arXiv subjects

Essam A. Rashed

Publications and source records attributed to Essam A. Rashed.

At least 19 recordsLinked to original sources

arXiv2026

Energy-Mamba: A Physics-Constrained State-Space Model for Medical Image Classification

State-Space Models (SSMs), particularly Mamba, offer linear-time complexity for long-range dependencies, making them attractive for medical imaging with limited annotated data. However, adapting these sequential models to 2D images through unconstrained state evolution causes representational drift, the dynamic hidden state progressively loses fidelity to local image features. We introduce Energy-Mamba, integrating SSM dynamics with physics-informed constraints via a learnable potential energy function that quantifies compatibility between evolving states and static local features. Our Energy-Mamba Block introduces a gradient-based forcing term, computed dynamically via automatic differentiation, that pulls states toward low-energy configurations maintaining local visual fidelity. This formulation mirrors Hamiltonian dynamics: kinetic energy (SSM scan) plus potential energy (our constraint function) govern state trajectories. This architectural prior enables learning implicit constraints for robust, faithful representations, crucial in medical imaging where fine-grained local detail drives accurate diagnosis. Evaluated on four datasets (retinal OCT, chest X-ray, microscopy, abdominal CT), Energy-Mamba achieves state-of-the-art classification performance with significantly fewer parameters, demonstrating that physics-informed grounding can enhance both efficiency and representational quality in medical vision tasks.

eess.IV↗

arXiv2025

MammoClean: Toward Reproducible and Bias-Aware AI in Mammography through Dataset Harmonization

The development of clinically reliable artificial intelligence (AI) systems for mammography is hindered by profound heterogeneity in data quality, metadata standards, and population distributions across public datasets. This heterogeneity introduces dataset-specific biases that severely compromise the generalizability of the model, a fundamental barrier to clinical deployment. We present MammoClean, a public framework for standardization and bias quantification in mammography datasets. MammoClean standardizes case selection, image processing (including laterality and intensity correction), and unifies metadata into a consistent multi-view structure. We provide a comprehensive review of breast anatomy, imaging characteristics, and public mammography datasets to systematically identify key sources of bias. Applying MammoClean to three heterogeneous datasets (CBIS-DDSM, TOMPEI-CMMD, VinDr-Mammo), we quantify substantial distributional shifts in breast density and abnormality prevalence. Critically, we demonstrate the direct impact of data corruption: AI models trained on corrupted datasets exhibit significant performance degradation compared to their curated counterparts. By using MammoClean to identify and mitigate bias sources, researchers can construct unified multi-dataset training corpora that enable development of robust models with superior cross-domain generalization. MammoClean provides an essential, reproducible pipeline for bias-aware AI development in mammography, facilitating fairer comparisons and advancing the creation of safe, effective systems that perform equitably across diverse patient populations and clinical settings. The open-source code is publicly available from: https://github.com/Minds-R-Lab/MammoClean.

eess.IV↗

arXiv2025

CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering

High-performing medical Large Language Models (LLMs) typically require extensive fine-tuning with substantial computational resources, limiting accessibility for resource-constrained healthcare institutions. This study introduces a confidence-driven multi-model framework that leverages model diversity to enhance medical question answering without fine-tuning. Our framework employs a two-stage architecture: a confidence detection module assesses the primary model's certainty, and an adaptive routing mechanism directs low-confidence queries to Helper models with complementary knowledge for collaborative reasoning. We evaluate our approach using Qwen3-30B-A3B-Instruct, Phi-4 14B, and Gemma 2 12B across three medical benchmarks; MedQA, MedMCQA, and PubMedQA. Result demonstrate that our framework achieves competitive performance, with particularly strong results in PubMedQA (95.0\%) and MedMCQA (78.0\%). Ablation studies confirm that confidence-aware routing combined with multi-model collaboration substantially outperforms single-model approaches and uniform reasoning strategies. This work establishes that strategic model collaboration offers a practical, computationally efficient pathway to improve medical AI systems, with significant implications for democratizing access to advanced medical AI in resource-limited settings.

cs.CL↗

arXiv2025

Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications

Medical Image Segmentation (MIS) stands as a cornerstone in medical image analysis, playing a pivotal role in precise diagnostics, treatment planning, and monitoring of various medical conditions. This paper presents a comprehensive and systematic survey of MIS methodologies, bridging the gap between traditional image processing techniques and modern deep learning approaches. The survey encompasses thresholding, edge detection, region-based segmentation, clustering algorithms, and model-based techniques while also delving into state-of-the-art deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), and the widely adopted U-Net and its variants. Moreover, integrating attention mechanisms, semi-supervised learning, generative adversarial networks (GANs), and Transformer-based models is thoroughly explored. In addition to covering established methods, this survey highlights emerging trends, including hybrid architectures, cross-modality learning, federated and distributed learning frameworks, and active learning strategies, which aim to address challenges such as limited labeled datasets, computational complexity, and model generalizability across diverse imaging modalities. Furthermore, a specialized case study on lumbar spine segmentation is presented, offering insights into the challenges and advancements in this relatively underexplored anatomical region. Despite significant progress in the field, critical challenges persist, including dataset bias, domain adaptation, interpretability of deep learning models, and integration into real-world clinical workflows.

cs.CV↗

arXiv2025

Medical AI Consensus: A Multi-Agent Framework for Radiology Report Generation and Evaluation

Automating radiology report generation poses a dual challenge: building clinically reliable systems and designing rigorous evaluation protocols. We introduce a multi-agent reinforcement learning framework that serves as both a benchmark and evaluation environment for multimodal clinical reasoning in the radiology ecosystem. The proposed framework integrates large language models (LLMs) and large vision models (LVMs) within a modular architecture composed of ten specialized agents responsible for image analysis, feature extraction, report generation, review, and evaluation. This design enables fine-grained assessment at both the agent level (e.g., detection and segmentation accuracy) and the consensus level (e.g., report quality and clinical relevance). We demonstrate an implementation using chatGPT-4o on public radiology datasets, where LLMs act as evaluators alongside medical radiologist feedback. By aligning evaluation protocols with the LLM development lifecycle, including pretraining, finetuning, alignment, and deployment, the proposed benchmark establishes a path toward trustworthy deviance-based radiology report generation.

cs.AI↗

arXiv2025

A Hybrid CNN-VSSM model for Multi-View, Multi-Task Mammography Analysis: Robust Diagnosis with Attention-Based Fusion

Early and accurate interpretation of screening mammograms is essential for effective breast cancer detection, yet it remains a complex challenge due to subtle imaging findings and diagnostic ambiguity. Many existing AI approaches fall short by focusing on single view inputs or single-task outputs, limiting their clinical utility. To address these limitations, we propose a novel multi-view, multitask hybrid deep learning framework that processes all four standard mammography views and jointly predicts diagnostic labels and BI-RADS scores for each breast. Our architecture integrates a hybrid CNN VSSM backbone, combining convolutional encoders for rich local feature extraction with Visual State Space Models (VSSMs) to capture global contextual dependencies. To improve robustness and interpretability, we incorporate a gated attention-based fusion module that dynamically weights information across views, effectively handling cases with missing data. We conduct extensive experiments across diagnostic tasks of varying complexity, benchmarking our proposed hybrid models against baseline CNN architectures and VSSM models in both single task and multi task learning settings. Across all tasks, the hybrid models consistently outperform the baselines. In the binary BI-RADS 1 vs. 5 classification task, the shared hybrid model achieves an AUC of 0.9967 and an F1 score of 0.9830. For the more challenging ternary classification, it attains an F1 score of 0.7790, while in the five-class BI-RADS task, the best F1 score reaches 0.4904. These results highlight the effectiveness of the proposed hybrid framework and underscore both the potential and limitations of multitask learning for improving diagnostic performance and enabling clinically meaningful mammography analysis.

eess.IV↗

arXiv2024

Neuro-TransUNet: Segmentation of stroke lesion in MRI using transformers

Accurate segmentation of the stroke lesions using magnetic resonance imaging (MRI) is associated with difficulties due to the complicated anatomy of the brain and the different properties of the lesions. This study introduces the Neuro-TransUNet framework, which synergizes the U-Net's spatial feature extraction with SwinUNETR's global contextual processing ability, further enhanced by advanced feature fusion and segmentation synthesis techniques. The comprehensive data pre-processing pipeline improves the framework's efficiency, which involves resampling, bias correction, and data standardization, enhancing data quality and consistency. Ablation studies confirm the significant impact of the advanced integration of U-Net with SwinUNETR and data pre-processing pipelines on performance and demonstrate the model's effectiveness. The proposed Neuro-TransUNet model, trained with the ATLAS v2.0 \emph{training} dataset, outperforms existing deep learning algorithms and establishes a new benchmark in stroke lesion segmentation.

eess.IV↗

arXiv2024

Transformers-based architectures for stroke segmentation: A review

Stroke remains a significant global health concern, necessitating precise and efficient diagnostic tools for timely intervention and improved patient outcomes. The emergence of deep learning methodologies has transformed the landscape of medical image analysis. Recently, Transformers, initially designed for natural language processing, have exhibited remarkable capabilities in various computer vision applications, including medical image analysis. This comprehensive review aims to provide an in-depth exploration of the cutting-edge Transformer-based architectures applied in the context of stroke segmentation. It commences with an exploration of stroke pathology, imaging modalities, and the challenges associated with accurate diagnosis and segmentation. Subsequently, the review delves into the fundamental ideas of Transformers, offering detailed insights into their architectural intricacies and the underlying mechanisms that empower them to effectively capture complex spatial information within medical images. The existing literature is systematically categorized and analyzed, discussing various approaches that leverage Transformers for stroke segmentation. A critical assessment is provided, highlighting the strengths and limitations of these methods, including considerations of performance and computational efficiency. Additionally, this review explores potential avenues for future research and development

eess.IV↗

arXiv2024

Deep models for stroke segmentation: do complex architectures always perform better?

Stroke segmentation plays a crucial role in the diagnosis and treatment of stroke patients by providing spatial information about affected brain regions and the extent of damage. Segmenting stroke lesions accurately is a challenging task, given that conventional manual techniques are time consuming and prone to errors. Recently, advanced deep models have been introduced for general medical image segmentation, demonstrating promising results that surpass many state of the art networks when evaluated on specific datasets. With the advent of the vision Transformers, several models have been introduced based on them, while others have aimed to design better modules based on traditional convolutional layers to extract long-range dependencies like Transformers. The question of whether such high-level designs are necessary for all segmentation cases to achieve the best results remains unanswered. In this study, we selected four types of deep models that were recently proposed and evaluated their performance for stroke segmentation: a pure Transformer-based architecture (DAE-Former), two advanced CNN-based models (LKA and DLKA) with attention mechanisms in their design, an advanced hybrid model that incorporates CNNs with Transformers (FCT), and the well-known self-adaptive nnUNet framework with its configuration based on given data. We examined their performance on two publicly available datasets, and found that the nnUNet achieved the best results with the simplest design among all. Revealing the robustness issue of Transformers to such variabilities serves as a potential reason for their weaker performance. Furthermore, nnUNet's success underscores the significant impact of preprocessing and postprocessing techniques in enhancing segmentation results, surpassing the focus solely on architectural designs

eess.IV↗

arXiv2023

SHARM: Segmented Head Anatomical Reference Models

Reliable segmentation of anatomical tissues of human head is a major step in several clinical applications such as brain mapping, surgery planning and associated computational simulation studies. Segmentation is based on identifying different anatomical structures through labeling different tissues through medical imaging modalities. The segmentation of brain structures is commonly feasible with several remarkable contributions mainly for medical perspective; however, non-brain tissues are of less interest due to anatomical complexity and difficulties to be observed using standard medical imaging protocols. The lack of whole head segmentation methods and unavailability of large human head segmented datasets limiting the variability studies, especially in the computational evaluation of electrical brain stimulation (neuromodulation), human protection from electromagnetic field, and electroencephalography where non-brain tissues are of great importance. To fill this gap, this study provides an open-access Segmented Head Anatomical Reference Models (SHARM) that consists of 196 subjects. These models are segmented into 15 different tissues; skin, fat, muscle, skull cancellous bone, skull cortical bone, brain white matter, brain gray matter, cerebellum white matter, cerebellum gray matter, cerebrospinal fluid, dura, vitreous humor, lens, mucous tissue and blood vessels. The segmented head models are generated using open-access IXI MRI dataset through convolutional neural network structure named ForkNet+. Results indicate a high consistency in statistical characteristics of different tissue distribution in age scale with real measurements. SHARM is expected to be a useful benchmark not only for electromagnetic dosimetry studies but also for different human head segmentation applications.

cs.CV↗

arXiv2022

COVID-19 forecasting using new viral variants and vaccination effectiveness models

Background: Recently, a high number of daily positive COVID-19 cases have been reported in regions with relatively high vaccination rates; hence, booster vaccination has become necessary. In addition, infections caused by the different variants and correlated factors have not been discussed in depth. With large variabilities and different co-factors, it is difficult to use conventional mathematical models to forecast the incidence of COVID-19. Methods: Machine learning based on long short-term memory was applied to forecasting the time series of new daily positive cases (DPC), serious cases, hospitalized cases, and deaths. Data acquired from regions with high rates of vaccination, such as Israel, were blended with the current data of other regions in Japan to factor in the potential effects of vaccination. The protection provided by symptomatic infection was also considered in terms of the population effectiveness of vaccination as well as the waning protection and ratio and infectivity of viral variants. To represent changes in public behavior, public mobility and interactions through social media were also included in the analysis. Findings: Comparing the observed and estimated new DPC in Tel Aviv, Israel, the parameters characterizing vaccination effectiveness and the waning protection from infection were well estimated; the vaccination effectiveness of the second dose after 5 months and the third dose after two weeks from infection by the delta variant were 0.24 and 0.95, respectively. Using the extracted parameters regarding vaccination effectiveness, new cases in three prefectures of Japan were replicated.

cs.LG↗

arXiv2021

Mobility-Dependent and Mobility-Compensated Effective Reproduction Number of COVID-19 Viral Variants: New Metric for Infectivity Evaluation

During epidemics, estimation of the effective reproduction number (ERN) associated with infectious disease is a challenging topic for policy development and medical resource management. There is still an open question about the dominant factors to characterize in corona virus disease 2019 (COVID-19), although recent studies based on nonlinear regression with machine learning suggested mobility. The emergence of new viral variants is common in widespread pandemics. However, understanding the potential ERN of new variants is required for policy revision, including lockdown constraints. In this study, we proposed time-averaged mobility at transit stations as a surrogate to correlate with ERN using data from three prefectures in Japan. The latency and duration to average over the mobility were 6-8 days and 6-7, respectively (R2 was 0.109-0.512 in Tokyo, 0.365-0.607 in Osaka, and 0.317-0.631 in Aichi). The same linear correlation was confirmed in Singapore and London. The mobility-adjusted ERN of the alpha variant was 15%-30%, and was 20%-40% higher than the standard type in Osaka, Aichi, and London. Similarly, the ERN of the delta variant was 20%-40% higher than that of the standard type in Osaka and Aichi. The proposed metric would be useful for proper evaluation of the infectivity of different variants in terms of ERN.

q-bio.PE↗

arXiv2021

Knowledge discovery from emergency ambulance dispatch during COVID-19: A case study of Nagoya City, Japan

Accurate forecasting of medical service requirements is an important big data problem that is crucial for resource management in critical times such as natural disasters and pandemics. With the global spread of coronavirus disease 2019 (COVID-19), several concerns have been raised regarding the ability of medical systems to handle sudden changes in the daily routines of healthcare providers. One significant problem is the management of ambulance dispatch and control during a pandemic. To help address this problem, we first analyze ambulance dispatch data records from April 2014 to August 2020 for Nagoya City, Japan. Significant changes were observed in the data during the pandemic, including the state of emergency (SoE) declared across Japan. In this study, we propose a deep learning framework based on recurrent neural networks to estimate the number of emergency ambulance dispatches (EADs) during a SoE. The fusion of data includes environmental factors, the localization data of mobile phone users, and the past history of EADs, thereby providing a general framework for knowledge discovery and better resource management. The results indicate that the proposed blend of training data can be used efficiently in a real-world estimation of EAD requirements during periods of high uncertainties such as pandemics.

cs.AI↗

arXiv2021

Influence of segmentation accuracy in structural MR head scans on electric field computation for TMS and tES

In several diagnosis and therapy procedures based on electrostimulation effect, the internal physical quantity related to the stimulation is the induced electric field. To estimate the induced electric field in an individual human model, the segmentation of anatomical imaging, such as (magnetic resonance image (MRI) scans, of the corresponding body parts into tissues is required. Then, electrical properties associated with different annotated tissues are assigned to the digital model to generate a volume conductor. An open question is how segmentation accuracy of different tissues would influence the distribution of the induced electric field. In this study, we applied parametric segmentation of different tissues to exploit the segmentation of available MRI to generate different quality of head models using deep learning neural network architecture, named ForkNet. Then, the induced electric field are compared to assess the effect of model segmentation variations. Computational results indicate that the influence of segmentation error is tissue-dependent. In brain, sensitivity to segmentation accuracy is relatively high in cerebrospinal fluid (CSF), moderate in gray matter (GM) and low in white matter for transcranial magnetic stimulation (TMS) and transcranial electrical stimulation (tES). A CSF segmentation accuracy reduction of 10% in terms of Dice coefficient (DC) lead to decrease up to 4% in normalized induced electric field in both applications. However, a GM segmentation accuracy reduction of 5.6% DC leads to increase of normalized induced electric field up to 6%. Opposite trend of electric field variation was found between CSF and GM for both TMS and tES. The finding obtained here would be useful to quantify potential uncertainty of computational results.

physics.med-ph↗

arXiv2020

Model-based approach for analyzing prevalence of nuclear cataracts in elderly residents

Recent epidemiological studies have hypothesized that the prevalence of cortical cataracts is closely related to ultraviolet radiation. However, the prevalence of nuclear cataracts is higher in elderly people in tropical areas than in temperate areas. The dominant factors inducing nuclear cataracts have been widely debated. In this study, the temperature increase in the lens due to exposure to ambient conditions was computationally quantified in subjects of 50-60 years of age in tropical and temperate areas, accounting for differences in thermoregulation. A thermoregulatory response model was extended to consider elderly people in tropical areas. The time course of lens temperature for different weather conditions in five cities in Asia was computed. The temperature was higher around the mid and posterior part of the lens, which coincides with the position of the nuclear cataract. The duration of higher temperatures in the lens varied, although the daily maximum temperatures were comparable. A strong correlation (adjusted R2 > 0.85) was observed between the prevalence of nuclear cataract and the computed cumulative thermal dose in the lens. We propose the use of a cumulative thermal dose to assess the prevalence of nuclear cataracts. Cumulative wet-bulb globe temperature, a new metric computed from weather data, would be useful for practical assessment in different cities.

physics.med-ph↗

arXiv2020

Correlation between COVID-19 morbidity and mortality rates in Japan and local population density, temperature and absolute humidity

This study analyzed the morbidity and mortality rates of the COVID-19 pandemic in different prefectures of Japan. Under the constraint that daily maximum confirmed deaths and daily maximum cases should exceed 4 and 10, respectively, 14 prefectures were included, and cofactors affecting the morbidity and mortality rates were evaluated. In particular, the number of confirmed deaths was assessed excluding the cases of nosocomial infections and nursing home patients. A mild correlation was observed between morbidity rate and population density (R2=0.394). In addition, the percentage of the elderly per population was also found to be non-negligible. Among weather parameters, the maximum temperature and absolute humidity averaged over the duration were found to be in modest correlation with the morbidity and mortality rates, excluding the cases of nosocomial infections. The lower morbidity and mortality are observed for higher temperature and absolute humidity. Multivariate analysis considering these factors showed that determination coefficients for the spread, decay, and combined stages were 0.708, 0.785, and 0.615, respectively. These findings could be useful for intervention planning during future pandemics, including a potential second COVID-19 outbreak.

q-bio.PE↗

arXiv2020

Influence of Absolute Humidity, Temperature and Population Density on COVID-19 Spread and Decay Durations: Multi-prefecture Study in Japan

This study analyzed the spread and decay durations of the COVID-19 pandemic in different prefectures of Japan. During the pandemic, affordable healthcare was widely available in Japan and the medical system did not suffer a collapse, making accurate comparisons between prefectures possible. For the 16 prefectures included in this study that had daily maximum confirmed cases exceeding ten, the number of daily confirmed cases follow bell-shape or log-normal distribution in most prefectures. A good correlation was observed between the spread and decay durations. However, some exceptions were observed in areas where travelers returned from foreign countries, which were defined as the origins of infection clusters. Excluding these prefectures, the population density was shown to be a major factor affecting the spread and decay patterns, with R2=0.39 (p<0.05) and 0.42 (p<0.05), respectively, approximately corresponding to social distancing. The maximum absolute humidity was found to affect the decay duration normalized by the population density (R2>0.36, p <0.05). Our findings indicate that the estimated pandemic spread duration, based on the multivariate analysis of maximum absolute humidity, ambient temperature, and population density (adjusted R2=0.53, p-value<0.05), could prove useful for intervention planning during potential future pandemics, including a second COVID-19 outbreak.

q-bio.PE↗

arXiv2020

Assessment of absorbed power density and temperature rise for nonplanar body model under electromagnetic exposure above 6 GHz

The averaged absorbed power density (APD) and temperature rise in body models with nonplanar surfaces were computed for electromagnetic exposure above 6 GHz. Different calculation schemes for the averaged APD were investigated. Additionally, a novel compensation method for correcting the heat convection rate on the air/skin interface in voxel human models was proposed and validated. The compensation method can be easily incorporated into bioheat calculations and does not require information regarding the normal direction of the boundary voxels, in contrast to a previously proposed method. The APD and temperature rise were evaluated using models of a two-dimensional cylinder and a three-dimensional partial forearm. The heating factor, which was defined as the ratio of the temperature rise to the APD, was calculated using different APD averaging schemes. Our computational results revealed different frequency and curvature dependences. For body models with curvature radii of >30 mm and at frequencies of >20 GHz, the differences in the heating factors among the APD schemes were small.

physics.comp-ph↗