Rusab Sarmun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rusab Sarmun has a total of 59 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Enamul Hoque Chowdhury
Department of Electrical Engineering, Qatar University, Doha P.O. Box 2713, Qatar
11 shared publications Muhammad E.H. Chowdhury
4 shared publications- Adam Mushtak
Department of Radiology, Hamad Medical Corporation, Doha, Qatar
3 shared publications Israa Al-Hashimi
3 shared publications- Saidul Kabir
Department of Electrical and Electronic Engineering, University of Dhaka, Dhaka, 1000, Bangladesh
3 shared publications - Abdulrahman Alqahtani
Department of Biomedical Technology, College of Applied Medical Sciences in Al-Kharj, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia
2 shared publications
Latest Publications
- Open Access
- 25 August 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 129
A novel detection-guided approach for multimodal brain tumor segmentation
- 25 August 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 129
Open AccessA novel detection-guided approach for multimodal brain tumor segmentation
- Top Cited PapersOpen Access
- 15 June 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38  (12) , 493
A comprehensive review of U-Net architectures for medical image segmentation: emerging trends and federated learning perspectives
U-Net has become a fundamental method in medical image segmentation with its architecture evolving to tackle complex segmentation tasks across modalities such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT) scans and microscopic images. This review offers a comprehensive analysis of various U-Net architectures including U-Net++, Residual U-Net, Dense U-Net and more recent transformer-based models like TransUNet and Swin-UNet. These architectures introduce optimizations like improved feature propagation, gradient flow and self-attention mechanisms, significantly enhancing segmentation accuracy. Despite its widespread success, U-Net faces limitations in handling data imbalance, computational complexity and challenges with multi-modal and large-scale data. The integration of federated learning with U-Net addresses privacy concerns by enabling secure, collaborative model training across healthcare institutions while maintaining data confidentiality. This review also highlights the applications of U-Net variants in key medical imaging tasks, including brain segmentation, retinal vessel segmentation, cell and nuclei segmentation, prostate segmentation and skin lesion segmentation, which play a critical role in early disease detection and treatment planning. In addition to exploring these applications, the paper examines benchmark datasets, loss functions and evaluation metrics essential for assessing U-Net architectures. The review also discusses emerging trends like self-supervised learning, lightweight models for resource-constrained environments and interpretability techniques, offering potential directions for future research. By presenting both the advancements and limitations of U-Net, this review provides valuable insights into how these models can be optimized and applied to real-world medical applications.
- 15 June 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38  (12) , 493
Top Cited PapersOpen AccessA comprehensive review of U-Net architectures for medical image segmentation: emerging trends and federated learning perspectives
U-Net has become a fundamental method in medical image segmentation with its architecture evolving to tackle complex segmentation tasks across modalities such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT) scans and microscopic images. This review offers a comprehensive analysis of various U-Net architectures including U-Net++, Residual U-Net, Dense U-Net and more recent transformer-based models like TransUNet and Swin-UNet. These architectures introduce optimizations like improved feature propagation, gradient flow and self-attention mechanisms, significantly enhancing segmentation accuracy. Despite its widespread success, U-Net faces limitations in handling data imbalance, computational complexity and challenges with multi-modal and large-scale data. The integration of federated learning with U-Net addresses privacy concerns by enabling secure, collaborative model training across healthcare institutions while maintaining data confidentiality. This review also highlights the applications of U-Net variants in key medical imaging tasks, including brain segmentation, retinal vessel segmentation, cell and nuclei segmentation, prostate segmentation and skin lesion segmentation, which play a critical role in early disease detection and treatment planning. In addition to exploring these applications, the paper examines benchmark datasets, loss functions and evaluation metrics essential for assessing U-Net architectures. The review also discusses emerging trends like self-supervised learning, lightweight models for resource-constrained environments and interpretability techniques, offering potential directions for future research. By presenting both the advancements and limitations of U-Net, this review provides valuable insights into how these models can be optimized and applied to real-world medical applications.
- 28 March 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 175
Point cloud-based three-dimensional segmentation of teeth from Cone Beam Computed Tomography images
- 28 March 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 175
Point cloud-based three-dimensional segmentation of teeth from Cone Beam Computed Tomography images
- Top Cited PapersOpen Access
- 18 February 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38  (4) , 56
A comprehensive review of convolutional neural networks: foundations, enhancements and applications
Convolutional Neural Networks (CNNs) have emerged as a cornerstone in the field of deep learning, demonstrating remarkable performance across various domains, including computer vision and natural language processing. Their widespread acceptance on both academic and industrial levels has spurred much research and development. This study provides a comprehensive overview of recent developments in convolutional neural network (CNN) architectures by analyzing their foundational concepts, structural enhancements, and various applications such as image classification, medical imaging, and autonomous systems. Starting with conventional CNN architectures and their fundamental elements, the paper uses a systematic approach to look into recent advances. Key architectural innovations, including advanced activation functions, novel pooling strategies, and optimized convolutional techniques, are discussed. The study also explores hybrid architectures that integrate CNNs with transformers and recurrent neural networks to enhance contextual and sequential learning. Advances in training processes, such as enhanced loss functions and regularization approaches, have been studied for enhancing model performance. The study highlights CNN advancements that improve accuracy, reduce computational costs, and enhance model generalization. It underscores the effectiveness of CNNs in critical domains. Findings reveal that improved feature extraction techniques and interpretability methods, including Gradient-weighted Class Activation Mapping (Grad-CAM) and Graph-CNNs, contribute significantly to CNN performance. Finally, the paper identifies open challenges and outlines potential research directions, providing insights into the future development of CNNs.
- 18 February 2026
- Published by Springer Nature in Neural Computing and Applications
- Vol. 38  (4) , 56
Top Cited PapersOpen AccessA comprehensive review of convolutional neural networks: foundations, enhancements and applications
Convolutional Neural Networks (CNNs) have emerged as a cornerstone in the field of deep learning, demonstrating remarkable performance across various domains, including computer vision and natural language processing. Their widespread acceptance on both academic and industrial levels has spurred much research and development. This study provides a comprehensive overview of recent developments in convolutional neural network (CNN) architectures by analyzing their foundational concepts, structural enhancements, and various applications such as image classification, medical imaging, and autonomous systems. Starting with conventional CNN architectures and their fundamental elements, the paper uses a systematic approach to look into recent advances. Key architectural innovations, including advanced activation functions, novel pooling strategies, and optimized convolutional techniques, are discussed. The study also explores hybrid architectures that integrate CNNs with transformers and recurrent neural networks to enhance contextual and sequential learning. Advances in training processes, such as enhanced loss functions and regularization approaches, have been studied for enhancing model performance. The study highlights CNN advancements that improve accuracy, reduce computational costs, and enhance model generalization. It underscores the effectiveness of CNNs in critical domains. Findings reveal that improved feature extraction techniques and interpretability methods, including Gradient-weighted Class Activation Mapping (Grad-CAM) and Graph-CNNs, contribute significantly to CNN performance. Finally, the paper identifies open challenges and outlines potential research directions, providing insights into the future development of CNNs.
- Open Access
- 31 August 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 112
Self-DenseMobileNet: A robust framework for lung nodule classification using Self-ONN and stacking-based meta-classifier
- 31 August 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 112
Open AccessSelf-DenseMobileNet: A robust framework for lung nodule classification using Self-ONN and stacking-based meta-classifier
- Open Access
- 1 July 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 195
SER inspired deep learning approach to detect cardiac arrhythmias in electrocardiogram signals using Temporal Convolutional Network and graph neural network
- 1 July 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 195
Open AccessSER inspired deep learning approach to detect cardiac arrhythmias in electrocardiogram signals using Temporal Convolutional Network and graph neural network
- Open Access
- 3 March 2025
- Published by Association of Basic Medical Sciences of FBIH in Biomolecules and Biomedicine
- Vol. 26  (1) , 79-90
A novel deep learning framework for automatic scoring of PD-L1 expression in non-small cell lung cancer
A critical predictive marker for anti-PD-1/PD-L1 therapy is programmed death-ligand 1 (PD-L1) expression, assessed by immunohistochemistry (IHC). This paper explores a novel automated framework using deep learning to accurately evaluate PD-L1 expression from whole slide images (WSIs) of non-small cell lung cancer (NSCLC), aiming to improve the precision and consistency of Tumor Proportion Score (TPS) evaluation, which is essential for determining patient eligibility for immunotherapy. Automating TPS evaluation can enhance accuracy and consistency while reducing pathologists' workload. The proposed automated framework encompasses three stages: identifying tumor patches, segmenting tumor areas, and detecting cell nuclei within these areas, followed by estimating the TPS based on the ratio of positively stained to total viable tumor cells. This study utilized a Reference Medicine (Phoenix, Arizona) dataset containing 66 NSCLC tissue samples, adopting a hybrid human-machine approach for annotating extensive WSIs. Patches of size 1000x1000 pixels were generated to train classification models such as EfficientNet, Inception, and Vision Transformer models. Additionally, segmentation performance was evaluated across various UNet and DeepLabV3 architectures, and the pre-trained StarDist model was employed for nuclei detection, replacing traditional watershed techniques. PD-L1 expression was categorized into three levels based on TPS: negative expression (TPS < 1%), low expression (TPS 1-49%), and high expression (TPS ≥ 50%). The Vision Transformer-based model excelled in classification, achieving an F1-score of 97.54%, while the modified DeepLabV3+ model led in segmentation, attaining a Dice Similarity Coefficient of 83.47%. The TPS predicted by the framework closely correlated with the pathologist's TPS at 0.9635, and the framework's three-level classification F1-score was 93.89%. The proposed deep learning framework for automatically evaluating the TPS of PD-L1 expression in NSCLC demonstrated promising performance. This framework presents a potential tool that could produce clinically significant results more efficiently and cost-effectively.
- 3 March 2025
- Published by Association of Basic Medical Sciences of FBIH in Biomolecules and Biomedicine
- Vol. 26  (1) , 79-90
Open AccessA novel deep learning framework for automatic scoring of PD-L1 expression in non-small cell lung cancer
A critical predictive marker for anti-PD-1/PD-L1 therapy is programmed death-ligand 1 (PD-L1) expression, assessed by immunohistochemistry (IHC). This paper explores a novel automated framework using deep learning to accurately evaluate PD-L1 expression from whole slide images (WSIs) of non-small cell lung cancer (NSCLC), aiming to improve the precision and consistency of Tumor Proportion Score (TPS) evaluation, which is essential for determining patient eligibility for immunotherapy. Automating TPS evaluation can enhance accuracy and consistency while reducing pathologists' workload. The proposed automated framework encompasses three stages: identifying tumor patches, segmenting tumor areas, and detecting cell nuclei within these areas, followed by estimating the TPS based on the ratio of positively stained to total viable tumor cells. This study utilized a Reference Medicine (Phoenix, Arizona) dataset containing 66 NSCLC tissue samples, adopting a hybrid human-machine approach for annotating extensive WSIs. Patches of size 1000x1000 pixels were generated to train classification models such as EfficientNet, Inception, and Vision Transformer models. Additionally, segmentation performance was evaluated across various UNet and DeepLabV3 architectures, and the pre-trained StarDist model was employed for nuclei detection, replacing traditional watershed techniques. PD-L1 expression was categorized into three levels based on TPS: negative expression (TPS < 1%), low expression (TPS 1-49%), and high expression (TPS ≥ 50%). The Vision Transformer-based model excelled in classification, achieving an F1-score of 97.54%, while the modified DeepLabV3+ model led in segmentation, attaining a Dice Similarity Coefficient of 83.47%. The TPS predicted by the framework closely correlated with the pathologist's TPS at 0.9635, and the framework's three-level classification F1-score was 93.89%. The proposed deep learning framework for automatically evaluating the TPS of PD-L1 expression in NSCLC demonstrated promising performance. This framework presents a potential tool that could produce clinically significant results more efficiently and cost-effectively.
- Open Access
- 15 February 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 105
Deep learning-driven segmentation of ischemic stroke lesions using multi-channel MRI
- 15 February 2025
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 105
Open AccessDeep learning-driven segmentation of ischemic stroke lesions using multi-channel MRI
- Open Access
Machine-agnostic Automated Lumbar MRI Segmentation using a Cascaded Model Based on Generative Neurons
Automated lumbar spine segmentation is very crucial for modern diagnosis systems. In this study, we introduce a novel machine-agnostic approach for segmenting lumbar vertebrae and intervertebral discs from MRI images, employing a cascaded model that synergizes an ROI detection and a Self-organized Operational Neural Network (Self-ONN)-based encoder-decoder network for segmentation. Addressing the challenge of diverse MRI modalities, our methodology capitalizes on a unique dataset comprising images from 12 scanners and 34 subjects, enhanced through strategic preprocessing and data augmentation techniques. The YOLOv8 medium model excels in ROI extraction, achieving an excellent performance of 0.916 mAP score. Significantly, our Self-ONN-based model, combined with a DenseNet121 encoder, demonstrates excellent performance in lumbar vertebrae and IVD segmentation with a mean Intersection over Union (IoU) of 83.66%, a sensitivity of 91.44%, and Dice Similarity Coefficient (DSC) of 91.03%, as validated through rigorous 10-fold cross-validation. This study not only showcases an effective approach to MRI segmentation in spine-related disorders but also sets the stage for future advancements in automated diagnostic tools, emphasizing the need for further dataset expansion and model refinement for broader clinical applicability.
Open AccessMachine-agnostic Automated Lumbar MRI Segmentation using a Cascaded Model Based on Generative Neurons
Automated lumbar spine segmentation is very crucial for modern diagnosis systems. In this study, we introduce a novel machine-agnostic approach for segmenting lumbar vertebrae and intervertebral discs from MRI images, employing a cascaded model that synergizes an ROI detection and a Self-organized Operational Neural Network (Self-ONN)-based encoder-decoder network for segmentation. Addressing the challenge of diverse MRI modalities, our methodology capitalizes on a unique dataset comprising images from 12 scanners and 34 subjects, enhanced through strategic preprocessing and data augmentation techniques. The YOLOv8 medium model excels in ROI extraction, achieving an excellent performance of 0.916 mAP score. Significantly, our Self-ONN-based model, combined with a DenseNet121 encoder, demonstrates excellent performance in lumbar vertebrae and IVD segmentation with a mean Intersection over Union (IoU) of 83.66%, a sensitivity of 91.44%, and Dice Similarity Coefficient (DSC) of 91.03%, as validated through rigorous 10-fold cross-validation. This study not only showcases an effective approach to MRI segmentation in spine-related disorders but also sets the stage for future advancements in automated diagnostic tools, emphasizing the need for further dataset expansion and model refinement for broader clinical applicability.
- Open Access
Self-DenseMobileNet: A Robust Framework for Lung Nodule Classification using Self-ONN and Stacking-based Meta-Classifier
In this study, we propose a novel and robust framework, Self-DenseMobileNet, designed to enhance the classification of nodules and non-nodules in chest radiographs (CXRs). Our approach integrates advanced image standardization and enhancement techniques to optimize the input quality, thereby improving classification accuracy. To enhance predictive accuracy and leverage the strengths of multiple models, the prediction probabilities from Self-DenseMobileNet were transformed into tabular data and used to train eight classical machine learning (ML) models; the top three performers were then combined via a stacking algorithm, creating a robust meta-classifier that integrates their collective insights for superior classification performance. To enhance the interpretability of our results, we employed class activation mapping (CAM) to visualize the decision-making process of the best-performing model. Our proposed framework demonstrated remarkable performance on internal validation data, achieving an accuracy of 99.28\% using a Meta-Random Forest Classifier. When tested on an external dataset, the framework maintained strong generalizability with an accuracy of 89.40\%. These results highlight a significant improvement in the classification of CXRs with lung nodules.
Open AccessSelf-DenseMobileNet: A Robust Framework for Lung Nodule Classification using Self-ONN and Stacking-based Meta-Classifier
In this study, we propose a novel and robust framework, Self-DenseMobileNet, designed to enhance the classification of nodules and non-nodules in chest radiographs (CXRs). Our approach integrates advanced image standardization and enhancement techniques to optimize the input quality, thereby improving classification accuracy. To enhance predictive accuracy and leverage the strengths of multiple models, the prediction probabilities from Self-DenseMobileNet were transformed into tabular data and used to train eight classical machine learning (ML) models; the top three performers were then combined via a stacking algorithm, creating a robust meta-classifier that integrates their collective insights for superior classification performance. To enhance the interpretability of our results, we employed class activation mapping (CAM) to visualize the decision-making process of the best-performing model. Our proposed framework demonstrated remarkable performance on internal validation data, achieving an accuracy of 99.28\% using a Meta-Random Forest Classifier. When tested on an external dataset, the framework maintained strong generalizability with an accuracy of 89.40\%. These results highlight a significant improvement in the classification of CXRs with lung nodules.