arXiv subjects

Reza Bozorgpour

Publications and source records attributed to Reza Bozorgpour.

8 recordsLinked to original sources

arXiv2026

A Network-Based Biomarker of Morphological Disruption Associated with Breast Cancer Malignancy

Breast cancer diagnosis commonly considers individual nuclear morphological characteristics, whereas their joint organization is less frequently evaluated. We developed the Morphological Network Disruption Index (MNDI), a patient-level measure of morphological abnormality relative to a benign reference state. Using the Wisconsin Diagnostic Breast Cancer dataset, ten nuclear characteristics were represented as network nodes, with MNDI summarizing disruption across 45 pairwise feature configurations. Performance was evaluated using repeated stratified five-fold cross-validation. Malignant lesions exhibited substantially higher MNDI than benign lesions (mean: 3.454 vs. 1.165; p = 2.94e-69). MNDI achieved an AUC of 0.941 (95% CI: 0.918-0.961), with 85.9% sensitivity and 91.6% specificity. A classifier using network-derived descriptors achieved an AUC of AUC of 0.928 +/- 0.024. Independent evaluation in the BreaKHis histopathology cohort showed limited discrimination (AUC = 0.538, 95% CI: 0.401-0.668), indicating dependence on the underlying morphological representation. MNDI provides an interpretable framework for quantifying patient-specific morphological disruption, while individual implementations require validation within compatible feature spaces.

q-bio.QM↗

arXiv2026

Performance and Interpretability of Convolutional, Transformer, and Hybrid Deep Learning Models in Colorectal Histology Classification

Deep learning has become an important tool in computational pathology, enabling automated analysis of histopathological images. While convolutional neural networks (CNNs) have traditionally dominated this field, transformer-based and hybrid architectures have recently demonstrated promising performance. However, comprehensive comparisons of these approaches for colorectal histopathology remain limited. This study evaluated twelve ImageNet-pretrained CNN, transformer, and hybrid architectures using the Kather colorectal histopathology dataset containing 5,000 image tiles from eight tissue classes. All models were trained using a standardized transfer-learning and fine-tuning protocol and assessed using multiple performance metrics, including accuracy, precision, sensitivity, specificity, F1-score, ROC-AUC, Cohen's kappa, and Matthews correlation coefficient. All evaluated models achieved high classification performance, with accuracies ranging from 93.2% to 97.1%. EVA-02 achieved the highest overall performance (97.1% accuracy, 97.0% F1-score), closely followed by ViT-B/16. Among CNNs, ResNet34 and ConvNeXt-Tiny demonstrated highly competitive performance, achieving accuracies of 96.4% and 96.3%, respectively. Transformer architectures generally produced the strongest results across evaluation metrics, although the performance gap between the best transformer and CNN models was relatively small. Per-class analysis showed consistently strong classification performance across all tissue categories, with Complex Stroma representing the most challenging class. Overall, transformer-based architectures achieved the highest predictive performance, whereas modern CNNs provided a favorable balance between accuracy and model complexity. These findings provide a comprehensive benchmark of major deep learning paradigms for colorectal histopathology classification.

q-bio.QM↗

arXiv2026

DSU-Net: An Attention-Enhanced Dense Skip U-Net for Breast Lesion Segmentation in Mammographic Images

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early detection essential for effective treatment. Mammography is the primary screening modality; however, accurate delineation of suspicious lesions remains challenging and subject to inter-observer variability. Automated segmentation methods can assist radiologists by providing consistent and efficient lesion localization. This study presents DSU-Net, an attention-enhanced Dense Skip U-Net architecture for automated breast lesion segmentation in mammographic images. The proposed framework integrates dense skip connections and attention mechanisms to improve feature propagation, preserve spatial information, and enhance lesion boundary delineation. Experiments were conducted using the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). To address severe foreground-background imbalance, a composite loss function combining Dice loss, focal loss, and binary cross-entropy loss was employed during training. The proposed model achieved a Dice Similarity Coefficient of 0.9421, an Intersection over Union of 0.8905, an accuracy of 0.9711, and an AUC-ROC of 0.9878 on the validation dataset. Qualitative evaluation demonstrated accurate delineation of lesions with varying sizes and morphologies, while quantitative results confirmed robust discrimination between lesion and background regions. These findings demonstrate that DSU-Net provides accurate and reliable breast lesion segmentation in mammographic images and highlights the potential of attention-guided deep learning for computer-aided breast cancer screening and diagnosis.

q-bio.QM↗

arXiv2026

Hemodynamic Overlap Between Ruptured and Unruptured Cerebral Aneurysms Using an In-House Parallel C++ Finite Element Solver

Cerebral aneurysm rupture has long been associated with abnormal hemodynamic conditions, particularly wall shear stress (WSS)-related flow behavior. Although aneurysm rupture is widely recognized as a multifactorial phenomenon involving complex interactions between geometry, flow structures, and multiple hemodynamic quantities, WSS-based parameters remain among the most commonly reported metrics in computational aneurysm studies. In the present study, computational fluid dynamics simulations were performed using an in-house parallel C++ finite element solver to investigate velocity streamlines, wall shear stress (WSS), and time-averaged wall shear stress (TAWSS) in patient-specific ruptured and unruptured cerebral aneurysm models. The computed flow fields demonstrated substantial hemodynamic overlap between the two groups, with elevated WSS and TAWSS regions observed in both ruptured and unruptured aneurysms. Similar high-velocity inflow structures and localized shear concentration patterns were identified across different cases, demonstrating that elevated shear-related magnitudes can be present in aneurysms with different rupture statuses. The results show that comparable WSS- and TAWSS-based hemodynamic characteristics may exist in aneurysms with different clinical outcomes, emphasizing the complexity and case-dependent nature of cerebral aneurysm hemodynamics. Rather than proposing rupture prediction criteria, the present study provides a focused computational assessment of hemodynamic similarities between ruptured and unruptured aneurysms and highlights the importance of careful interpretation of isolated WSS- and TAWSS-based analyses in rupture assessment.

physics.med-ph↗

arXiv2025

CFD-Based Quantification of Hemodynamic Variables in Cerebral Aneurysms: How Hemodynamics Shape Aneurysm Fate

Cerebral aneurysms are pathological dilations of intracranial arteries that can rupture with devastating consequences, including subarachnoid hemorrhage, stroke, and death. Accumulating evidence indicates that local hemodynamic forces play a critical role in aneurysm initiation, growth, and rupture. Computational fluid dynamics (CFD) and imaging-based techniques have enabled the extraction of various hemodynamic variables to characterize these flow conditions. However, the literature is highly fragmented, with different studies adopting distinct sets of metrics such as wall shear stress (WSS), oscillatory shear index (OSI), wall shear stress gradient (WSSG), relative residence time (RRT), or endothelial cell activation potential (ECAP) making it difficult to compare results or establish standardized methodologies. This paper provides the first comprehensive catalog of hemodynamic variables used in cerebral aneurysm studies to date. By systematically identifying and organizing these parameters based on their physical basis and frequency of use, this work offers a consolidated reference to guide future research. The goal is to support consistent variable selection, enhance reproducibility, and facilitate the design of more robust studies linking vascular biomechanics to aneurysm pathophysiology. This review aims to serve as a foundational resource for researchers and clinicians seeking to incorporate hemodynamic modeling into cerebral aneurysm analysis and risk assessment.

q-bio.OT↗

arXiv2025

Hemodynamic Markers: CFD-Based Prediction of Cerebral Aneurysm Rupture Risk

This study investigates the influence of aneurysm evolution on hemodynamic characteristics within the sac region. Using computational fluid dynamics (CFD), blood flow through the parent vessel and aneurysm sac was analyzed to assess the impact on wall shear stress (WSS), time-averaged wall shear stress (TAWSS), and the oscillatory shear index (OSI), key indicators of rupture risk. Additionally, Relative Residence Time (RRT) and Endothelial Cell Activation Potential (ECAP) were examined to provide a broader understanding of the aneurysm's hemodynamic environment. Six distinct cerebral aneurysm (CA) models, all from individuals of the same gender, were selected to minimize gender-related variability. Results showed that unruptured cases exhibited higher WSS and TAWSS, along with lower OSI and RRT values patterns consistent with stable flow conditions supporting vascular integrity. In contrast, ruptured cases had lower WSS and TAWSS, coupled with elevated OSI and RRT, suggesting disturbed and oscillatory flow commonly linked to aneurysm wall weakening. ECAP was also higher in ruptured cases, indicating increased endothelial activation under unstable flow. Notably, areas with the highest OSI and RRT often aligned with vortex centers, reinforcing the association between disturbed flow and aneurysm instability. These findings highlight the value of combining multiple hemodynamic parameters for rupture risk assessment. Including RRT and ECAP provides deeper insight into flow endothelium-interactions, offering a stronger basis for evaluating aneurysm stability and guiding treatment decisions.

q-bio.QM↗

arXiv2023

Computational Explorations in Biomedicine: Unraveling Molecular Dynamics for Cancer, Drug Delivery, and Biomolecular Insights using LAMMPS Simulations

With the rapid advancement of computational techniques, Molecular Dynamics (MD) simulations have emerged as powerful tools in biomedical research, enabling in-depth investigations of biological systems at the atomic level. Among the diverse range of simulation software available, LAMMPS (Large-scale Atomic/Molecular Massively Parallel Simulator) has gained significant recognition for its versatility, scalability, and extensive range of functionalities. This literature review aims to provide a comprehensive overview of the utilization of LAMMPS in the field of biomedical applications. This review begins by outlining the fundamental principles of MD simulations and highlighting the unique features of LAMMPS that make it suitable for biomedical research. Subsequently, a survey of the literature is conducted to identify key studies that have employed LAMMPS in various biomedical contexts, such as protein folding, drug design, biomaterials, and cellular processes. The reviewed studies demonstrate the remarkable contributions of LAMMPS in understanding the behavior of biological macromolecules, investigating drug-protein interactions, elucidating the mechanical properties of biomaterials, and studying cellular processes at the molecular level. Additionally, this review explores the integration of LAMMPS with other computational tools and experimental techniques, showcasing its potential for synergistic investigations that bridge the gap between theory and experiment. Moreover, this review discusses the challenges and limitations associated with using LAMMPS in biomedical simulations, including the parameterization of force fields, system size limitations, and computational efficiency. Strategies employed by researchers to mitigate these challenges are presented, along with potential future directions for enhancing LAMMPS capabilities in the biomedical field.

q-bio.BM↗

arXiv2023

Exploring the Role of Molecular Dynamics Simulations in Most Recent Cancer Research: Insights into Treatment Strategies

Cancer is a complex disease that is characterized by uncontrolled growth and division of cells. It involves a complex interplay between genetic and environmental factors that lead to the initiation and progression of tumors. Recent advances in molecular dynamics simulations have revolutionized our understanding of the molecular mechanisms underlying cancer initiation and progression. Molecular dynamics simulations enable researchers to study the behavior of biomolecules at an atomic level, providing insights into the dynamics and interactions of proteins, nucleic acids, and other molecules involved in cancer development. In this review paper, we provide an overview of the latest advances in molecular dynamics simulations of cancer cells. We will discuss the principles of molecular dynamics simulations and their applications in cancer research. We also explore the role of molecular dynamics simulations in understanding the interactions between cancer cells and their microenvironment, including signaling pathways, proteinprotein interactions, and other molecular processes involved in tumor initiation and progression. In addition, we highlight the current challenges and opportunities in this field and discuss the potential for developing more accurate and personalized simulations. Overall, this review paper aims to provide a comprehensive overview of the current state of molecular dynamics simulations in cancer research, with a focus on the molecular mechanisms underlying cancer initiation and progression.

q-bio.BM↗