MFMostafa Fatemi

Mostafa Fatemi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Mostafa Fatemi has a total of 294 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Added Value of Shear Wave Elastography for Noninvasive Detection of Axillary Lymph Node Metastasis and IHC-Defined Surrogate Subtype Characterization in Breast Cancer

    by Jie Chen, David P. Rosen, Tanin Adl Parvar, Robert T. Fazzio, Nicholas B. Larson, Mostafa Fatemi, Azra Alizad

    Background: Accurate preoperative characterization of axillary lymph nodes (ALNs) is important in breast cancer, but conventional ultrasound has variable diagnostic performance. We evaluated quantitative shear wave elastography (SWE) for distinguishing reactive from metastatic ALNs, and we explored associations between nodal SWE parameters, breast cancer subtypes, and histological grades. Methods: We prospectively enrolled women with suspicious breast lesions and ALNs identified by clinical ultrasound who were scheduled for biopsy. After exclusions, 141 patients (57 reactive and 84 metastatic ALNs) were included. ElasticNet-regularized logistic regression with nested cross-validation compared clinical ultrasound alone with ultrasound plus SWE. Among 70 patients with metastatic ALNs and immunohistochemical characterization, SWE parameters were compared across surrogate subtypes and histological grades using Kruskal–Wallis tests with Holm adjustments. Results: The combined ultrasound–SWE model achieved an area under the receiver operating characteristic curve of 0.911 (95% CI, 0.859–0.961) compared to 0.798 (95% CI, 0.723–0.873) for ultrasound alone. At the Youden-derived threshold, the combined model achieved 88.1% sensitivity, 82.5% specificity, and 85.8% accuracy. Among metastatic ALNs, SWE parameters, namely Vmean, Vsd, and Vmax, differed significantly across surrogate subtypes, with the most pronounced differences observed between Luminal A and Luminal B tumors, (p = 0.0250, p = 0.0069, and p = 0.0065). No statistically significant differences were detected with histological grades in the five SWE parameters. Conclusions: Quantitative SWE complemented conventional ultrasound for assessing axillary nodal metastasis, with higher cross-validated discrimination for the combined model. Exploratory analyses identified differences in several SWE stiffness metrics between Luminal A and Luminal B tumors; these subtype-associated biomechanical differences require validation in larger cohorts.

  • Applications of Artificial Intelligence in Urodynamic Data Interpretation: A Narrative Review

    by Farzad Pourghazi, Pradeep Kumar Chaudhary, Brian J. Linder, Azra Alizad, Mostafa Fatemi

    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.


  • Open Access

    BWS-Net: An Optimal Deep Learning Architecture for the Anterior Bladder Wall Segmentation using Ultrasound Imaging

    by Manali Saini, Yifei Jiang, Tuhinangshu Gangopadhyay, David P. Rosen, Azra Alizad, Mostafa Fatemi

    Urodynamic tests are used to assess bladder function by measuring detrusor pressure, which requires invasive catheterization. Ultrasound bladder vibrometry offers a non-invasive approach to evaluate bladder compliance for diagnostic purposes by estimating detrusor pressure from ultrasound-generated Lamb waves in the bladder wall. Therefore, it is crucial to precisely segment the anterior portion of bladder wall prior to these assessments. Traditional segmentation methods are time-consuming and require manual intervention, while deep learning offers a promising alternative. Existing deep learning approaches are limited and often lack clinical validation. Therefore, we propose a novel deep learning network for precise segmentation of anterior bladder wall. It comprises blueprint separable convolutional layers in an encoder-decoder structure with adaptive attention-based skip connections. Performance evaluation on 8592 distinct images acquired from 64 patients using 5-fold cross-validation demonstrates that it achieves a mean Dice score and sensitivity of 0.82 and 0.85 respectively, along with a mean root mean square error of $0.67 \pm 0.35mm$ between the thickness of predicted and ground truth portions of the bladder wall. Blueprint separable convolutions and adaptive attention-skip connections improve segmentation performance with fewer computations compared to respective standard counterparts. A comparative analysis demonstrates improvements between 2-20% in the dice score with respect to some but one of the existing networks and reductions in computational complexity by $94-96\%$ with respect to all existing networks analyzed in this work. Therefore, the proposed method can be effective for accurate bladder wall segmentation and demonstrates potential for real-time application in clinical settings.

  • Open Access

    Ultrasound urodynamic studies (US-UDS): noninvasive estimation of detrusor pressure through ultrasound

    by David P Rosen, Brian J Linder, Azra Alizad, Mostafa Fatemi

    Objective. Urodynamic studies (UDSs) are vital for evaluating bladder function but require invasive catheterization to measure detrusor pressure ( P det ). Our purpose is to report on technical developments toward a noninvasive and accurate estimation of P det through ultrasound (US), a technique we refer to as US-UDS. Approach. The proposed US-UDS technique produces an estimate of P det by using US to induce and track elastic waves that propagate within and around the bladder wall. Key components of the US-UDS processing include: an US sequence with dense time sampling; an empirical correction accounting for deviation from a Lamb wave dispersion model; and constrained optimization for P det estimation. US-UDS analysis for estimation of P det was applied to 533 distinct data points collected from 3 human subjects undergoing concurrent UDS. Concordance analysis was used to evaluate agreement between US-UDS and UDS measures of P det while response operator characteristic analysis was used to evaluate US-UDS for detection of detrusor activity (parameterized as UDS P det >15 cmH 2 O). Main results. US-UDS was able estimate P det within 10 cmH 2 O and 5 cmH 2 O of UDS measurements with coverage probabilities of 95.7% and 68.8% respectively. Furthermore, US-UDS was able to detect UDS P det measurements greater than 15 cmH 2 O with a sensitivities and specificities of 0.99 and 0.83 using a fixed threshold (>15 cmH 2 O for US-UDS) and 1.0 and 0.93 for an optimized threshold (> 11.08 cmH 2 O for US-UDS). Significance. Our results show that the technical developments of US-UDS put forth in this work are able produce accurate and useful estimates of P det as compared to traditional UDS. Although additional research with a large number of subjects is needed to fully characterize the clinical utility of US-UDS, the developments and results from this work demonstrate that clinically useful non-invasive measurements of P det are feasible from US measurements.


  • Open Access

    Artifacts in Urodynamic Studies: A Narrative Review

    by Farzad Pourghazi, Brian J. Linder, Azra Alizad, Mostafa Fatemi

    Background: Urodynamic studies (UDS) are integral to the evaluation and management of lower urinary tract dysfunction. However, artifacts are frequently encountered, affecting both clinical interpretation and research reliability. Objective: This expert narrative review examines the prevalence, classification, and clinical relevance of artifacts encountered during UDS, based on findings from the existing literature. Methods: A focused literature review was conducted, analyzing studies that reported data on the sources and impact of UDS artifacts, particularly from the patient perspective. Emphasis was placed on identifying both technical and patient‐related contributors to artifact generation. Results: Artifacts are common in UDS despite adherence to Good Urodynamic Practices recommended by the International Continence Society. Technical artifacts may stem from equipment‐related issues such as calibration errors, catheter displacement, and device variability. Patient‐related artifacts can arise from physical movement or test‐induced detrusor overactivity. These artifacts may lead to misinterpretation, misdiagnosis, and inappropriate interventions in clinical practice. Furthermore, they may affect the validity of research findings related to diagnostic tools for lower urinary tract symptoms. Conclusion: Identifying and addressing UDS artifacts during the procedure or in post‐test interpretation is critical for accurate clinical decision‐making and reliable research outcomes. Efforts to minimize artifacts should be prioritized to improve the quality and utility of UDS.


  • Open Access

    Quantitative microvessel orientation biomarkers derived from contrast free ultrasound imaging for cancer diagnosis.

    by Pradeep Kumar Chaudhary, Nicholas B Larson, Azra Alizad, Mostafa Fatemi

    Microvessel orientations are known to differ between benign and malignant tumors. This article introduces novel orientation-based quantitative biomarkers for contrast-free ultrasound microvasculature imaging to distinguish malignant from benign breast lesions. The proposed biomarkers were computed in both polar and Cartesian coordinates using images acquired by a high-definition microvasculature imaging technique. Seven biomarkers were derived based on the histogram, gradient angle, angle of penetration, and penetration factor of the microvessel. These biomarkers are first evaluated using simulated microvessel images and subsequently validated in in vivo studies on human breast masses. The new biomarkers demonstrated statistical significance in differentiating benign from malignant breast masses. In the in vivo study, the area under the receiver operating characteristic curve (AUC) for the proposed biomarkers was 0.91 (95% confidence interval [CI]: 0.86, 0.97). When the Breast Imaging Reporting and Data System (BI-RADS) score was included in the classification model, the AUC improved to 0.97 (95% CI: 0.91,1.00). These orientation-based biomarkers show promise in enhancing the diagnostic performance of ultrasound for classification of breast masses.


  • Open Access

    Artificial intelligence techniques in liver cancer

    by Lulu Wang, Mostafa Fatemi, Azra Alizad

    Hepatocellular Carcinoma (HCC), the most common primary liver cancer, is a significant contributor to worldwide cancer-related deaths. Various medical imaging techniques, including computed tomography, magnetic resonance imaging, and ultrasound, play a crucial role in accurately evaluating HCC and formulating effective treatment plans. Artificial Intelligence (AI) technologies have demonstrated potential in supporting physicians by providing more accurate and consistent medical diagnoses. Recent advancements have led to the development of AI-based multi-modal prediction systems. These systems integrate medical imaging with other modalities, such as electronic health record reports and clinical parameters, to enhance the accuracy of predicting biological characteristics and prognosis, including those associated with HCC. These multi-modal prediction systems pave the way for predicting the response to transarterial chemoembolization and microvascular invasion treatments and can assist clinicians in identifying the optimal patients with HCC who could benefit from interventional therapy. This paper provides an overview of the latest AI-based medical imaging models developed for diagnosing and predicting HCC. It also explores the challenges and potential future directions related to the clinical application of AI techniques.


  • Open Access

    Background Noise Removal in Non-Contrast- Enhanced Ultrasound Microvasculature Imaging Using Combined Collaborative, Morphological, and Vesselness Filtering

    by Soroosh Sabeti, Mostafa Fatemi, Azra Alizad

    Suppression of background noise in clutter filtered contrast-free ultrasound microvasculature images is an important step towards better visualization, accurate segmentation, and subsequent morphological analysis of vascular structures. While different approaches to tackling this problem have been proposed, the use of denoising and vessel-enhancing filters has proven to be a straightforward and effective scheme. In this paper, we propose a multi-stage background noise removal framework, suited to microvasculature images, comprising sequential implementation of three different modes of suppressing noise and intensifying vascular patterns, namely self-similarity based collaborative filtering, mathematical morphology based denoising, and Hessian based vessel enhancement. We evaluate the effects of each filtering stage in the framework using in-vitro phantom data and compare the denoising performance of the framework with a number of existing noise removal approaches, as well as the clutter filtered images in the absence of noise suppression techniques, using in-vivo data from human subjects. The results indicate that the suggested method is, in many cases, capable of complete background noise removal, zeroing out most background regions, and improving signal-to-noise ratio and contrast-to-noise ratio in other regions by tens of dB compared to the other methods.


  • Open Access

    Pulsed Vibro-Acoustic Analysis Technique for Monitoring Bone Health in Preterm Infants: A Pilot Study

    by Pradeep Kumar Chaudhary, Juanjuan Gu, David P. Rosen, Nicholas B. Larson, Jane E. Brumbaugh, Mostafa Fatemi, Azra Alizad

    Despite advances in neonatal care, metabolic bone disease of prematurity (MBDP) remains a common problem in preterm infants. The development of non-invasive and affordable diagnostic approaches can be highly beneficial in the diagnosis and management of preterm infants at risk of MBDP. In this study, we present an ultrasound method called pulsed vibro-acoustic analysis to investigate the progression of bone mineralization in infants over time versus weight and postmenstrual age. The proposed pulsed vibro-acoustic analysis method is used to evaluate the vibrational characteristics of the bone. This method uses the acoustic radiation force of ultrasound to vibrate the bone. The generated acoustic waves are detected using a hydrophone placed on the skin over the tibia. The frequency of vibration and the speeds of received acoustic waves have information regarding the material property of the bone. We examined the feasibility of this method through an in vivo study consisting of 25 preterm and 10 full term infants. The pulsed vibro-acoustic data were acquired longitudinally in preterm infants with multiple visits and at a single visit in full term infants. Speed of sound and mean peak frequency of slow and fast sound waves recorded by hydrophone were used to analyze bone mineralization progress. Linear mixed model was used for statistical analysis in characterizing the mineralization progress in preterm infants compared to data from full term subjects. Significance changes in wave parameters (speed of sound and mean peak frequency) with respect to the postmenstrual age and weight in preterm infants were observed with p-values less than 0.05. Statistical significances in speed of sound measurement for both fast and slow waves were observed between preterm and full term infants, with p-values of <0.01 and 0.02, respectively. The results of this pilot study indicate the potential use of vibro-acoustic analysis for monitoring the progression of bone mineralization in preterm infants.