the review covers ML-based system designs for carotid and coronary ultrasonography, the main focus of the review is on CVD/stroke risk scores based on carotid ultrasound. There are two key conclusions from this review: (i) fusion of image-based features with conventional cardiovascular risk factors can lead to more accurate CVD/stroke risk stratification; (ii) the ability to handle multiple sources of information in big data framework using artificial intelligence-based paradigms (such as ML and DL) is likely to be the future in preventive CVD/stroke risk assessment.

The present and future of deep learning in radiology

The advent of Deep Learning (DL) is poised to dramatically change the delivery of healthcare in the near future. Not only has DL profoundly affected the healthcare industry it has also influenced global businesses. Within a span of very few years, advances such as self-driving cars, robots performing jobs that are hazardous to human, and chat bots talking with human operators have proved that DL has already made large impact on our lives. The open source nature of DL and decreasing prices of computer hardware will further propel such changes. In healthcare, the potential is immense due to the need to automate the processes and evolve error free paradigms. The sheer quantum of DL publications in healthcare has surpassed other domains growing at a very fast pace, particular in radiology. It is therefore imperative for the radiologists to learn about DL and how it differs from other approaches of Artificial Intelligence (AI). The next generation of radiology will see a significant role of DL and will likely serve as the base for augmented radiology (AR). Better clinical judgement by AR will help in improving the quality of life and help in life saving decisions, while lowering healthcare costs. A comprehensive review of DL as well as its implications upon the healthcare is presented in this review. We had analysed 150 articles of DL in healthcare domain from PubMed, Google Scholar, and IEEE EXPLORE focused in medical imagery only. We have further examined the ethic, moral and legal issues surrounding the use of DL in medical imaging.

A NEW APPROACH FOR CLASSIFICATION OF ATHEROSCLEROSIS OF COMMON CAROTID ARTERY FROM ULTRASOUND IMAGES

Background and objectives: The diagnosis of carotid atherosclerosis is of vital importance, as this cardiovascular disease may cause myocardial infarction. One-third of deaths in the world occur due to myocardial infarction, commonly known as heart attack. Atherosclerosis is deposition of plaque in artery wall. It could be detected from the features of intima-media complex of the artery wall. This study proposes a new classification approach to distinguish between symptomatic and asymptomatic plaques using non-invasive carotid B-mode ultrasound images. These two types of plaques have diverse impacts on human life. In the first condition, slowly plaque formation reaches life-threatening condition and the second condition is acute in nature. Hence treatment protocol is to be decided based on the type of plaque.

Methods: To locate the intima-media-complex region, the images are segmented using snake-based segmentation algorithm. Several features are extracted using fixed size blocks selected from the segmented region using gray-level co-occurrence matrix. Finally classification is performed using support vector machine. Results: The performance shows improvement in accuracy using lesser number of features than previous works. The reduction in feature size is achieved by incorporating segmentation in the pre-processing stage. In the classifier, 10-fold cross-validation protocol is used for training and testing and an accuracy of 100% is obtained.

Conclusion: This proposed technique could work as an adjunct tool in quick decision-making for cardiologists and radiologists.

Rheumatoid Arthritis: Atherosclerosis Imaging and Cardiovascular Risk Assessment Using Machine and Deep Learning-Based Tissue Characterization

PURPOSE OF THE REVIEW

Rheumatoid arthritis (RA) is a chronic, autoimmune disease which may result in a higher risk of cardiovascular (CV) events and stroke. Tissue characterization and risk stratification of patients with rheumatoid arthritis are a challenging problem. Risk stratification of RA patients using traditional risk factor-based calculators either underestimates or overestimates the CV risk. Advancements in medical imaging have facilitated early and accurate CV risk stratification compared to conventional cardiovascular risk calculators.

RECENT FINDING

In recent years, a link between carotid atherosclerosis and rheumatoid arthritis has been widely discussed by multiple studies. Imaging the carotid artery using 2-D ultrasound is a noninvasive, economic, and efficient imaging approach that provides an atherosclerotic plaque tissue-specific image. Such images can help to morphologically characterize the plaque type and accurately measure vital phenotypes such as media wall thickness and wall variability. Intelligence-based paradigms such as machine learning- and deep learning-based techniques not only automate the risk characterization process but also provide an accurate CV risk stratification for better management of RA patients. This review provides a brief understanding of the pathogenesis of RA and its association with carotid atherosclerosis imaged using the B-mode ultrasound technique. Lacunas in traditional risk scores and the role of machine learning-based tissue characterization algorithms are discussed and could facilitate cardiovascular risk assessment in RA patients. The key takeaway points from this review are the following: (i) inflammation is a common link between RA and atherosclerotic plaque buildup, (ii) carotid ultrasound is a better choice to characterize the atherosclerotic plaque tissues in RA patients, and (iii) intelligence-based paradigms are useful for accurate tissue characterization and risk stratification of RA patients.

Echolucency-based phenotype in carotid atherosclerosis disease for risk stratification of diabetes patients

AIM

The study investigated the association of carotid ultrasound echolucent plaque-based biomarker with HbA1c, measured as age-adjusted grayscale median (AAGSM) as a function of chronological age, total plaque area, and conventional grayscale median (GSM_conv).

METHODS

Two stages were developed: (a) automated measurement of carotid parameters such as total plaque area (TPA); (b) computing the AAGSM as a function of GSM_conv, age, and TPA. Intra-operator (novice and experienced) analysis was conducted.

RESULTS

IRB approved, 204 patients' left/right CCA (408 images) ultrasound scans were collected: mean age: 69 ± 11 years; mean HbA1c: 6.12 ± 1.47%. A moderate inverse correlation was observed between AAGSM and HbA1c (CC of -0.13, P = 0.01), compared to GSM (CC of -0.06, P = 0.24). The RCCA and LCCA showed CC of -0.18, P < 0.01 and -0.08; P < 0.24. Female and males showed CC of -0.29, P < 0.01 and -0.10, P = 0.09. Using the threshold for AAGSM and HbA1c as: low-risk (AAGSM > 100; HbA1c < 5.7%), moderate-risk (40 < AAGSM < 100; 5.7% < HbA1c < 6.5%) and high-risk (AAGSM < 40; HbA1c > 6.5%), the area under the curve showed a better performance of AAGSM over GSM_conv. A paired t-test between operators and expert (P < 0.0001); inter-operator CC of 0.85 (P < 0.0001).

CONCLUSIONS

Echolucent plaque in patients with diabetes can be more accurately characterized for risk stratification using AAGSM compared to GSM_conv.

Automated characterization of cardiovascular diseases using relative wavelet nonlinear features extracted from ECG signals

Cardiovascular diseases (CVDs) are the leading cause of deaths worldwide. The rising mortality rate can be reduced by early detection and treatment interventions. Clinically, electrocardiogram (ECG) signal provides useful information about the cardiac abnormalities and hence employed as a diagnostic modality for the detection of various CVDs. However, subtle changes in these time series indicate a particular disease. Therefore, it may be monotonous, time-consuming and stressful to inspect these ECG beats manually. In order to overcome this limitation of manual ECG signal analysis, this paper uses a novel discrete wavelet transform (DWT) method combined with nonlinear features for automated characterization of CVDs. ECG signals of normal, and dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy (HCM) and myocardial infarction (MI) are subjected to five levels of DWT. Relative wavelet of four nonlinear features such as fuzzy entropy, sample entropy, fractal dimension and signal energy are extracted from the DWT coefficients. These features are fed to sequential forward selection (SFS) technique and then ranked using ReliefF method. Our proposed methodology achieved maximum classification accuracy (acc) of 99.27%, sensitivity (sen) of 99.74%, and specificity (spec) of 98.08% with K-nearest neighbor (kNN) classifier using 15 features ranked by the ReliefF method. Our proposed methodology can be used by clinical staff to make faster and accurate diagnosis of CVDs. Thus, the chances of survival can be significantly increased by early detection and treatment of CVDs.

Automated localization and segmentation techniques for B-mode ultrasound images: A review

B-mode ultrasound imaging is used extensively in medicine. Hence, there is a need to have efficient segmentation tools to aid in computer-aided diagnosis, image-guided interventions, and therapy. This paper presents a comprehensive review on automated localization and segmentation techniques for B-mode ultrasound images. The paper first describes the general characteristics of B-mode ultrasound images. Then insight on the localization and segmentation of tissues is provided, both in the case in which the organ/tissue localization provides the final segmentation and in the case in which a two-step segmentation process is needed, due to the desired boundaries being too fine to locate from within the entire ultrasound frame. Subsequenly, examples of some main techniques found in literature are shown, including but not limited to shape priors, superpixel and classification, local pixel statistics, active contours, edge-tracking, dynamic programming, and data mining. Ten selected applications (abdomen/kidney, breast, cardiology, thyroid, liver, vascular, musculoskeletal, obstetrics, gynecology, prostate) are then investigated in depth, and the performances of a few specific applications are compared. In conclusion, future perspectives for B-mode based segmentation, such as the integration of RF information, the employment of higher frequency probes when possible, the focus on completely automatic algorithms, and the increase in available data are discussed.

AUTOMATED IDENTIFICATION OF CORONARY ARTERY DISEASE FROM SHORT-TERM 12 LEAD ELECTROCARDIOGRAM SIGNALS BY USING WAVELET PACKET DECOMPOSITION AND COMMON SPATIAL PATTERN TECHNIQUES

The occlusion of the coronary arteries commonly known as coronary artery disease (CAD) restricts the normal blood circulation required to the heart muscles, thus results in an irreversible myocardial damage or death (myocardial infarction). Clinically, electrocardiogram (ECG) is performed as a primary diagnostic tool to capture these cardiac activities and detect the presence of CAD. However, the use of computer-aided techniques can reduce the visual burden and manual time required for the analysis of complex ECG signals in order to identify the CAD affected subjects from normal ones. Therefore, in this study, a novel computer-aided technique is proposed using 2[Formula: see text]s of 12 lead ECG signals for the identification of CAD affected patients. Each of the 2[Formula: see text]s 12 lead ECG signal beats (3791 normal and 12308 CAD ECG signal beats) are implemented with four levels of wavelet packet decomposition (WPD) to obtain various coefficients. Using the fourth-level coefficients obtained for each lead ECG signal beat, new 2[Formula: see text]s. ECG signal beats are reconstructed. Later, the reconstructed signals are split into two-fold data sets, in which one set is used for acquiring common spatial pattern (CSP) filter and the other for obtaining features vector (vice versa). The obtained features are one by one fed into k-nearest neighbors (KNN) classifier for automated classification. The proposed system yielded maximum average classification results of 99.65% accuracy, 99.64% sensitivity and 99.7% specificity using 10 features. Our proposed algorithm is highly efficient and can be used by the clinicians as an aiding system in their CAD diagnosis, thus, assisting in faster treatment and avoiding the progression of CAD condition.

APPLICATION OF ENTROPIES FOR AUTOMATED DIAGNOSIS OF ABNORMALITIES IN ULTRASOUND IMAGES: A REVIEW

Automation of diagnosis process in medical imaging using various computer-aided techniques is a leading topic of research. Among many computer-aided methods, nonlinear entropies are widely applied in the development of automated algorithms to diagnose abnormalities present in medical images. The use of entropy features in development of Computer-Aided Diagnosis (CAD) may enhance the accuracy of the system. Entropy features depict the nonlinearity of images and thereby the presence of complexity in the images. Various types of entropies have been employed in medical image analysis for automated diagnosis of abnormalities present in the images. This paper focuses on the diverse types of entropies employed in the development of CAD systems for the diagnosis of abnormalities in the medical images. In addition to the diagnosis, these entropies can be used to differentiate the images based on the severity of the abnormalities and for other biomedical applications.

THE EFFECT OF DIABETES ON CARDIOVASCULAR SYSTEM

Diabetes mellitus (DM) is a critical and long-term disorder due to the insufficient production of insulin by the pancreas or ineffective use of insulin by the body. Importantly, cardiovascular disease (CVD) has long been thought to be linked with diabetes. Despite more diabetic individuals surviving from better medications and treatments, there has been significant rise in the morbidity and mortality from CVD. Indeed, the classification of DM based on the electrocardiogram signals of the heart will be an advantageous system. Further, computer-aided classification of DM with integrated algorithms may enhance the execution of the system. In this paper, we have reviewed various studies using heart rate variability signals for automated classification of diabetes. Furthermore, the different techniques used to extract the features and the efficiency of the classification systems are discussed.

ALGORITHM FOR THE DETECTION OF CONGESTIVE HEART FAILURE INDEX

This study documents our efforts to provide computer support for the diagnosis of congestive heart failure (CHF). That computer support takes the form of an index value. A high index value indicates a low probability of CHF, and an index value below a threshold of 25.6 suggests a high probability of CHF. To create that index, we have designed a sophisticated algorithm chain which takes electrocardiogram signals as input. The signals are pre-processed before they are sent to a range of nonlinear feature extraction algorithms. The top 10 feature extraction methods were used to create the CHF index. By using objective feature extraction algorithms, we avoid the problem of inter- and intra-observer variability. We observed that the nonlinear feature extraction methods reflect the nature of the human heart very well. That observation is based on the fact that the nonlinear features achieved low [Formula: see text]-values and high feature ranking criterion scores.

PERFORMANCE EVALUATION OF DRY EYE DETECTION SYSTEM USING HIGHER-ORDER SPECTRA FEATURES FOR DIFFERENT NOISE LEVELS IN IR THERMAL IMAGES

The enhanced tear film evaporation and diminished tear production causes a dry eye (DE) condition. A non-invasive infrared (IR) thermography is most commonly used as a diagnostic tool for diagnosis of DE. However, the availability of high-quality IR thermal camera at low cost is difficult. Hence, an efficient DE detection system which can perform efficiently by using low-cost and low-quality images instead of conventional IR images would be a significant contribution. Therefore, in this work, we have evaluated the performance of automated non-invasive DE detection system using low-quality images obtained by adding different levels of noise to high-quality IR images. In this work, the performances of two non-linear higher-order spectra (HOS) cumulants and bispectrum features are compared. These features are extracted from the IR images with different levels of Gaussian noise. Principal component analysis (PCA) is performed on these extracted features and they are ranked using [Formula: see text]-value and later fed to different classifiers. We have achieved the accuracies, sensitivities and specificities of: (i) 86.90%, 85.71% and 88.10%, with noise level 0 using 24 bispectrum features, and (ii) 80.95%, 85.71% and 76.19%, with noise level 10 using 15 bispectrum features for right eye IR images. This study exhibits that even in the presence of high levels of noise, the detection of DE is possible and our proposed method performs efficiently using HOS bispectrum features. Thus, our proposed method can be used to detect DE using low-quality and inexpensive cameras instead of high-cost IR camera.

SHOCKABLE VERSUS NONSHOCKABLE LIFE-THREATENING VENTRICULAR ARRHYTHMIAS USING DWT AND NONLINEAR FEATURES OF ECG SIGNALS

Shockable ventricular arrhythmias (VAs) such as ventricular tachycardia (VT) and ventricular fibrillation (VFib) are the life-threatening conditions requiring immediate attention. Cardiopulmonary resuscitation (CPR) and defibrillation are the significant immediate recommended treatments for these shockable arrhythmias to obtain the return of spontaneous circulation. However, accurate classification of these shockable VAs from nonshockable ones is the key step during defibrillation by automated external defibrillator (AED). Therefore, in this work, we have proposed a novel algorithm for an automated differentiation of shockable and nonshockable VAs from electrocardiogram (ECG) signal. The ECG signals are segmented into 5, 8 and 10[Formula: see text]s. These segmented ECGs are subjected to four levels of discrete wavelet transformation (DWT). Various nonlinear features such as approximate entropy ([Formula: see text], signal energy ([Formula: see text]), Fuzzy entropy ([Formula: see text]), Kolmogorov Sinai entropy ([Formula: see text], permutation entropy ([Formula: see text]), Renyi entropy ([Formula: see text]), sample entropy ([Formula: see text]), Shannon entropy ([Formula: see text]), Tsallis entropy ([Formula: see text]), wavelet entropy ([Formula: see text]), fractal dimension ([Formula: see text]), Kolmogorov complexity ([Formula: see text]), largest Lyapunov exponent ([Formula: see text]), recurrence quantification analysis (RQA) parameters ([Formula: see text]), Hurst exponent ([Formula: see text]), activity entropy ([Formula: see text]), Hjorth complexity ([Formula: see text]), Hjorth mobility ([Formula: see text]), modified multi scale entropy ([Formula: see text]) and higher order statistics (HOS) bispectrum ([Formula: see text]) are obtained from the DWT coefficients. Later, these features are subjected to sequential forward feature selection (SFS) method and selected features are then ranked using seven ranking methods namely, Bhattacharyya distance, entropy, Fuzzy maximum relevancy and minimum redundancy (mRMR), receiver operating characteristic (ROC), Student’s [Formula: see text]-test, Wilcoxon and ReliefF. These ranked features are supplied independently into the [Formula: see text]-Nearest Neighbor (kNN) classifier. Our proposed system achieved maximum accuracy, sensitivity and specificity of (i) 97.72%, 94.79% and 98.74% for 5[Formula: see text]s, (ii) 98.34%, 95.49% and 99.14% for 8[Formula: see text]s and (iii) 98.32%, 95.16% and 99.20% for 10[Formula: see text]s of ECG segments using only ten features. The integration of the proposed algorithm with ECG acquisition systems in the intensive care units (ICUs) can help the clinicians to decipher the shockable and nonshockable life-threatening arrhythmias accurately. Hence, doctors can use the CPR or AED immediately and increase the chance of survival during shockable life-threatening arrhythmia intervals.

ALCOHOLIC INDEX USING NON-LINEAR FEATURES EXTRACTED FROM DIFFERENT FREQUENCY BANDS

Alcoholism is a complex condition that mainly disturbs the neuronal networks in Central Nervous System (CNS). This disorder not only disturbs the brain, but also affects the behavior, emotions, and cognitive judgements. Electroencephalography (EEG) is a valuable tool to examine the neuropsychiatric disorders like alcoholism. The EEG is a well-established modality to diagnose the electrical activity produced by the populations of neurons in cerebral cortex. However, EEG signals are non-linear in nature; hence very challenging to interpret the valuable information from them using linear methods. Thus, using non-linear methods to analyze EEG signals can be beneficial in order to predict the brain signals condition. This paper presents a computer-aided diagnostic method for the detection of alcoholic EEG signals from normal by employing the non-linear techniques. First, the EEG signals are subjected to six levels of Wavelet Packet Decomposition (WPD) to obtain seven wavebands (delta ([Formula: see text]), theta ([Formula: see text]), lower alpha (la), upper alpha (ua), lower beta (lb), upper beta (ub), lower gamma (lg)). From each wavebands (activity bands), 19 non-linear features such as Recurrence Quantification Analysis (RQA) ([Formula: see text]), Approximate Entropy ([Formula: see text]), Energy ([Formula: see text]), Fractal Dimension (FD) ([Formula: see text]), Permutation Entropy ([Formula: see text]), Detrended Fluctuation Analysis ([Formula: see text]), Hurst Exponent ([Formula: see text]), Largest Lyapunov Exponent ([Formula: see text]), Sample Entropy ([Formula: see text]), Shannon’s Entropy ([Formula: see text]), Renyi’s entropy ([Formula: see text]), Tsalli’s entropy ([Formula: see text]), Fuzzy entropy ([Formula: see text]), Wavelet entropy ([Formula: see text]), Kolmogorov–Sinai entropy ([Formula: see text]), Modified Multiscale Entropy ([Formula: see text]), Hjorth’s parameters (activity ([Formula: see text]), mobility ([Formula: see text]), and complexity ([Formula: see text])) are extracted. The extracted features are then ranked using Bhattacharyya, Entropy, Fuzzy entropy-based Max-Relevancy and Min-Redundancy (mRMR), Receiver Operating Characteristic (ROC), [Formula: see text]-test, and Wilcoxon. These ranked features are given to train Support Vector Machine (SVM) classifier. The SVM classifier with radial basis function (RBF) achieved 95.41% accuracy, 93.33% sensitivity and 97.50% specificity using four non-linear features ranked by Wilcoxon method. In addition, an integrated index called Alcoholic Index (ALCOHOLI) is developed using highly ranked two features for identification of normal and alcoholic EEG signals using a single number. This system is rapid, efficient, and inexpensive and can be employed as an EEG analysis assisting system by clinicians in the detection of alcoholism. In addition, the proposed system can be used in rehabilitation centers to evaluate person with alcoholism over time and observe the outcome of treatment provided for reducing or reversing the impact of the condition on the brain.

THE BIOPHYSICAL PARAMETER MEASUREMENTS FROM PPG SIGNAL

Early investigation on blood circulation by Hertzman (1937) leads to the observation of vital body signs such as respiration rate, heart rate (HR), blood oxygenation and vascular assessment using photoplethysmographic (PPG) device. PPG is a noninvasive, painless optical technique used to monitor the pulsations linked to alteration in the blood volume. The PPG waveform is a summation of pulsatile and nonpulsatile components and contains useful information about the physiological systems. With the breakthrough in technology and development of powerful analytical tools, PPG devices are constantly being used in advanced medical equipments such as smart-watches and smart-wristbands for HR monitoring, pulse oximeters for measuring respiratory rate and noncontact PPG device for blood oxygen saturation measurement. This paper presents description on PPG and its characteristic waveform and working principle. It also includes brief explanation on nonlinear analysis of PPG signals and salient applications of PPG followed by its advantages and limitations.

Wall-based measurement features provides an improved IVUS coronary artery risk assessment when fused with plaque texture-based features during machine learning paradigm

BACKGROUND

Planning of percutaneous interventional procedures involves a pre-screening and risk stratification of the coronary artery disease. Current screening tools use stand-alone plaque texture-based features and therefore lack the ability to stratify the risk.

METHOD

This IRB approved study presents a novel strategy for coronary artery disease risk stratification using an amalgamation of IVUS plaque texture-based and wall-based measurement features. Due to common genetic plaque makeup, carotid plaque burden was chosen as a gold standard for risk labels during training-phase of machine learning (ML) paradigm. Cross-validation protocol was adopted to compute the accuracy of the ML framework. A set of 59 plaque texture-based features was padded with six wall-based measurement features to show the improvement in stratification accuracy. The ML system was executed using principle component analysis-based framework for dimensionality reduction and uses support vector machine classifier for training and testing-phases.

RESULTS

The ML system produced a stratification accuracy of 91.28%, demonstrating an improvement of 5.69% when wall-based measurement features were combined with plaque texture-based features. The fused system showed an improvement in mean sensitivity, specificity, positive predictive value, and area under the curve by: 6.39%, 4.59%, 3.31% and 5.48%, respectively when compared to the stand-alone system. While meeting the stability criteria of 5%, the ML system also showed a high average feature retaining power and mean reliability of 89.32% and 98.24%, respectively.

CONCLUSIONS

The ML system showed an improvement in risk stratification accuracy when the wall-based measurement features were fused with the plaque texture-based features.

A novel and robust Bayesian approach for segmentation of psoriasis lesions and its risk stratification

BACKGROUND AND OBJECTIVE

The need for characterization of psoriasis lesion severity is clinically valuable and vital for dermatologists since it provides a reliable and precise decision on risk assessment. The automated delineation of lesion is a prerequisite prior to characterization, which is challenging itself. Thus, this paper has two major objectives: (a) design of a segmentation system which can model by learning the lesion characteristics and this is posed as a Bayesian model; (b) develop a psoriasis risk assessment system (pRAS) by crisscrossing the blocks which drives the fundamental machine learning paradigm.

METHODS

The segmentation system uses the knowledge derived by the experts along with the features reflected by the lesions to build a Bayesian framework that helps to classify each pixel of the image into lesion vs.

BACKGROUND

Since this lesion has several stages and grades, hence the system undergoes the risk assessment to classify into five levels of severity: healthy, mild, moderate, severe and very severe. We build nine kinds of pRAS utilizing different combinations of the key blocks. These nine pRAS systems use three classifiers (Support Vector Machine (SVM), Decision Tree (DT) and Neural Network (NN)) and three feature selection techniques (Principal Component Analysis (PCA), Fisher Discriminant Ratio (FDR) and Mutual Information (MI)). The two major experiments conducted using these nine systems were: (i) selection of best system combination based on classification accuracy and (ii) understanding the reliability of the system. This leads us to computation of key system performance parameters such as: feature retaining power, aggregated feature effect and reliability index besides conventional attributes like accuracy, sensitivity, specificity.

RESULTS

Using the database used in this study consisted of 670 psoriasis images, the combination of SVM and FDR was revealed as the optimal pRAS system and yielded a classification accuracy of 99.84% using cross-validation protocol. Further, SVM-FDR system provides the reliability of 99.99% using cross-validation protocol.

CONCLUSIONS

The study demonstrates a fully novel model of segmentation embedded with risk assessment. Among all nine systems, SVM-FDR produced best results. Further, we validated our pRAS system with automatic segmented lesions against manually segmented lesions showing comparable performance.

A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images

Glaucoma is an optic neuropathy defined by characteristic damage to the optic nerve and accompanying visual field deficits. Early diagnosis and treatment are critical to prevent irreversible vision loss and ultimate blindness. Current techniques for computer-aided analysis of the optic nerve and retinal nerve fiber layer (RNFL) are expensive and require keen interpretation by trained specialists. Hence, an automated system is highly desirable for a cost-effective and accurate screening for the diagnosis of glaucoma. This paper presents a new methodology and a computerized diagnostic system. Adaptive histogram equalization is used to convert color images to grayscale images followed by convolution of these images with Leung-Malik (LM), Schmid (S), and maximum response (MR4 and MR8) filter banks. The basic microstructures in typical images are called textons. The convolution process produces textons. Local configuration pattern (LCP) features are extracted from these textons. The significant features are selected using a sequential floating forward search (SFFS) method and ranked using the statistical t-test. Finally, various classifiers are used for classification of images into normal and glaucomatous classes. A high classification accuracy of 95.8% is achieved using six features obtained from the LM filter bank and the k-nearest neighbor (kNN) classifier. A glaucoma integrative index (GRI) is also formulated to obtain a reliable and effective system.