Skip to main content

Showing 25 publication

SwiftMSeg: lightweight multi-scale local–global context modeling with transformer for medical image segmentation
2026
SwiftMSeg: lightweight multi-scale local–global context modeling with transform…

Jahid Hasan Rony, Md Shakhawat Hossain & Fazlul Hasan Siddiqui

Scientific Reports (Nature)

Accurate medical image segmentation requires both fine boundary localization and robust contextual understanding, which is often difficult to achieve simultaneously, particularly in lightweight architectures. …

LGGC-Net: a local-global graph and color attention-based lightweight CNN for skin cancer classification
2026
LGGC-Net: a local-global graph and color attention-based lightweight CNN for sk…

Md Aminur Sarker, Md Alamgir Kabir, Md Shakhawat Hossain

Scientific Reports (Nature Publishing Group)

Developing clinically deployable AI systems for skin cancer classification remains challenging due to limited robustness, lack of interpretability and constrained computational resources in hospitals. …

SiNuS: A Comprehensive Dataset for Singular Nuclei Segmentation for HER2 Grading of Breast Cancer
2026
SiNuS: A Comprehensive Dataset for Singular Nuclei Segmentation for HER2 Gradin…

Md Shakhawat Hossain, Md Sahilur Rahman, Munim Ahmed

Data in Brief

Singular nuclei are those that are intact and do not overlap with neighboring nuclei. According to the American Society of Clinical Oncology and the …

Bacterial Foraging Optimization-boosted convolutional neural network for brain tumor detection using MRI images
2026
Bacterial Foraging Optimization-boosted convolutional neural network for brain …

Md. Tarequl Islam, Md Wahidur Rahman, Kaniz Roksana, Md Shakhawat Hossain, Mostofa Kamal Nasir, Angel Rio-Álvarez, Víctor M. González

Journal of Computational Science

Accurate brain tumor classification from magnetic resonance imaging (MRI) is essential for early diagnosis and treatment planning; however, existing automated approaches often face challenges related …

From survey to solution: A deep learning framework for reliable monkeypox diagnosis using skin images
2025
From survey to solution: A deep learning framework for reliable monkeypox diagn…

Md Shakhawat Hossain, Munim Ahmed, Md Sahilur Rahman

Array , Vol. 28

Monkeypox, a re-emerging zoonotic disease, poses a global health threat due to its rapid transmission and visual similarity to other skin lesions such as chickenpox, measles and acne. Deep learning methods, which detect monkeypox from skin images, offer a promising solution to overcome the limitations of manual and PCR-based diagnoses, which are time-consuming, error-prone and impractical in low-resource settings. However, existing methods are limited by poor dataset quality, weak generalizability and inconsistent benchmarking. Practical issues, such as lesion variability, image noise, unsuitable augmentations and minimal preprocessing, pose further challenges to clinical deployment. This study addressed these issues through a three-fold contribution: a comprehensive survey of deep learning methods analyzing their strengths and limitations; the development of a diverse, clinically representative benchmark dataset to better assess model generalizability; and a robust deep learning ensemble framework that improved diagnostic accuracy across diverse skin images. The proposed ensemble method incorporated practical classes, a noise-free and balanced dataset, clinically relevant augmentations and effective preprocessing steps, achieving over 95% accuracy across major public datasets to ensure robustness and readiness for clinical deployment. Explainability analysis using Shapley Additive exPlanation (SHAP) confirmed the method’s reliability across all skin tones and body parts. A paired t-test showed that the ensemble model performed significantly better than individual models across four public datasets (𝑝 = 0.005, Cohen’s 𝑑 = 2.38).

Automated Gleason Grading of Prostate Cancer from Low-Resolution Histopathology Images Using an Ensemble Network of CNN and Transformer Models
2025
Automated Gleason Grading of Prostate Cancer from Low-Resolution Histopathology…

Md Shakhawat Hossain, Md Sahilur Rahman, Munim Ahmed, Anowar Hussen, Zahid Ullah, Mona Jamjoom

Computers, Materials & Continua

One in every eight men in the US is diagnosed with prostate cancer, making it the most common cancer in men. Gleason grading is …

Ripen Banana Dataset: A Comprehensive Resource for Carbide Detection and Ripening Stage Analysis to Enhance Food Quality and Agricultural Efficiency
2025
Ripen Banana Dataset: A Comprehensive Resource for Carbide Detection and Ripeni…

Elman Alam, Md Tarequl Islam, Ishrat Zahan Raka, Onamika Sarkar Ritu, Md Shakhawat Hossain, Wahidur Rahman, Rahat Khan

Data in Brief , Vol. 60

We introduce the “Ripen Banana” dataset, a newly developed collection featuring two distinct classes of ripen banana images: carbide and non-carbide. The dataset contains …

A Comprehensive Dataset of Surface Water Quality Spanning 1940-2023 for Empirical and ML Adopted Research
2025
A Comprehensive Dataset of Surface Water Quality Spanning 1940-2023 for Empiric…

Md Rajaul Karim, MM Mahbubul Syeed, Ashifur Rahman, Khondkar Ayaz Rabbani, Kaniz Fatema, Razib Hayat Khan, Md Shakhawat Hossain, Mohammad Faisal Uddin

Scientific Data (Nature) , Vol. 12 (1)

Assessment and monitoring of surface water quality are essential for food security, public health, and ecosystem protection. Although water quality monitoring is a known …

Predicting the effect of Bevacizumab therapy in ovarian cancer from H&E whole slide images using transformer model
2025
Predicting the effect of Bevacizumab therapy in ovarian cancer from H&E whole s…

Md Shakhawat Hossain, Munim Ahmed, Md Sahilur Rahman, MM Mahbubul Syeed, Mohammad Faisal Uddin

Intelligence-Based Medicine , Vol. 11 (100231)

Ovarian cancer (OC) ranks fifth in all cancer-related fatalities in women. Epithelial ovarian cancer (EOC) is a subclass of OC, accounting for 95 % of …

Vision Transformer for the Categorization of Breast Cancer from H&E Histopathology Images
2025
Vision Transformer for the Categorization of Breast Cancer from H&E Histopathol…

Md Shakhawat Hossain, Ashifur Rahman, Munim Ahmed, Kaniz Fatema, MM Mahbubul Syeed, Mohammad Anowar Hussen and Mohammad Faisal Uddin

Journal of Image and Graphics , Vol. 13 (4) , pp. 380-393

Breast Cancer (BC) is the most frequent form of cancer, accounting for 24.5% of all cancer cases worldwide, with projections estimating 364,000 cases by …

Medicinal plant classification using particle swarm optimized cascaded network
2024
Medicinal plant classification using particle swarm optimized cascaded network

Md Tarequl Islam, Wahidur Rahman, Md Shakhawat Hossain, Kaniz Roksana, Irma Domínguez Azpíroz, Raquel Martínez Diaz, Imran Ashraf, Md Abdus Samad

IEEE Access , Vol. 12 , pp. 42465-42478

Medicinal plants are essential to healthcare since ancient times and are integral to developing drugs and other medical treatments. More than 25% of medicines …

Residual Tumor Cellularity Assessment of Breast Cancer after Neoadjuvant Therapy using Image Transformer
2024
Residual Tumor Cellularity Assessment of Breast Cancer after Neoadjuvant Therap…

Md Shakhawat Hossain, Md Sahilur Rahman, Munim Ahmed, Nazia Alfaz, Sirajum Munira Shifat, MM Mahbubul Syeed, Mohammad Anowar Hussen, Mohammad Faisal …

IEEE Access , Vol. 12 , pp. 86083 - 86095

Residual tumor cellularity (RTC) is assessed routinely after neoadjuvant therapy (NAT) for Breast Cancer (BC) patients to determine the effectiveness of therapy and plan …

SwiftMSeg: lightweight multi-scale local–global context modeling with transformer for medical image segmentation
2026

SwiftMSeg: lightweight multi-scale local–global context modeling with transformer for medical image segmentation

Jahid Hasan Rony, Md Shakhawat Hossain & Fazlul Hasan Siddiqui

Scientific Reports (Nature)

Accurate medical image segmentation requires both fine boundary localization and robust contextual understanding, which is often difficult to achieve simultaneously, particularly in lightweight architectures. In this paper, we propose SwiftMSeg, a lightweight encoder–decoder framework that integrates a convolutional encoder, …

LGGC-Net: a local-global graph and color attention-based lightweight CNN for skin cancer classification
2026

LGGC-Net: a local-global graph and color attention-based lightweight CNN for skin cancer classification

Md Aminur Sarker, Md Alamgir Kabir, Md Shakhawat Hossain

Scientific Reports (Nature Publishing Group)

Developing clinically deployable AI systems for skin cancer classification remains challenging due to limited robustness, lack of interpretability and constrained computational resources in hospitals. Although many deep learning models report high accuracy, their large sizes, extensive training requirements and …

SiNuS: A Comprehensive Dataset for Singular Nuclei Segmentation for HER2 Grading of Breast Cancer
2026

SiNuS: A Comprehensive Dataset for Singular Nuclei Segmentation for HER2 Grading of Breast Cancer

Md Shakhawat Hossain, Md Sahilur Rahman, Munim Ahmed

Data in Brief

Singular nuclei are those that are intact and do not overlap with neighboring nuclei. According to the American Society of Clinical Oncology and the College of American Pathologists ASCO/CAP, the human epidermal growth factor receptor 2 (HER2) grading of …

Bacterial Foraging Optimization-boosted convolutional neural network for brain tumor detection using MRI images
2026

Bacterial Foraging Optimization-boosted convolutional neural network for brain tumor detection using MRI images

Md. Tarequl Islam, Md Wahidur Rahman, Kaniz Roksana, Md Shakhawat Hossain, Mostofa Kamal Nasir, Angel Rio-Álvarez, Víctor M. González

Journal of Computational Science

Accurate brain tumor classification from magnetic resonance imaging (MRI) is essential for early diagnosis and treatment planning; however, existing automated approaches often face challenges related to feature redundancy, computational complexity, and limited training data. In this study, we propose a …

From survey to solution: A deep learning framework for reliable monkeypox diagnosis using skin images
2025

From survey to solution: A deep learning framework for reliable monkeypox diagnosis using skin images

Md Shakhawat Hossain, Munim Ahmed, Md Sahilur Rahman

Array , Vol. 28

Monkeypox, a re-emerging zoonotic disease, poses a global health threat due to its rapid transmission and visual similarity to other skin lesions such as chickenpox, measles and acne. Deep learning methods, which detect monkeypox from skin images, offer a promising solution to overcome the limitations of manual and PCR-based diagnoses, which are time-consuming, error-prone and impractical in low-resource settings. However, existing methods are limited by poor dataset quality, weak generalizability and inconsistent benchmarking. Practical issues, such as lesion variability, image noise, unsuitable augmentations and minimal preprocessing, pose further challenges to clinical deployment. This study addressed these issues through a three-fold contribution: a comprehensive survey of deep learning methods analyzing their strengths and limitations; the development of a diverse, clinically representative benchmark dataset to better assess model generalizability; and a robust deep learning ensemble framework that improved diagnostic accuracy across diverse skin images. The proposed ensemble method incorporated practical classes, a noise-free and balanced dataset, clinically relevant augmentations and effective preprocessing steps, achieving over 95% accuracy across major public datasets to ensure robustness and readiness for clinical deployment. Explainability analysis using Shapley Additive exPlanation (SHAP) confirmed the method’s reliability across all skin tones and body parts. A paired t-test showed that the ensemble model performed significantly better than individual models across four public datasets (𝑝 = 0.005, Cohen’s 𝑑 = 2.38).

Automated Gleason Grading of Prostate Cancer from Low-Resolution Histopathology Images Using an Ensemble Network of CNN and Transformer Models
2025

Automated Gleason Grading of Prostate Cancer from Low-Resolution Histopathology Images Using an Ensemble Network of CNN and Transformer Models

Md Shakhawat Hossain, Md Sahilur Rahman, Munim Ahmed, Anowar Hussen, Zahid Ullah, Mona Jamjoom

Computers, Materials & Continua

One in every eight men in the US is diagnosed with prostate cancer, making it the most common cancer in men. Gleason grading is one of the most essential diagnostic and prognostic factors for planning the treatment of prostate …

Ripen Banana Dataset: A Comprehensive Resource for Carbide Detection and Ripening Stage Analysis to Enhance Food Quality and Agricultural Efficiency
2025

Ripen Banana Dataset: A Comprehensive Resource for Carbide Detection and Ripening Stage Analysis to Enhance Food Quality and Agricultural Efficiency

Elman Alam, Md Tarequl Islam, Ishrat Zahan Raka, Onamika Sarkar Ritu, Md Shakhawat Hossain, Wahidur Rahman, Rahat Khan

Data in Brief , Vol. 60

We introduce the “Ripen Banana” dataset, a newly developed collection featuring two distinct classes of ripen banana images: carbide and non-carbide. The dataset contains images from raw to ripe bananas that have been ripened with carbide and without carbide. …

A Comprehensive Dataset of Surface Water Quality Spanning 1940-2023 for Empirical and ML Adopted Research
2025

A Comprehensive Dataset of Surface Water Quality Spanning 1940-2023 for Empirical and ML Adopted Research

Md Rajaul Karim, MM Mahbubul Syeed, Ashifur Rahman, Khondkar Ayaz Rabbani, Kaniz Fatema, Razib Hayat Khan, Md Shakhawat Hossain, Mohammad Faisal Uddin

Scientific Data (Nature) , Vol. 12 (1)

Assessment and monitoring of surface water quality are essential for food security, public health, and ecosystem protection. Although water quality monitoring is a known phenomenon, little effort has been made to offer a comprehensive and harmonized dataset for surface …

Predicting the effect of Bevacizumab therapy in ovarian cancer from H&E whole slide images using transformer model
2025

Predicting the effect of Bevacizumab therapy in ovarian cancer from H&E whole slide images using transformer model

Md Shakhawat Hossain, Munim Ahmed, Md Sahilur Rahman, MM Mahbubul Syeed, Mohammad Faisal Uddin

Intelligence-Based Medicine , Vol. 11 (100231)

Ovarian cancer (OC) ranks fifth in all cancer-related fatalities in women. Epithelial ovarian cancer (EOC) is a subclass of OC, accounting for 95 % of all patients. Conventional treatment for EOC is debulking surgery with adjuvant Chemotherapy; however, in 70 % …

Vision Transformer for the Categorization of Breast Cancer from H&E Histopathology Images
2025

Vision Transformer for the Categorization of Breast Cancer from H&E Histopathology Images

Md Shakhawat Hossain, Ashifur Rahman, Munim Ahmed, Kaniz Fatema, MM Mahbubul Syeed, Mohammad Anowar Hussen and Mohammad Faisal Uddin

Journal of Image and Graphics , Vol. 13 (4) , pp. 380-393

Breast Cancer (BC) is the most frequent form of cancer, accounting for 24.5% of all cancer cases worldwide, with projections estimating 364,000 cases by 2040. Accurate diagnosis and effective categorization of BC are essential for proper treatment planning, patient …

Medicinal plant classification using particle swarm optimized cascaded network
2024

Medicinal plant classification using particle swarm optimized cascaded network

Md Tarequl Islam, Wahidur Rahman, Md Shakhawat Hossain, Kaniz Roksana, Irma Domínguez Azpíroz, Raquel Martínez Diaz, Imran Ashraf, Md Abdus Samad

IEEE Access , Vol. 12 , pp. 42465-42478

Medicinal plants are essential to healthcare since ancient times and are integral to developing drugs and other medical treatments. More than 25% of medicines in developed countries are produced from medicinal plants, while in developing countries, approximately 80% of …

Residual Tumor Cellularity Assessment of Breast Cancer after Neoadjuvant Therapy using Image Transformer
2024

Residual Tumor Cellularity Assessment of Breast Cancer after Neoadjuvant Therapy using Image Transformer

Md Shakhawat Hossain, Md Sahilur Rahman, Munim Ahmed, Nazia Alfaz, Sirajum Munira Shifat, MM Mahbubul Syeed, Mohammad Anowar Hussen, Mohammad Faisal Uddin

IEEE Access , Vol. 12 , pp. 86083 - 86095

Residual tumor cellularity (RTC) is assessed routinely after neoadjuvant therapy (NAT) for Breast Cancer (BC) patients to determine the effectiveness of therapy and plan the treatment. RTC is also considered a prognostic biomarker associated with metastatic recurrence and survival …