COVLIAS 3.0: cloud-based quantized hybrid UNet3+ deep learning for COVID-19 lesion detection in lung computed tomography.

Background and novelty: When RT-PCR is ineffective in early diagnosis and understanding of COVID-19 severity, Computed Tomography (CT) scans are needed for COVID diagnosis, especially in patients having high ground-glass opacities, consolidations, and crazy paving. Radiologists find the manual method for lesion detection in CT very challenging and tedious. Previously solo deep learning (SDL) was tried but they had low to moderate-level performance. This study presents two new cloud-based quantized deep learning UNet3+ hybrid (HDL) models, which incorporated full-scale skip connections to enhance and improve the detections. Methodology: Annotations from expert radiologists were used to train one SDL (UNet3+), and two HDL models, namely, VGG-UNet3+ and ResNet-UNet3+. For accuracy, 5-fold cross-validation protocols, training on 3,500 CT scans, and testing on unseen 500 CT scans were adopted in the cloud framework. Two kinds of loss functions were used: Dice Similarity (DS) and binary cross-entropy (BCE). Performance was evaluated using (i) Area error, (ii) DS, (iii) Jaccard Index, (iii) Bland-Altman, and (iv) Correlation plots. Results: Among the two HDL models, ResNet-UNet3+ was superior to UNet3+ by 17 and 10% for Dice and BCE loss. The models were further compressed using quantization showing a percentage size reduction of 66.76, 36.64, and 46.23%, respectively, for UNet3+, VGG-UNet3+, and ResNet-UNet3+. Its stability and reliability were proved by statistical tests such as the Mann-Whitney, Paired t-Test, Wilcoxon test, and Friedman test all of which had a p < 0.001. Conclusion: Full-scale skip connections of UNet3+ with VGG and ResNet in HDL framework proved the hypothesis showing powerful results improving the detection accuracy of COVID-19.

GeneAI 3.0: powerful, novel, generalized hybrid and ensemble deep learning frameworks for miRNA species classification of stationary patterns from nucleotides.

Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present AtheroPoint's GeneAI 3.0, a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a composite feature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of 5 EML and 6 EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11 + 27 = 38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL > HDL > SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences.

Quantitative Biomarkers Derived from a Novel, Contrast-Free Ultrasound, High-Definition Microvessel Imaging for Differentiating Choroidal Tumors.

Angiogenesis has an essential role in the de novo evolution of choroidal melanoma as well as choroidal nevus transformation into melanoma. Differentiating early-stage melanoma from nevus is of high clinical importance; thus, imaging techniques that provide objective information regarding tumor microvasculature structures could aid accurate early detection. Herein, we investigated the feasibility of quantitative high-definition microvessel imaging (qHDMI) for differentiation of choroidal tumors in humans. This new ultrasound-based technique encompasses a series of morphological filtering and vessel enhancement techniques, enabling the visualization of tumor microvessels as small as 150 microns and extracting vessel morphological features as new tumor biomarkers. Distributional differences between the malignant melanomas and benign nevi were tested on 37 patients with choroidal tumors using a non-parametric Wilcoxon rank-sum test, and statistical significance was declared for biomarkers with p-values < 0.05. The ocular oncology diagnosis was choroidal melanoma (malignant) in 21 and choroidal nevus (benign) in 15 patients. The mean thickness of benign and malignant masses was 1.70 ± 0.40 mm and 3.81 ± 2.63 mm, respectively. Six HDMI biomarkers, including number of vessel segments (p = 0.003), number of branch points (p = 0.003), vessel density (p = 0.03), maximum tortuosity (p = 0.001), microvessel fractal dimension (p = 0.002), and maximum diameter (p = 0.003) exhibited significant distributional differences between the two groups. Contrast-free HDMI provided noninvasive imaging and quantification of microvessels of choroidal tumors. The results of this pilot study indicate the potential use of qHDMI as a complementary tool for characterization of small ocular tumors and early detection of choroidal melanoma.

A Force-Matched Approach to Large-Strain Nonlinearity in Elasticity Imaging for Breast Lesion Characterization.

OBJECTIVE: Ultrasound elasticity imaging is a class of ultrasound techniques with applications that include the detection of malignancy in breast lesions. Although elasticity imaging traditionally assumes linear elasticity, the large strain elastic response of soft tissue is known to be nonlinear. This study evaluates the nonlinear response of breast lesions for the characterization of malignancy using force measurement and force-controlled compression during ultrasound imaging. METHODS: 54 patients were recruited for this study. A custom force-instrumented compression device was used to apply a controlled force during ultrasound imaging. Motion tracking derived strain was averaged over lesion or background ROIs and matched with compression force. The resulting force-matched strain was used for subsequent analysis and curve fitting. RESULTS: Greater median differences between malignant and benign lesions were observed at higher compressional forces (p-value < 0.05 for compressional forces of 2-6N). Of three candidate functions, a power law function produced the best fit to the force-matched strain. A statistically significant difference in the scaling parameter of the power function between malignant and benign lesions was observed (p-value = 0.025). CONCLUSIONS: We observed a greater separation in average lesion strain between malignant and benign lesions at large compression forces and demonstrated the characterization of this nonlinear effect using a power law model. Using this model, we were able to differentiate between malignant and benign breast lesions. SIGNIFICANCE: With further development, the proposed method to utilize the nonlinear elastic response of breast tissue has the potential for improving non-invasive lesion characterization for potential malignancy.

Mapping Pharmacologically Evoked Neurovascular Activation and Its Suppression in a Rat Model of Tremor Using Functional Ultrasound: A Feasibility Study.

Functional ultrasound (fUS), an emerging hemodynamic-based functional neuroimaging technique, is especially suited to probe brain activity and primarily used in animal models. Increasing use of pharmacological models for essential tremor extends new research to the utilization of fUS imaging in such models. Harmaline-induced tremor is an easily provoked model for the development of new therapies for essential tremor (ET). Furthermore, harmaline-induced tremor can be suppressed by the same classic medications used for essential tremor, which leads to the utilization of this model for preclinical testing. However, changes in local cerebral activities under the effect of tremorgenic doses of harmaline have not been completely investigated. In this study, we explored the feasibility of fUS imaging for visualization of cerebral activation and deactivation associated with harmaline-induced tremor and tremor-suppressing effects of propranolol. The spatial resolution of fUS using a high frame rate imaging enabled us to visualize time-locked and site-specific changes in cerebral blood flow associated with harmaline-evoked tremor. Intraperitoneal administration of harmaline generated significant neural activity changes in the primary motor cortex and ventrolateral thalamus (VL Thal) regions during tremor and then gradually returned to baseline level as tremor subsided with time. To the best of our knowledge, this is the first functional ultrasound study to show the neurovascular activation of harmaline-induced tremor and the therapeutic suppression in a rat model. Thus, fUS can be considered a noninvasive imaging method for studying neuronal activities involved in the ET model and its treatment.

Contrast-free ultrasound imaging for blood flow assessment of the lower limb in patients with peripheral arterial disease: a feasibility study.

While being a relatively prevalent condition particularly among aging patients, peripheral arterial disease (PAD) of lower extremities commonly goes undetected or misdiagnosed due to its symptoms being nonspecific. Additionally, progression of PAD in the absence of timely intervention can lead to dire consequences. Therefore, development of non-invasive and affordable diagnostic approaches can be highly beneficial in detection and treatment planning for PAD patients. In this study, we present a contrast-free ultrasound-based quantitative blood flow imaging technique for PAD diagnosis. The method involves monitoring the variations of blood flow in the calf muscle in response to thigh-pressure-cuff-induced occlusion. Four quantitative metrics are introduced for analysis of these variations. These metrics include post-occlusion to baseline flow intensity variation (PBFIV), total response region (TRR), Lag0 response region (L0RR), and Lag4 (and more) response region (L4 + RR). We examine the feasibility of this method through an in vivo study consisting of 14 PAD patients with abnormal ankle-brachial index (ABI) and 8 healthy volunteers. Ultrasound data acquired from 13 legs in the patient group and 13 legs in the healthy group are analyzed. Out of the four utilized metrics, three exhibited significantly different distributions between the two groups (p-value < 0.05). More specifically, p-values of 0.0015 for PBFIV, 0.0183 for TRR, and 0.0048 for L0RR were obtained. The results of this feasibility study indicate the diagnostic potential of the proposed method for the detection of PAD.

Deep Learning in Different Ultrasound Methods for Breast Cancer, from Diagnosis to Prognosis: Current Trends, Challenges, and an Analysis.

Breast cancer is the second-leading cause of mortality among women around the world. Ultrasound (US) is one of the noninvasive imaging modalities used to diagnose breast lesions and monitor the prognosis of cancer patients. It has the highest sensitivity for diagnosing breast masses, but it shows increased false negativity due to its high operator dependency. Underserved areas do not have sufficient US expertise to diagnose breast lesions, resulting in delayed management of breast lesions. Deep learning neural networks may have the potential to facilitate early decision-making by physicians by rapidly yet accurately diagnosing and monitoring their prognosis. This article reviews the recent research trends on neural networks for breast mass ultrasound, including and beyond diagnosis. We discussed original research recently conducted to analyze which modes of ultrasound and which models have been used for which purposes, and where they show the best performance. Our analysis reveals that lesion classification showed the highest performance compared to those used for other purposes. We also found that fewer studies were performed for prognosis than diagnosis. We also discussed the limitations and future directions of ongoing research on neural networks for breast ultrasound.

Noninvasive prediction of axillary lymph node breast cancer metastasis using morphometric analysis of nodal tumor microvessels in a contrast-free ultrasound approach.

PURPOSE: Changes in microcirculation of axillary lymph nodes (ALNs) may indicate metastasis. Reliable noninvasive imaging technique to quantify such variations is lacking. We aim to develop and investigate a contrast-free ultrasound quantitative microvasculature imaging technique for detection of metastatic ALN in vivo. EXPERIMENTAL DESIGN: The proposed ultrasound-based technique, high-definition microvasculature imaging (HDMI) provides superb images of tumor microvasculature at sub-millimeter size scales and enables quantitative analysis of microvessels structures. We evaluated the new HDMI technique on 68 breast cancer patients with ultrasound-identified suspicious ipsilateral axillary lymph nodes recommended for fine needle aspiration biopsy (FNAB). HDMI was conducted before the FNAB and vessel morphological features were extracted, analyzed, and the results were correlated with the histopathology. RESULTS: Out of 15 evaluated quantitative HDMI biomarkers, 11 were significantly different in metastatic and reactive ALNs (10 with P << 0.01 and one with 0.01 < P < 0.05). We further showed that through analysis of these biomarkers, a predictive model trained on HDMI biomarkers combined with clinical information (i.e., age, node size, cortical thickness, and BI-RADS score) could identify metastatic lymph nodes with an area under the curve of 0.9 (95% CI [0.82,0.98]), sensitivity of 90%, and specificity of 88%. CONCLUSIONS: The promising results of our morphometric analysis of HDMI on ALNs offer a new means of detecting lymph node metastasis when used as a complementary imaging tool to conventional ultrasound. The fact that it does not require injection of contrast agents simplifies its use in routine clinical practice.

Custom-made flow phantoms for quantitative ultrasound microvessel imaging.

Morphologically realistic flow phantoms are essential experimental tools for quantitative ultrasound-based microvessel imaging. As new quantitative flow imaging tools are developed, the need for more complex vessel-mimicking phantoms is indisputable. In this article, we propose a method for fabricating phantoms with sub-millimeter channels consisting of branches and curvatures in various shapes and sizes suitable for quantifying vessel morphological features. We used different tissue-mimicking materials (TMMs) compatible with ultrasound imaging as the base and metal wires of different diameters (0.15-1.25 mm) to create wall-less channels. The TMMs used are silicone rubber, plastisol, conventional gelatin, and medical gelatin. Mother channels in these phantoms were made in diameters of 1.25 mm or 0.3 mm and the daughter channels in diameters 0.3 mm or 0.15 mm. Bifurcations were created by soldering wires together at branch points. Quantitative parameters were assessed, and accuracy of measurements from the ground truth were determined. Channel diameters were seen to have increased (76-270%) compared to the initial state in the power Doppler images, partly due to blood mimicking fluid pressure. Amongst the microflow phantoms made from the different TMMs, the medical gelatin phantom was selected as the best option for microflow imaging, fulfilling the objective of being easy to fabricate with high transmittance while having a speed of sound and acoustic attenuation close to human tissue. A flow velocity of 0.85 ± 0.01 mm/s, comparable to physiological flow velocity was observed in the smallest diameter phantom (medical gelatin branch) presented here. We successfully constructed more complex geometries, including tortuous and multibranch channels using the medical gelatin as the TMM. We anticipate this will create new avenues for validating quantitative ultrasound microvessel imaging techniques.

Morphometric analysis of tumor microvessels for detection of hepatocellular carcinoma using contrast-free ultrasound imaging: A feasibility study.

Introduction: A contrast-free ultrasound microvasculature imaging technique was evaluated in this study to determine whether extracting morphological features of the vascular networks in hepatic lesions can be beneficial in differentiating benign and malignant tumors (hepatocellular carcinoma (HCC) in particular). Methods: A total of 29 lesions from 22 patients were included in this work. A post-processing algorithm consisting of clutter filtering, denoising, and vessel enhancement steps was implemented on ultrasound data to visualize microvessel structures. These structures were then further characterized and quantified through additional image processing. A total of nine morphological metrics were examined to compare different groups of lesions. A two-sided Wilcoxon rank sum test was used for statistical analysis. Results: In the malignant versus benign comparison, six of the metrics manifested statistical significance. Comparing only HCC cases with the benign, only three of the metrics were significantly different. No statistically significant distinction was observed between different malignancies (HCC versus cholangiocarcinoma and metastatic adenocarcinoma) for any of the metrics. Discussion: Obtained results suggest that designing predictive models based on such morphological characteristics on a larger sample size may prove helpful in differentiating benign from malignant liver masses.

Quantitative Biomarkers Derived from a Novel Contrast-Free Ultrasound High-Definition Microvessel Imaging for Distinguishing Thyroid Nodules.

Low specificity in current ultrasound modalities for thyroid cancer detection necessitates the development of new imaging modalities for optimal characterization of thyroid nodules. Herein, the quantitative biomarkers of a new high-definition microvessel imaging (HDMI) were evaluated for discrimination of benign from malignant thyroid nodules. Without the help of contrast agents, this new ultrasound-based quantitative technique utilizes processing methods including clutter filtering, denoising, vessel enhancement filtering, morphological filtering, and vessel segmentation to resolve tumor microvessels at size scales of a few hundred microns and enables the extraction of vessel morphological features as new tumor biomarkers. We evaluated quantitative HDMI on 92 patients with 92 thyroid nodules identified in ultrasound. A total of 12 biomarkers derived from vessel morphological parameters were associated with pathology results. Using the Wilcoxon rank-sum test, six of the twelve biomarkers were significantly different in distribution between the malignant and benign nodules (all p < 0.01). A support vector machine (SVM)-based classification model was trained on these six biomarkers, and the receiver operating characteristic curve (ROC) showed an area under the curve (AUC) of 0.9005 (95% CI: [0.8279,0.9732]) with sensitivity, specificity, and accuracy of 0.7778, 0.9474, and 0.8929, respectively. When additional clinical data, namely TI-RADS, age, and nodule size were added to the features, model performance reached an AUC of 0.9044 (95% CI: [0.8331,0.9757]) with sensitivity, specificity, and accuracy of 0.8750, 0.8235, and 0.8400, respectively. Our findings suggest that tumor vessel morphological features may improve the characterization of thyroid nodules.

Volumetric imaging and morphometric analysis of breast tumor angiogenesis using a new contrast-free ultrasound technique: a feasibility study.

BACKGROUND: There is a strong correlation between the morphological features of new tumor vessels and malignancy. However, angiogenic heterogeneity necessitates 3D microvascular data of tumor microvessels for more reliable quantification. To provide more accurate information regarding vessel morphological features and improve breast lesion characterization, we introduced a quantitative 3D high-definition microvasculature imaging (q3D-HDMI) as a new easily applicable and robust tool to morphologically characterize microvasculature networks in breast tumors using a contrast-free ultrasound-based imaging approach. METHODS: In this prospective study, from January 2020 through December 2021, a newly developed q3D-HDMI technique was evaluated on participants with ultrasound-identified suspicious breast lesions recommended for core needle biopsy. The morphological features of breast tumor microvessels were extracted from the q3D-HDMI. Leave-one-out cross-validation (LOOCV) was applied to test the combined diagnostic performance of multiple morphological parameters of breast tumor microvessels. Receiver operating characteristic (ROC) curves were used to evaluate the prediction performance of the generated pooled model. RESULTS: Ninety-three participants (mean age 52 ± 17 years, 91 women) with 93 breast lesions were studied. The area under the ROC curve (AUC) generated with q3D-HDMI was 95.8% (95% CI 0.901-1.000), yielding a sensitivity of 91.7% and a specificity of 98.2%, that was significantly higher than the AUC generated with the q2D-HDMI (p = 0.02). When compared to q2D-HDMI, the tumor microvessel morphological parameters obtained from q3D-HDMI provides distinctive information that increases accuracy in differentiating breast tumors. CONCLUSIONS: The proposed quantitative volumetric imaging technique augments conventional breast ultrasound evaluation by increasing specificity in differentiating malignant from benign breast masses.

Economics of Artificial Intelligence in Healthcare: Diagnosis vs. Treatment.

Motivation: The price of medical treatment continues to rise due to (i) an increasing population; (ii) an aging human growth; (iii) disease prevalence; (iv) a rise in the frequency of patients that utilize health care services; and (v) increase in the price. Objective: Artificial Intelligence (AI) is already well-known for its superiority in various healthcare applications, including the segmentation of lesions in images, speech recognition, smartphone personal assistants, navigation, ride-sharing apps, and many more. Our study is based on two hypotheses: (i) AI offers more economic solutions compared to conventional methods; (ii) AI treatment offers stronger economics compared to AI diagnosis. This novel study aims to evaluate AI technology in the context of healthcare costs, namely in the areas of diagnosis and treatment, and then compare it to the traditional or non-AI-based approaches. Methodology: PRISMA was used to select the best 200 studies for AI in healthcare with a primary focus on cost reduction, especially towards diagnosis and treatment. We defined the diagnosis and treatment architectures, investigated their characteristics, and categorized the roles that AI plays in the diagnostic and therapeutic paradigms. We experimented with various combinations of different assumptions by integrating AI and then comparing it against conventional costs. Lastly, we dwell on three powerful future concepts of AI, namely, pruning, bias, explainability, and regulatory approvals of AI systems. Conclusions: The model shows tremendous cost savings using AI tools in diagnosis and treatment. The economics of AI can be improved by incorporating pruning, reduction in AI bias, explainability, and regulatory approvals.

Cardiovascular/Stroke Risk Stratification in Diabetic Foot Infection Patients Using Deep Learning-Based Artificial Intelligence: An Investigative Study.

A diabetic foot infection (DFI) is among the most serious, incurable, and costly to treat conditions. The presence of a DFI renders machine learning (ML) systems extremely nonlinear, posing difficulties in CVD/stroke risk stratification. In addition, there is a limited number of well-explained ML paradigms due to comorbidity, sample size limits, and weak scientific and clinical validation methodologies. Deep neural networks (DNN) are potent machines for learning that generalize nonlinear situations. The objective of this article is to propose a novel investigation of deep learning (DL) solutions for predicting CVD/stroke risk in DFI patients. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) search strategy was used for the selection of 207 studies. We hypothesize that a DFI is responsible for increased morbidity and mortality due to the worsening of atherosclerotic disease and affecting coronary artery disease (CAD). Since surrogate biomarkers for CAD, such as carotid artery disease, can be used for monitoring CVD, we can thus use a DL-based model, namely, Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN) for CVD/stroke risk prediction in DFI patients, which combines covariates such as office and laboratory-based biomarkers, carotid ultrasound image phenotype (CUSIP) lesions, along with the DFI severity. We confirmed the viability of CVD/stroke risk stratification in the DFI patients. Strong designs were found in the research of the DL architectures for CVD/stroke risk stratification. Finally, we analyzed the AI bias and proposed strategies for the early diagnosis of CVD/stroke in DFI patients. Since DFI patients have an aggressive atherosclerotic disease, leading to prominent CVD/stroke risk, we, therefore, conclude that the DL paradigm is very effective for predicting the risk of CVD/stroke in DFI patients.

Vascular Implications of COVID-19: Role of Radiological Imaging, Artificial Intelligence, and Tissue Characterization: A Special Report.

The SARS-CoV-2 virus has caused a pandemic, infecting nearly 80 million people worldwide, with mortality exceeding six million. The average survival span is just 14 days from the time the symptoms become aggressive. The present study delineates the deep-driven vascular damage in the pulmonary, renal, coronary, and carotid vessels due to SARS-CoV-2. This special report addresses an important gap in the literature in understanding (i) the pathophysiology of vascular damage and the role of medical imaging in the visualization of the damage caused by SARS-CoV-2, and (ii) further understanding the severity of COVID-19 using artificial intelligence (AI)-based tissue characterization (TC). PRISMA was used to select 296 studies for AI-based TC. Radiological imaging techniques such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound were selected for imaging of the vasculature infected by COVID-19. Four kinds of hypotheses are presented for showing the vascular damage in radiological images due to COVID-19. Three kinds of AI models, namely, machine learning, deep learning, and transfer learning, are used for TC. Further, the study presents recommendations for improving AI-based architectures for vascular studies. We conclude that the process of vascular damage due to COVID-19 has similarities across vessel types, even though it results in multi-organ dysfunction. Although the mortality rate is ~2% of those infected, the long-term effect of COVID-19 needs monitoring to avoid deaths. AI seems to be penetrating the health care industry at warp speed, and we expect to see an emerging role in patient care, reduce the mortality and morbidity rate.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson's Disease Affected by COVID-19: A Narrative Review.

Background and Motivation: Parkinson's disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

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.

Added value of mass characteristic frequency to 2-D shear wave elastography for differentiation of benign and malignant thyroid nodules.

Mass characteristic frequency (fmass) is a novel shear wave (SW) parameter that represents the ratio of the averaged minimum SW speed within the regions of interest to the largest dimension of the mass. Our study objective was to evaluate if the addition of fmass to conventional 2-D shear wave elastography (SWE) parameters would improve the differentiation of benign from malignant thyroid nodules. Our cohort comprised 107 patients with 113 thyroid nodules, of which 67 (59%) were malignant. Two-dimensional SWE data were obtained using the Supersonic Imagine Aixplorer ultrasound system equipped with a 44- to 15-MHz15-MHz linear array transducer. A receiver operating characteristic curve was generated based on a multivariable logistic regression analysis to evaluate the ability of SWE parameters with/without fmass and with/without clinical factors to discriminate benign from malignant thyroid nodules. The addition of fmass to conventional SW elasticity parameters increased the area under the curve from 0.808 to 0.871 (p = 0.02). The combination of SW elasticity parameters plus fmass plus clinical factors provided the strongest thyroid nodule malignancy probability estimate, with a sensitivity of 93.4% and specificity of 91.1% at the optimal threshold. In summary, fmass can be a valuable addition to conventional 2-D SWE parameters.

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.

Cardiovascular Risk Stratification in Diabetic Retinopathy via Atherosclerotic Pathway in COVID-19/Non-COVID-19 Frameworks Using Artificial Intelligence Paradigm: A Narrative Review.

Diabetes is one of the main causes of the rising cases of blindness in adults. This microvascular complication of diabetes is termed diabetic retinopathy (DR) and is associated with an expanding risk of cardiovascular events in diabetes patients. DR, in its various forms, is seen to be a powerful indicator of atherosclerosis. Further, the macrovascular complication of diabetes leads to coronary artery disease (CAD). Thus, the timely identification of cardiovascular disease (CVD) complications in DR patients is of utmost importance. Since CAD risk assessment is expensive for low-income countries, it is important to look for surrogate biomarkers for risk stratification of CVD in DR patients. Due to the common genetic makeup between the coronary and carotid arteries, low-cost, high-resolution imaging such as carotid B-mode ultrasound (US) can be used for arterial tissue characterization and risk stratification in DR patients. The advent of artificial intelligence (AI) techniques has facilitated the handling of large cohorts in a big data framework to identify atherosclerotic plaque features in arterial ultrasound. This enables timely CVD risk assessment and risk stratification of patients with DR. Thus, this review focuses on understanding the pathophysiology of DR, retinal and CAD imaging, the role of surrogate markers for CVD, and finally, the CVD risk stratification of DR patients. The review shows a step-by-step cyclic activity of how diabetes and atherosclerotic disease cause DR, leading to the worsening of CVD. We propose a solution to how AI can help in the identification of CVD risk. Lastly, we analyze the role of DR/CVD in the COVID-19 framework.