Inter-observer Variability Analysis of Automatic Lung Delineation in Normal and Disease Patients

Cardiovascular Disease Risk Stratification Using Hybrid Deep Learning Paradigm: First of Its Kind on Canadian Trial Data

BACKGROUND

The risk of cardiovascular disease (CVD) has traditionally been predicted via the assessment of carotid plaques. In the proposed study, AtheroEdge™ 3.0HDL (AtheroPoint™, Roseville, CA, USA) was designed to demonstrate how well the features obtained from carotid plaques determine the risk of CVD. We hypothesize that hybrid deep learning (HDL) will outperform unidirectional deep learning, bidirectional deep learning, and machine learning (ML) paradigms.

METHODOLOGY

500 people who had undergone targeted carotid B-mode ultrasonography and coronary angiography were included in the proposed study. ML feature selection was carried out using three different methods, namely principal component analysis (PCA) pooling, the chi-square test (CST), and the random forest regression (RFR) test. The unidirectional and bidirectional deep learning models were trained, and then six types of novel HDL-based models were designed for CVD risk stratification. The AtheroEdge™ 3.0HDL was scientifically validated using seen and unseen datasets while the reliability and statistical tests were conducted using CST along with p-value significance. The performance of AtheroEdge™ 3.0HDL was evaluated by measuring the p-value and area-under-the-curve for both seen and unseen data.

RESULTS

The HDL system showed an improvement of 30.20% (0.954 vs. 0.702) over the ML system using the seen datasets. The ML feature extraction analysis showed 70% of common features among all three methods. The generalization of AtheroEdge™ 3.0HDL showed less than 1% (p-value < 0.001) difference between seen and unseen data, complying with regulatory standards.

CONCLUSIONS

The hypothesis for AtheroEdge™ 3.0HDL was scientifically validated, and the model was tested for reliability and stability and is further adaptable clinically.

Four Transformer-Based Deep Learning Classifiers Embedded with an Attention U-Net-Based Lung Segmenter and Layer-Wise Relevance Propagation-Based Heatmaps for COVID-19 X-ray Scans

Background: Diagnosing lung diseases accurately is crucial for proper treatment. Convolutional neural networks (CNNs) have advanced medical image processing, but challenges remain in their accurate explainability and reliability. This study combines U-Net with attention and Vision Transformers (ViTs) to enhance lung disease segmentation and classification. We hypothesize that Attention U-Net will enhance segmentation accuracy and that ViTs will improve classification performance. The explainability methodologies will shed light on model decision-making processes, aiding in clinical acceptance. Methodology: A comparative approach was used to evaluate deep learning models for segmenting and classifying lung illnesses using chest X-rays. The Attention U-Net model is used for segmentation, and architectures consisting of four CNNs and four ViTs were investigated for classification. Methods like Gradient-weighted Class Activation Mapping plus plus (Grad-CAM++) and Layer-wise Relevance Propagation (LRP) provide explainability by identifying crucial areas influencing model decisions. Results: The results support the conclusion that ViTs are outstanding in identifying lung disorders. Attention U-Net obtained a Dice Coefficient of 98.54% and a Jaccard Index of 97.12%. ViTs outperformed CNNs in classification tasks by 9.26%, reaching an accuracy of 98.52% with MobileViT. An 8.3% increase in accuracy was seen while moving from raw data classification to segmented image classification. Techniques like Grad-CAM++ and LRP provided insights into the decision-making processes of the models. Conclusions: This study highlights the benefits of integrating Attention U-Net and ViTs for analyzing lung diseases, demonstrating their importance in clinical settings. Emphasizing explainability clarifies deep learning processes, enhancing confidence in AI solutions and perhaps enhancing clinical acceptance for improved healthcare results.

Deep learning approach for cardiovascular disease risk stratification and survival analysis on a Canadian cohort

The quantification of carotid plaque has been routinely used to predict cardiovascular risk in cardiovascular disease (CVD) and coronary artery disease (CAD). To determine how well carotid plaque features predict the likelihood of CAD and cardiovascular (CV) events using deep learning (DL) and compare against the machine learning (ML) paradigm. The participants in this study consisted of 459 individuals who had undergone coronary angiography, contrast-enhanced ultrasonography, and focused carotid B-mode ultrasound. Each patient was tracked for thirty days. The measurements on these patients consisted of maximum plaque height (MPH), total plaque area (TPA), carotid intima-media thickness (cIMT), and intraplaque neovascularization (IPN). CAD risk and CV event stratification were performed by applying eight types of DL-based models. Univariate and multivariate analysis was also conducted to predict the most significant risk predictors. The DL's model effectiveness was evaluated by the area-under-the-curve measurement while the CV event prediction was evaluated using the Cox proportional hazard model (CPHM) and compared against the DL-based concordance index (c-index). IPN showed a substantial ability to predict CV events (p < 0.0001). The best DL system improved by 21% (0.929 vs. 0.762) over the best ML system. DL-based CV event prediction showed a ~ 17% increase in DL-based c-index compared to the CPHM (0.86 vs. 0.73). CAD and CV incidents were linked to IPN and carotid imaging characteristics. For survival analysis and CAD prediction, the DL-based system performs superior to ML-based models.

Deep Learning Paradigm and Its Bias for Coronary Artery Wall Segmentation in Intravascular Ultrasound Scans: A Closer Look

BACKGROUND AND MOTIVATION

Coronary artery disease (CAD) has the highest mortality rate; therefore, its diagnosis is vital. Intravascular ultrasound (IVUS) is a high-resolution imaging solution that can image coronary arteries, but the diagnosis software via wall segmentation and quantification has been evolving. In this study, a deep learning (DL) paradigm was explored along with its bias.

METHODS

Using a PRISMA model, 145 best UNet-based and non-UNet-based methods for wall segmentation were selected and analyzed for their characteristics and scientific and clinical validation. This study computed the coronary wall thickness by estimating the inner and outer borders of the coronary artery IVUS cross-sectional scans. Further, the review explored the bias in the DL system for the first time when it comes to wall segmentation in IVUS scans. Three bias methods, namely (i) ranking, (ii) radial, and (iii) regional area, were applied and compared using a Venn diagram. Finally, the study presented explainable AI (XAI) paradigms in the DL framework.

FINDINGS AND CONCLUSIONS

UNet provides a powerful paradigm for the segmentation of coronary walls in IVUS scans due to its ability to extract automated features at different scales in encoders, reconstruct the segmented image using decoders, and embed the variants in skip connections. Most of the research was hampered by a lack of motivation for XAI and pruned AI (PAI) models. None of the UNet models met the criteria for bias-free design. For clinical assessment and settings, it is necessary to move from a paper-to-practice approach.

Attention-Enabled Ensemble Deep Learning Models and Their Validation for Depression Detection: A Domain Adoption Paradigm

Depression is increasingly prevalent, leading to higher suicide risk. Depression detection and sentimental analysis of text inputs in cross-domain frameworks are challenging. Solo deep learning (SDL) and ensemble deep learning (EDL) models are not robust enough. Recently, attention mechanisms have been introduced in SDL. We hypothesize that attention-enabled EDL (aeEDL) architectures are superior compared to attention-not-enabled SDL (aneSDL) or aeSDL models. We designed EDL-based architectures with attention blocks to build eleven kinds of SDL model and five kinds of EDL model on four domain-specific datasets. We scientifically validated our models by comparing "seen" and "unseen" paradigms (SUP). We benchmarked our results against the SemEval (2016) sentimental dataset and established reliability tests. The mean increase in accuracy for EDL over their corresponding SDL components was 4.49%. Regarding the effect of attention block, the increase in the mean accuracy (AUC) of aeSDL over aneSDL was 2.58% (1.73%), and the increase in the mean accuracy (AUC) of aeEDL over aneEDL was 2.76% (2.80%). When comparing EDL vs. SDL for non-attention and attention, the mean aneEDL was greater than aneSDL by 4.82% (3.71%), and the mean aeEDL was greater than aeSDL by 5.06% (4.81%). For the benchmarking dataset (SemEval), the best-performing aeEDL model (ALBERT+BERT-BiLSTM) was superior to the best aeSDL (BERT-BiLSTM) model by 3.86%. Our scientific validation and robust design showed a difference of only 2.7% in SUP, thereby meeting the regulatory constraints. We validated all our hypotheses and further demonstrated that aeEDL is a very effective and generalized method for detecting symptoms of depression in cross-domain settings.

Deep learning artificial intelligence framework for multiclass coronary artery disease prediction using combination of conventional risk factors, carotid ultrasound, and intraplaque neovascularization

OBJECTIVE

Cardiovascular disease (CVD) is a major healthcare challenge and therefore early risk assessment is vital. Previous assessment techniques use either "conventional CVD risk calculators (CCVRC)" or machine learning (ML) paradigms. These techniques are ad-hoc, unreliable, not fully automated, and have variabilities. We, therefore, introduce AtheroEdge-MCDLAI (AE3.0DL) windows-based platform using multiclass Deep Learning (DL) system.

METHODS

Data was collected on 500 patients having both carotid ultrasound and corresponding coronary angiography scores (CAS), measured as stenosis in coronary arteries and considered as the gold standard. A total of 39 covariates were used, clubbed into three clusters, namely (i) Office-based: age, gender, body mass index, smoker, hypertension, systolic blood pressure, and diastolic blood pressure; (ii) Laboratory-based: Hyperlipidemia, hemoglobin A1c, and estimated glomerular filtration rate; and (iii) Carotid ultrasound image phenotypes: maximum plaque height, total plaque area, and intra-plaque neovascularization. Baseline characteristics for four classes (target labels) having significant (p < 0.0001) values were calculated using Chi-square and ANOVA. For handling the cohort's imbalance in the risk classes, AE3.0DL used the synthetic minority over-sampling technique (SMOTE). AE3.0DL used Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) DL models and the performance (accuracy and area-under-the-curve) was computed using 10-fold cross-validation (90% training, 10% testing) frameworks. AE3.0DL was validated and benchmarked.

RESULTS

The AE3.0DL using RNN and LSTM showed an accuracy and AUC (p < 0.0001) pairs as (95.00% and 0.98), and (95.34% and 0.99), respectively, and showed an improvement of 32.93% and 9.94% against CCVRC and ML, respectively. AE3.0DL runs in <1 s.

CONCLUSION

DL algorithms are a powerful paradigm for coronary artery disease (CAD) risk prediction and CVD risk stratification.

Attention-Based UNet Deep Learning Model for Plaque Segmentation in Carotid Ultrasound for Stroke Risk Stratification: An Artificial Intelligence Paradigm

Stroke and cardiovascular diseases (CVD) significantly affect the world population. The early detection of such events may prevent the burden of death and costly surgery. Conventional methods are neither automated nor clinically accurate. Artificial Intelligence-based methods of automatically detecting and predicting the severity of CVD and stroke in their early stages are of prime importance. This study proposes an attention-channel-based UNet deep learning (DL) model that identifies the carotid plaques in the internal carotid artery (ICA) and common carotid artery (CCA) images. Our experiments consist of 970 ICA images from the UK, 379 CCA images from diabetic Japanese patients, and 300 CCA images from post-menopausal women from Hong Kong. We combined both CCA images to form an integrated database of 679 images. A rotation transformation technique was applied to 679 CCA images, doubling the database for the experiments. The cross-validation K5 (80% training: 20% testing) protocol was applied for accuracy determination. The results of the Attention-UNet model are benchmarked against UNet, UNet++, and UNet3P models. Visual plaque segmentation showed improvement in the Attention-UNet results compared to the other three models. The correlation coefficient (CC) value for Attention-UNet is 0.96, compared to 0.93, 0.96, and 0.92 for UNet, UNet++, and UNet3P models. Similarly, the AUC value for Attention-UNet is 0.97, compared to 0.964, 0.966, and 0.965 for other models. Conclusively, the Attention-UNet model is beneficial in segmenting very bright and fuzzy plaque images that are hard to diagnose using other methods. Further, we present a multi-ethnic, multi-center, racial bias-free study of stroke risk assessment.

Segmentation-Based Classification Deep Learning Model Embedded with Explainable AI for COVID-19 Detection in Chest X-ray Scans

Background and Motivation: COVID-19 has resulted in a massive loss of life during the last two years. The current imaging-based diagnostic methods for COVID-19 detection in multiclass pneumonia-type chest X-rays are not so successful in clinical practice due to high error rates. Our hypothesis states that if we can have a segmentation-based classification error rate <5%, typically adopted for 510 (K) regulatory purposes, the diagnostic system can be adapted in clinical settings. Method: This study proposes 16 types of segmentation-based classification deep learning-based systems for automatic, rapid, and precise detection of COVID-19. The two deep learning-based segmentation networks, namely UNet and UNet+, along with eight classification models, namely VGG16, VGG19, Xception, InceptionV3, Densenet201, NASNetMobile, Resnet50, and MobileNet, were applied to select the best-suited combination of networks. Using the cross-entropy loss function, the system performance was evaluated by Dice, Jaccard, area-under-the-curve (AUC), and receiver operating characteristics (ROC) and validated using Grad-CAM in explainable AI framework. Results: The best performing segmentation model was UNet, which exhibited the accuracy, loss, Dice, Jaccard, and AUC of 96.35%, 0.15%, 94.88%, 90.38%, and 0.99 (p-value <0.0001), respectively. The best performing segmentation-based classification model was UNet+Xception, which exhibited the accuracy, precision, recall, F1-score, and AUC of 97.45%, 97.46%, 97.45%, 97.43%, and 0.998 (p-value <0.0001), respectively. Our system outperformed existing methods for segmentation-based classification models. The mean improvement of the UNet+Xception system over all the remaining studies was 8.27%. Conclusion: The segmentation-based classification is a viable option as the hypothesis (error rate <5%) holds true and is thus adaptable in clinical practice.

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 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.

An artificial intelligence framework and its bias for brain tumor segmentation: A narrative review

BACKGROUND

Artificial intelligence (AI) has become a prominent technique for medical diagnosis and represents an essential role in detecting brain tumors. Although AI-based models are widely used in brain lesion segmentation (BLS), understanding their effectiveness is challenging due to their complexity and diversity. Several reviews on brain tumor segmentation are available, but none of them describe a link between the threats due to risk-of-bias (RoB) in AI and its architectures. In our review, we focused on linking RoB and different AI-based architectural Cluster in popular DL framework. Further, due to variance in these designs and input data types in medical imaging, it is necessary to present a narrative review considering all facets of BLS.

APPROACH

The proposed study uses a PRISMA strategy based on 75 relevant studies found by searching PubMed, Scopus, and Google Scholar. Based on the architectural evolution, DL studies were subsequently categorized into four classes: convolutional neural network (CNN)-based, encoder-decoder (ED)-based, transfer learning (TL)-based, and hybrid DL (HDL)-based architectures. These studies were then analyzed considering 32 AI attributes, with clusters including AI architecture, imaging modalities, hyper-parameters, performance evaluation metrics, and clinical evaluation. Then, after these studies were scored for all attributes, a composite score was computed, normalized, and ranked. Thereafter, a bias cutoff (AP(ai)Bias 1.0, AtheroPoint, Roseville, CA, USA) was established to detect low-, moderate- and high-bias studies.

CONCLUSION

The four classes of architectures, from best-to worst-performing, are TL > ED > CNN > HDL. ED-based models had the lowest AI bias for BLS. This study presents a set of three primary and six secondary recommendations for lowering the RoB.

Cardiovascular disease detection using machine learning and carotid/femoral arterial imaging frameworks in rheumatoid arthritis patients

The study proposes a novel machine learning (ML) paradigm for cardiovascular disease (CVD) detection in individuals at medium to high cardiovascular risk using data from a Greek cohort of 542 individuals with rheumatoid arthritis, or diabetes mellitus, and/or arterial hypertension, using conventional or office-based, laboratory-based blood biomarkers and carotid/femoral ultrasound image-based phenotypes. Two kinds of data (CVD risk factors and presence of CVD-defined as stroke, or myocardial infarction, or coronary artery syndrome, or peripheral artery disease, or coronary heart disease) as ground truth, were collected at two-time points: (i) at visit 1 and (ii) at visit 2 after 3 years. The CVD risk factors were divided into three clusters (conventional or office-based, laboratory-based blood biomarkers, carotid ultrasound image-based phenotypes) to study their effect on the ML classifiers. Three kinds of ML classifiers (Random Forest, Support Vector Machine, and Linear Discriminant Analysis) were applied in a two-fold cross-validation framework using the data augmented by synthetic minority over-sampling technique (SMOTE) strategy. The performance of the ML classifiers was recorded. In this cohort with overall 46 CVD risk factors (covariates) implemented in an online cardiovascular framework, that requires calculation time less than 1 s per patient, a mean accuracy and area-under-the-curve (AUC) of 98.40% and 0.98 (p < 0.0001) for CVD presence detection at visit 1, and 98.39% and 0.98 (p < 0.0001) at visit 2, respectively. The performance of the cardiovascular framework was significantly better than the classical CVD risk score. The ML paradigm proved to be powerful for CVD prediction in individuals at medium to high cardiovascular risk.

COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts

(1) Background: COVID-19 computed tomography (CT) lung segmentation is critical for COVID lung severity diagnosis. Earlier proposed approaches during 2020-2021 were semiautomated or automated but not accurate, user-friendly, and industry-standard benchmarked. The proposed study compared the COVID Lung Image Analysis System, COVLIAS 1.0 (GBTI, Inc., and AtheroPointTM, Roseville, CA, USA, referred to as COVLIAS), against MedSeg, a web-based Artificial Intelligence (AI) segmentation tool, where COVLIAS uses hybrid deep learning (HDL) models for CT lung segmentation. (2) Materials and Methods: The proposed study used 5000 ITALIAN COVID-19 positive CT lung images collected from 72 patients (experimental data) that confirmed the reverse transcription-polymerase chain reaction (RT-PCR) test. Two hybrid AI models from the COVLIAS system, namely, VGG-SegNet (HDL 1) and ResNet-SegNet (HDL 2), were used to segment the CT lungs. As part of the results, we compared both COVLIAS and MedSeg against two manual delineations (MD 1 and MD 2) using (i) Bland-Altman plots, (ii) Correlation coefficient (CC) plots, (iii) Receiver operating characteristic curve, and (iv) Figure of Merit and (v) visual overlays. A cohort of 500 CROATIA COVID-19 positive CT lung images (validation data) was used. A previously trained COVLIAS model was directly applied to the validation data (as part of Unseen-AI) to segment the CT lungs and compare them against MedSeg. (3) Result: For the experimental data, the four CCs between COVLIAS (HDL 1) vs. MD 1, COVLIAS (HDL 1) vs. MD 2, COVLIAS (HDL 2) vs. MD 1, and COVLIAS (HDL 2) vs. MD 2 were 0.96, 0.96, 0.96, and 0.96, respectively. The mean value of the COVLIAS system for the above four readings was 0.96. CC between MedSeg vs. MD 1 and MedSeg vs. MD 2 was 0.98 and 0.98, respectively. Both had a mean value of 0.98. On the validation data, the CC between COVLIAS (HDL 1) vs. MedSeg and COVLIAS (HDL 2) vs. MedSeg was 0.98 and 0.99, respectively. For the experimental data, the difference between the mean values for COVLIAS and MedSeg showed a difference of <2.5%, meeting the standard of equivalence. The average running times for COVLIAS and MedSeg on a single lung CT slice were ~4 s and ~10 s, respectively. (4) Conclusions: The performances of COVLIAS and MedSeg were similar. However, COVLIAS showed improved computing time over MedSeg.

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.

Systematic Review of Artificial Intelligence in Acute Respiratory Distress Syndrome for COVID-19 Lung Patients: A Biomedical Imaging Perspective

SARS-CoV-2 has infected over ∼165 million people worldwide causing Acute Respiratory Distress Syndrome (ARDS) and has killed ∼3.4 million people. Artificial Intelligence (AI) has shown to benefit in the biomedical image such as X-ray/Computed Tomography in diagnosis of ARDS, but there are limited AI-based systematic reviews (aiSR). The purpose of this study is to understand the Risk-of-Bias (RoB) in a non-randomized AI trial for handling ARDS using novel AtheroPoint-AI-Bias (AP(ai)Bias). Our hypothesis for acceptance of a study to be in low RoB must have a mean score of 80% in a study. Using the PRISMA model, 42 best AI studies were analyzed to understand the RoB. Using the AP(ai)Bias paradigm, the top 19 studies were then chosen using the raw-cutoff of 1.9. This was obtained using the intersection of the cumulative plot of "mean score vs. study" and score distribution. Finally, these studies were benchmarked against ROBINS-I and PROBAST paradigm. Our observation showed that AP(ai)Bias, ROBINS-I, and PROBAST had only 32%, 16%, and 26% studies, respectively in low-moderate RoB (cutoff>2.5), however none of them met the RoB hypothesis. Further, the aiSR analysis recommends six primary and six secondary recommendations for the non-randomized AI for ARDS. The primary recommendations for improvement in AI-based ARDS design inclusive of (i) comorbidity, (ii) inter-and intra-observer variability studies, (iii) large data size, (iv) clinical validation, (v) granularity of COVID-19 risk, and (vi) cross-modality scientific validation. The AI is an important component for diagnosis of ARDS and the recommendations must be followed to lower the RoB.

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.

Hybrid deep learning segmentation models for atherosclerotic plaque in internal carotid artery B-mode ultrasound

The automated and accurate carotid plaque segmentation in B-mode ultrasound (US) is an essential part of stroke risk stratification. Previous segmented methods used AtheroEdge™ 2.0 (AtheroPoint™, Roseville, CA) for the common carotid artery (CCA). This study focuses on automated plaque segmentation in the internal carotid artery (ICA) using solo deep learning (SDL) and hybrid deep learning (HDL) models. The methodology consists of a novel design of 10 types of SDL/HDL models (AtheroEdge™ 3.0 systems (AtheroPoint™, Roseville, CA) with a depth of four layers each. Five of the models use cross-entropy (CE)-loss, and the other five models use Dice similarity coefficient (DSC)-loss functions derived from UNet, UNet+, SegNet, SegNet-UNet, and SegNet-UNet+. The K10 protocol (Train:Test:90%:10%) was applied for all 10 models for training and predicting (segmenting) the plaque region, which was then quantified to compute the plaque area in mm². Further, the data augmentation effect was analyzed. The database consisted of 970 ICA B-mode US scans taken from 99 moderate to high-risk patients. Using the difference area threshold of 10 mm² between ground truth (GT) and artificial intelligence (AI), the area under the curve (AUC) values were 0.91, 0.911, 0.908, 0.905, and 0.898, all with a p-value of <0.001 (for CE-loss models) and 0.883, 0.889, 0.905, 0.889, and 0.907, all with a p-value of <0.001 (for DSC-loss models). The correlations between the AI-based plaque area and GT plaque area were 0.98, 0.96, 0.97, 0.98, and 0.97, all with a p-value of <0.001 (for CE-loss models) and 0.98, 0.98, 0.97, 0.98, and 0.98 (for DSC-loss models). Overall, the online system performs plaque segmentation in less than 1 s. We validate our hypothesis that HDL and SDL models demonstrate comparable performance. SegNet-UNet was the best-performing hybrid architecture.

A Review on Joint Carotid Intima-Media Thickness and Plaque Area Measurement in Ultrasound for Cardiovascular/Stroke Risk Monitoring: Artificial Intelligence Framework

Cardiovascular diseases (CVDs) are the top ten leading causes of death worldwide. Atherosclerosis disease in the arteries is the main cause of the CVD, leading to myocardial infarction and stroke. The two primary image-based phenotypes used for monitoring the atherosclerosis burden is carotid intima-media thickness (cIMT) and plaque area (PA). Earlier segmentation and measurement methods were based on ad hoc conventional and semi-automated digital imaging solutions, which are unreliable, tedious, slow, and not robust. This study reviews the modern and automated methods such as artificial intelligence (AI)-based. Machine learning (ML) and deep learning (DL) can provide automated techniques in the detection and measurement of cIMT and PA from carotid vascular images. Both ML and DL techniques are examples of supervised learning, i.e., learn from "ground truth" images and transformation of test images that are not part of the training. This review summarizes (1) the evolution and impact of the fast-changing AI technology on cIMT/PA measurement, (2) the mathematical representations of ML/DL methods, and (3) segmentation approaches for cIMT/PA regions in carotid scans based for (a) region-of-interest detection and (b) lumen-intima and media-adventitia interface detection using ML/DL frameworks. AI-based methods for cIMT/PA segmentation have emerged for CVD/stroke risk monitoring and may expand to the recommended parameters for atherosclerosis assessment by carotid ultrasound.

Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization

The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound, contrast-enhanced ultrasound, and coronary angiography were performed on 459 participants. These participants were followed for 30 days. Plaque characteristics such as carotid intima-media thickness (cIMT), maximum plaque height (MPH), total plaque area (TPA), and intraplaque neovascularization (IPN) were measured at baseline. Two ML-based algorithms-random forest (RF) and random survival forest (RSF) were used for CAD and CV event prediction. The performance of these algorithms was compared against (i) univariate and multivariate analysis for CAD prediction using the area-under-the-curve (AUC) and (ii) Cox proportional hazard model for CV event prediction using the concordance index (c-index). There was a significant association between CAD and carotid plaque characteristics [cIMT (odds ratio (OR) = 1.49, p = 0.03), MPH (OR = 2.44, p < 0.0001), TPA (OR = 1.61, p < 0.0001), and IPN (OR = 2.78, p < 0.0001)]. IPN alone reported significant CV event prediction (hazard ratio = 1.24, p < 0.0001). CAD prediction using the RF algorithm reported an improvement in AUC by ~ 3% over the univariate analysis with IPN alone (0.97 vs. 0.94, p < 0.0001). Cardiovascular event prediction using RSF demonstrated an improvement in the c-index by ~ 17.8% over the Cox-based model (0.86 vs. 0.73). Carotid imaging phenotypes and IPN were associated with CAD and CV events. The ML-based system is superior to the conventional statistically-derived approaches for CAD prediction and survival analysis.

A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence

COVID-19 has infected 77.4 million people worldwide and has caused 1.7 million fatalities as of December 21, 2020. The primary cause of death due to COVID-19 is Acute Respiratory Distress Syndrome (ARDS). According to the World Health Organization (WHO), people who are at least 60 years old or have comorbidities that have primarily been targeted are at the highest risk from SARS-CoV-2. Medical imaging provides a non-invasive, touch-free, and relatively safer alternative tool for diagnosis during the current ongoing pandemic. Artificial intelligence (AI) scientists are developing several intelligent computer-aided diagnosis (CAD) tools in multiple imaging modalities, i.e., lung computed tomography (CT), chest X-rays, and lung ultrasounds. These AI tools assist the pulmonary and critical care clinicians through (a) faster detection of the presence of a virus, (b) classifying pneumonia types, and (c) measuring the severity of viral damage in COVID-19-infected patients. Thus, it is of the utmost importance to fully understand the requirements of for a fast and successful, and timely lung scans analysis. This narrative review first presents the pathological layout of the lungs in the COVID-19 scenario, followed by understanding and then explains the comorbid statistical distributions in the ARDS framework. The novelty of this review is the approach to classifying the AI models as per the by school of thought (SoTs), exhibiting based on segregation of techniques and their characteristics. The study also discusses the identification of AI models and its extension from non-ARDS lungs (pre-COVID-19) to ARDS lungs (post-COVID-19). Furthermore, it also presents AI workflow considerations of for medical imaging modalities in the COVID-19 framework. Finally, clinical AI design considerations will be discussed. We conclude that the design of the current existing AI models can be improved by considering comorbidity as an independent factor. Furthermore, ARDS post-processing clinical systems must involve include (i) the clinical validation and verification of AI-models, (ii) reliability and stability criteria, and (iii) easily adaptable, and (iv) generalization assessments of AI systems for their use in pulmonary, critical care, and radiological settings.

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.

Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm

BACKGROUND

Stroke is in the top three leading causes of death worldwide. Non-invasive monitoring of stroke can be accomplished via stenosis measurements. The current conventional image-based methods for these measurements are not accurate and reliable. They do not incorporate shape and intelligent learning component in their design.

METHODS

In this study, we propose a deep learning (DL)-based methodology for accurate measurement of stenosis in common carotid artery (CCA) ultrasound (US) scans using a class of AtheroEdge system from AtheroPoint, USA. Three radiologists manually traced the lumen-intima (LI) for the near and the far walls, respectively, which served as a gold standard (GS) for training the DL-based model. Three DL-based systems were developed based on three types of GS.

RESULTS

IRB approved (Toho University, Japan) 407 US scans from 204 patients were collected. The risk was characterized into three classes: low, moderate, and high-risk. The area-under-curve (AUC) corresponding to three DL systems using receiver operating characteristic (ROC) analysis computed were: 0.90, 0.94 and 0.86, respectively.

CONCLUSIONS

Novel DL-based strategy showed reliable, accurate and stable stenosis severity index (SSI) measurements.

LEFMIS: locally-oriented evaluation framework for medical image segmentation algorithms

This article proposes a novel framework for the locally-oriented evaluation of segmentation algorithms (LEFMIS). The presented approach is robust and takes into account local inter/intra-observer variability and the anisotropy of medical images. What is more, the framework makes it possible to distinguish types of error locally. These features are crucial in the context of cancer image data. The proposed framework is based on use of the signed anisotropic Euclidean distance transform and the distance projection. It can be used easily in many different applications with or without additional expert outlines (both inter- and intra-observer variability). The performance of the proposed framework is depicted using both artificial and kidney cancer CT data with experts' manual outlines. In the article, in the case of artificial data, it is presented that the manual outlines dispersion is symmetric in relation to the truth border. The effectiveness of the selected segmentation algorithm was analysed in the context of kidney cancer using computed tomography data. For the calculated local inter-observer variability, 80.11% of the surface points generated by the kidney segmentation algorithm are within one expert outline standard deviation and 97.96% are within five. An error distribution shift in the direction of type I error equivalent was also observed. Finally, the significance of the local estimation of error type differences is presented. The article shows the greater usefulness and flexibility of the proposed framework in comparison to the state-of-the-art methods. The exemplary usage of the LEFMIS with or without inter-/intra-observer variability is also presented.

Web-based accurate measurements of carotid lumen diameter and stenosis severity: An ultrasound-based clinical tool for stroke risk assessment during multicenter clinical trials

BACKGROUND

This pilot study presents a completely automated, novel, smart, cloud-based, point-of-care system for (a) carotid lumen diameter (LD); (b) stenosis severity index (SSI) and (c) total lumen area (TLA) measurement using B-mode ultrasound. The proposed system was (i) validated against manual reading taken by the Neurologist and (ii) benchmarked against the commercially available system.

METHOD

One hundred patients (73 M/27 F, mean age: 68 ± 11 years), institutional review board approved, written informed consent, consisted of left/right common carotid artery (200 ultrasound scans) were acquired using a 7.5-MHz linear transducer.

RESULTS

The measured mean LD for left and right carotids were (in mm): (i) for proposed system (6.49 ± 1.77, 6.66 ± 1.70); and (ii) for manual (6.29 ± 1.79, 6.45 ± 1.63), respectively and coefficient of correlation between cloud-based automated against manual were 0.98 (P < 0.0001) and 0.99 (P < 0.0001), respectively. The corresponding TLA error, Precision-of-Merit, and Figure-of-Merit when measured against the manual were: 4.56 ± 3.54%, 96.18 ± 3.21%, and 96.85%, respectively. The AUC for the receiving operating characteristics for the cloud-based system was: 1.0. Four statistical tests such as: Two-tailed z-test, Mann-Whitney test, Kolmogorov-Smirnov (KS) and one-way ANOVA were performed to demonstrate consistency and reliability.

CONCLUSIONS

The proposed system is reliable, accurate, fast, completely automated, anytime-anywhere solution for multi-center clinical trials and routine vascular screening.

Plaque Tissue Morphology-Based Stroke Risk Stratification Using Carotid Ultrasound: A Polling-Based PCA Learning Paradigm

Severe atherosclerosis disease in carotid arteries causes stenosis which in turn leads to stroke. Machine learning systems have been previously developed for plaque wall risk assessment using morphology-based characterization. The fundamental assumption in such systems is the extraction of the grayscale features of the plaque region. Even though these systems have the ability to perform risk stratification, they lack the ability to achieve higher performance due their inability to select and retain dominant features. This paper introduces a polling-based principal component analysis (PCA) strategy embedded in the machine learning framework to select and retain dominant features, resulting in superior performance. This leads to more stability and reliability. The automated system uses offline image data along with the ground truth labels to generate the parameters, which are then used to transform the online grayscale features to predict the risk of stroke. A set of sixteen grayscale plaque features is computed. Utilizing the cross-validation protocol (K = 10), and the PCA cutoff of 0.995, the machine learning system is able to achieve an accuracy of 98.55 and 98.83%corresponding to the carotidfar wall and near wall plaques, respectively. The corresponding reliability of the system was 94.56 and 95.63%, respectively. The automated system was validated against the manual risk assessment system and the precision of merit for same cross-validation settings and PCA cutoffs are 98.28 and 93.92%for the far and the near wall, respectively.PCA-embedded morphology-based plaque characterization shows a powerful strategy for risk assessment and can be adapted in clinical settings.

Stroke Risk Stratification and its Validation using Ultrasonic Echolucent Carotid Wall Plaque Morphology: A Machine Learning Paradigm

Stroke risk stratification based on grayscale morphology of the ultrasound carotid wall has recently been shown to have a promise in classification of high risk versus low risk plaque or symptomatic versus asymptomatic plaques. In previous studies, this stratification has been mainly based on analysis of the far wall of the carotid artery. Due to the multifocal nature of atherosclerotic disease, the plaque growth is not restricted to the far wall alone. This paper presents a new approach for stroke risk assessment by integrating assessment of both the near and far walls of the carotid artery using grayscale morphology of the plaque. Further, this paper presents a scientific validation system for stroke risk assessment. Both these innovations have never been presented before. The methodology consists of an automated segmentation system of the near wall and far wall regions in grayscale carotid B-mode ultrasound scans. Sixteen grayscale texture features are computed, and fed into the machine learning system. The training system utilizes the lumen diameter to create ground truth labels for the stratification of stroke risk. The cross-validation procedure is adapted in order to obtain the machine learning testing classification accuracy through the use of three sets of partition protocols: (5, 10, and Jack Knife). The mean classification accuracy over all the sets of partition protocols for the automated system in the far and near walls is 95.08% and 93.47%, respectively. The corresponding accuracies for the manual system are 94.06% and 92.02%, respectively. The precision of merit of the automated machine learning system when compared against manual risk assessment system are 98.05% and 97.53% for the far and near walls, respectively. The ROC of the risk assessment system for the far and near walls is close to 1.0 demonstrating high accuracy.