Alizad, Azra

ABSTRACT Background Interpretation of urodynamic studies (UDS) is central to diagnosing lower urinary tract dysfunction, but it is often complex, time‐consuming, and subject to interobserver variability. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have enabled automated analysis of multichannel pressure–flow data and may improve objectivity and efficiency in UDS interpretation. Objective To critically review current applications of ML and DL for interpretation of multichannel UDS data and to evaluate their performance, clinical targets, and limitations. Methods A literature search of PubMed, Scopus, and Web of Science was performed through September 2, 2025, without language or date restrictions. A narrative review was conducted of peer‐reviewed studies applying ML or DL techniques to invasive UDS signals, including vesical, abdominal, and detrusor pressures as well as urinary flow. Studies limited to uroflowmetry or non‐UDS inputs were excluded. Model design, input features, validation strategies, and clinical outcomes were systematically assessed. Results A total of 12 studies met inclusion criteria. AI models were applied to a range of UDS tasks, including detection of detrusor overactivity, classification of bladder outlet obstruction and detrusor underactivity, multi‐feature UDS pattern recognition, severity grading, and real‐time event detection. Reported diagnostic performance was generally high, with many models achieving accuracies or AUCs between 80% and 95% for primary outcomes. However, study designs were heterogeneous, most datasets were retrospective and single‐center, and external validation was limited. Conclusions ML and DL approaches can extract clinically meaningful information from multichannel UDS recordings and demonstrate strong technical performance across several diagnostic tasks. However, variability in methodology, limited generalizability, and lack of prospective validation currently limit clinical adoption. AI‐based UDS interpretation remains an emerging research area requiring standardized data, robust validation, and integration with clinical workflows.

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.

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.

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.

Background and motivation: Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. Methodology: The system consists of a cascade of quality control, ResNet–UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL’s. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts—Croatia (80 COVID) and Italy (72 COVID and 30 controls)—leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. Results: Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. Conclusion: EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.

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.

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.

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.