2025
9.
Rahman, Md Mostafijur; Marculescu, Radu
LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation Conference Forthcoming
Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2025), Forthcoming.
BibTeX | Tags: Deep Learning, Logit Mixing, Medical Image Segmentation, Medical Imaging, Supervision
@conference{lomix@rahman,
title = {LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation},
author = {Md Mostafijur Rahman and Radu Marculescu},
year = {2025},
date = {2025-12-03},
urldate = {2025-09-03},
publisher = {Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2025)},
keywords = {Deep Learning, Logit Mixing, Medical Image Segmentation, Medical Imaging, Supervision},
pubstate = {forthcoming},
tppubtype = {conference}
}
8.
Rahman, Md Mostafijur; Marculescu, Radu
MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation Conference
Proceedings of the International Conference on Computer Vision (ICCV) Workshops, 2025.
Abstract | Links | BibTeX | Tags: Efficient AI, Lightweight Architecture, Medical Image Segmentation, Multi-kernel Convolutions
@conference{mkunet@rahman,
title = {MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation},
author = {Md Mostafijur Rahman and Radu Marculescu},
url = {https://openaccess.thecvf.com/content/ICCV2025W/CVAMD/html/Rahman_MK-UNet_Multi-kernel_Lightweight_CNN_for_Medical_Image_Segmentation_ICCVW_2025_paper.html},
year = {2025},
date = {2025-10-19},
urldate = {2025-10-19},
publisher = {Proceedings of the International Conference on Computer Vision (ICCV) Workshops},
abstract = {In this paper, we introduce MK-UNet, a paradigm shift towards ultra-lightweight, multi-kernel U-shaped CNNs tailored for medical image segmentation. Central to MK-UNet is the multi-kernel depth-wise convolution block (MKDC) we design to adeptly process images through multiple kernels, while capturing complex multi-resolution spatial relationships. MK-UNet also emphasizes the images salient features through sophisticated attention mechanisms, including channel, spatial, and grouped gated attention. Our MK-UNet network, with a modest computational footprint of only 0.316 M parameters and 0.314 G FLOPs, represents not only a remarkably lightweight, but also significantly improved segmentation solution that provides higher accuracy over state-of-the-art (SOTA) methods across six binary medical imaging benchmarks. Specifically, MK-UNet outperforms TransUNet in DICE score with nearly 333x and 123x fewer parameters and FLOPs, respectively. Similarly, when compared against UNeXt, MK-UNet exhibits superior segmentation performance, improving the DICE score up to 6.7% margins while operating with 4.7 x fewer# Params. Our MK-UNet also outperforms other recent lightweight networks, such as MedT, CMUNeXt, EGE-UNet, and Rolling-UNet, with much lower computational resources. This leap in performance, coupled with drastic computational gains, positions MK-UNet as an unparalleled solution for real-time, high-fidelity medical diagnostics in resource-limited settings, such as point-of-care devices. Our implementation is available at https://github. com/SLDGroup/MK-UNet.},
keywords = {Efficient AI, Lightweight Architecture, Medical Image Segmentation, Multi-kernel Convolutions},
pubstate = {published},
tppubtype = {conference}
}
In this paper, we introduce MK-UNet, a paradigm shift towards ultra-lightweight, multi-kernel U-shaped CNNs tailored for medical image segmentation. Central to MK-UNet is the multi-kernel depth-wise convolution block (MKDC) we design to adeptly process images through multiple kernels, while capturing complex multi-resolution spatial relationships. MK-UNet also emphasizes the images salient features through sophisticated attention mechanisms, including channel, spatial, and grouped gated attention. Our MK-UNet network, with a modest computational footprint of only 0.316 M parameters and 0.314 G FLOPs, represents not only a remarkably lightweight, but also significantly improved segmentation solution that provides higher accuracy over state-of-the-art (SOTA) methods across six binary medical imaging benchmarks. Specifically, MK-UNet outperforms TransUNet in DICE score with nearly 333x and 123x fewer parameters and FLOPs, respectively. Similarly, when compared against UNeXt, MK-UNet exhibits superior segmentation performance, improving the DICE score up to 6.7% margins while operating with 4.7 x fewer# Params. Our MK-UNet also outperforms other recent lightweight networks, such as MedT, CMUNeXt, EGE-UNet, and Rolling-UNet, with much lower computational resources. This leap in performance, coupled with drastic computational gains, positions MK-UNet as an unparalleled solution for real-time, high-fidelity medical diagnostics in resource-limited settings, such as point-of-care devices. Our implementation is available at https://github. com/SLDGroup/MK-UNet.
7.
Rahman, Md Mostafijur; Munir, Mustafa; Marculescu, Radu
EfficientMedNeXt: Multi-Receptive Dilated Convolutions for Medical Image Segmentation Conference
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025.
Abstract | Links | BibTeX | Tags: 3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Inference, Featured, Medical Image Segmentation
@conference{efficientmednext@rahman,
title = {EfficientMedNeXt: Multi-Receptive Dilated Convolutions for Medical Image Segmentation},
author = {Md Mostafijur Rahman and Mustafa Munir and Radu Marculescu},
url = {https://link.springer.com/chapter/10.1007/978-3-032-04965-0_19},
year = {2025},
date = {2025-09-23},
urldate = {2025-09-23},
publisher = {International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
abstract = {In this work, we introduce EfficientMedNeXt\textemdasha lightweight, high-performance segmentation architecture developed through a two-phase optimization process applied to the MedNeXt architecture. To this end, we first optimize the decoder by reducing the high-resolution redundancy and unifying the decoder channels across stages for enhanced efficiency. Then, we introduce a new Dilated Multi-Receptive Field Block (DMRFB) to capture the multi-scale spatial context efficiently without increasing the kernel sizes and relying on the channel expansion convolutions. Extensive evaluations on BTCV, FeTA, and MSD show that EfficientMedNeXt-L achieves 87.0% DICE score on BTCV (+1.04% over MedNeXt-L) with 96.5% fewer parameters and 77.03% lower FLOPs. In addition, EfficientMedNeXt-S offers comparable DICE score, improved HD95, and 78.1% higher throughput while reducing parameters by 98.5% and FLOPs by 95%. These results demonstrate EfficientMedNeXt’s efficiency and accuracy, making it well-suited for real-world clinical applications. Code will be released upon acceptance.},
keywords = {3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Inference, Featured, Medical Image Segmentation},
pubstate = {published},
tppubtype = {conference}
}
In this work, we introduce EfficientMedNeXt—a lightweight, high-performance segmentation architecture developed through a two-phase optimization process applied to the MedNeXt architecture. To this end, we first optimize the decoder by reducing the high-resolution redundancy and unifying the decoder channels across stages for enhanced efficiency. Then, we introduce a new Dilated Multi-Receptive Field Block (DMRFB) to capture the multi-scale spatial context efficiently without increasing the kernel sizes and relying on the channel expansion convolutions. Extensive evaluations on BTCV, FeTA, and MSD show that EfficientMedNeXt-L achieves 87.0% DICE score on BTCV (+1.04% over MedNeXt-L) with 96.5% fewer parameters and 77.03% lower FLOPs. In addition, EfficientMedNeXt-S offers comparable DICE score, improved HD95, and 78.1% higher throughput while reducing parameters by 98.5% and FLOPs by 95%. These results demonstrate EfficientMedNeXt’s efficiency and accuracy, making it well-suited for real-world clinical applications. Code will be released upon acceptance.
6.
Rahman, Md Mostafijur; Marculescu, Radu
Training-Free Dataset Pruning for Polyp Segmentation via Community Detection in Similarity Networks Conference
Medical Imaging with Deep Learning (MIDL) , 2025.
Abstract | Links | BibTeX | Tags: Community Detection, Dataset Pruning, Featured, Medical Image Segmentation, Polyp segmentation, Training-free
@conference{prime@rahman,
title = {Training-Free Dataset Pruning for Polyp Segmentation via Community Detection in Similarity Networks},
author = {Md Mostafijur Rahman and Radu Marculescu},
url = {https://openreview.net/pdf?id=VQX4B2A2Y0},
year = {2025},
date = {2025-07-09},
urldate = {2025-07-09},
publisher = {Medical Imaging with Deep Learning (MIDL) },
abstract = {Recent advances in deep learning have been driven by the availability of larger datasets and more complex models; however, this progress comes at the expense of substantial computational and annotation costs. To address these issues, we introduce a novel, training-free dataset pruning method,PRIME, targeting polyp segmentation in medical imaging. To this end, PRIME constructs a similarity network among the images in the target dataset and then applies community detection to retain a much smaller, yet representative subset of images from the original dataset. Unlike existing methods that require model training for dataset pruning, our PRIME completely avoids model training, thus significantly reducing computational demands. The reduction in the training dataset cuts 56.2% data annotation costs and enables 2.3× faster training of polyp segmentation models, with only a 0.5% drop in the DICE score. Consequently, our PRIME enables efficient training, fine-tuning, and domain adaptation across medical centers, thus offering a cost-effective solution for deep learning in polyp segmentation.},
keywords = {Community Detection, Dataset Pruning, Featured, Medical Image Segmentation, Polyp segmentation, Training-free},
pubstate = {published},
tppubtype = {conference}
}
Recent advances in deep learning have been driven by the availability of larger datasets and more complex models; however, this progress comes at the expense of substantial computational and annotation costs. To address these issues, we introduce a novel, training-free dataset pruning method,PRIME, targeting polyp segmentation in medical imaging. To this end, PRIME constructs a similarity network among the images in the target dataset and then applies community detection to retain a much smaller, yet representative subset of images from the original dataset. Unlike existing methods that require model training for dataset pruning, our PRIME completely avoids model training, thus significantly reducing computational demands. The reduction in the training dataset cuts 56.2% data annotation costs and enables 2.3× faster training of polyp segmentation models, with only a 0.5% drop in the DICE score. Consequently, our PRIME enables efficient training, fine-tuning, and domain adaptation across medical centers, thus offering a cost-effective solution for deep learning in polyp segmentation.
5.
Rahman, Md Mostafijur; Marculescu, Radu
EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation Conference
Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2025.
Abstract | Links | BibTeX | Tags: 3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Decoder, Featured, Medical Image Segmentation
@conference{effidec3d@rahman,
title = {EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation},
author = {Md Mostafijur Rahman and Radu Marculescu},
url = {https://openaccess.thecvf.com/content/CVPR2025/html/Rahman_EffiDec3D_An_Optimized_Decoder_for_High-Performance_and_Efficient_3D_Medical_CVPR_2025_paper.html},
year = {2025},
date = {2025-06-10},
urldate = {2025-06-10},
publisher = {Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)},
abstract = {Recent 3D deep networks such as SwinUNETR, SwinUNETRv2, and 3D UX-Net have shown promising performance by leveraging self-attention and large-kernel convolutions to capture the volumetric context. However, their substantial computational requirements limit their use in real-time and resource-constrained environments. The high #FLOPs and #Params in these networks stem largely from complex decoder designs with high-resolution layers and
excessive channel counts. In this paper, we propose EffiDec3D, an optimized 3D decoder that employs a channel reduction strategy across all decoder stages, which sets the number of channels to the minimum needed for accurate feature representation. Additionally, EffiDec3D removes the high-resolution layers when their contribution
to segmentation quality is minimal. Our optimized EffiDec3D decoder achieves a 96.4% reduction in #Params and a 93.0% reduction in #FLOPs compared to the decoder of original 3D UX-Net. Similarly, for SwinUNETR and SwinUNETRv2 (which share an identical decoder), we observe reductions of 94.9% in #Params and 86.2% in #FLOPs. Our extensive experiments on 12 different medical imaging tasks confirm that EffiDec3D not only significantly reduces the computational demands, but also maintains a performance level comparable to original models, thus establishing a new standard for efficient 3D medical image segmentation. Our implementation is available at https://github.com/SLDGroup/EffiDec3D.},
keywords = {3D Segmentation, Deep Learning Architecture, Efficient AI, Efficient Decoder, Featured, Medical Image Segmentation},
pubstate = {published},
tppubtype = {conference}
}
Recent 3D deep networks such as SwinUNETR, SwinUNETRv2, and 3D UX-Net have shown promising performance by leveraging self-attention and large-kernel convolutions to capture the volumetric context. However, their substantial computational requirements limit their use in real-time and resource-constrained environments. The high #FLOPs and #Params in these networks stem largely from complex decoder designs with high-resolution layers and
excessive channel counts. In this paper, we propose EffiDec3D, an optimized 3D decoder that employs a channel reduction strategy across all decoder stages, which sets the number of channels to the minimum needed for accurate feature representation. Additionally, EffiDec3D removes the high-resolution layers when their contribution
to segmentation quality is minimal. Our optimized EffiDec3D decoder achieves a 96.4% reduction in #Params and a 93.0% reduction in #FLOPs compared to the decoder of original 3D UX-Net. Similarly, for SwinUNETR and SwinUNETRv2 (which share an identical decoder), we observe reductions of 94.9% in #Params and 86.2% in #FLOPs. Our extensive experiments on 12 different medical imaging tasks confirm that EffiDec3D not only significantly reduces the computational demands, but also maintains a performance level comparable to original models, thus establishing a new standard for efficient 3D medical image segmentation. Our implementation is available at https://github.com/SLDGroup/EffiDec3D.
excessive channel counts. In this paper, we propose EffiDec3D, an optimized 3D decoder that employs a channel reduction strategy across all decoder stages, which sets the number of channels to the minimum needed for accurate feature representation. Additionally, EffiDec3D removes the high-resolution layers when their contribution
to segmentation quality is minimal. Our optimized EffiDec3D decoder achieves a 96.4% reduction in #Params and a 93.0% reduction in #FLOPs compared to the decoder of original 3D UX-Net. Similarly, for SwinUNETR and SwinUNETRv2 (which share an identical decoder), we observe reductions of 94.9% in #Params and 86.2% in #FLOPs. Our extensive experiments on 12 different medical imaging tasks confirm that EffiDec3D not only significantly reduces the computational demands, but also maintains a performance level comparable to original models, thus establishing a new standard for efficient 3D medical image segmentation. Our implementation is available at https://github.com/SLDGroup/EffiDec3D.
2024
4.
Rahman, Md Mostafijur; Munir, Mustafa; Marculescu, Radu
EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation Conference
Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024.
Abstract | Links | BibTeX | Tags: Deep Learning Architecture, Efficient Decoder, Medical Image Segmentation, Multi-scale Depth-wise Convolutions, Vision Transformer
@conference{EMCAD_CVPR_2024,
title = {EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation},
author = {Md Mostafijur Rahman and Mustafa Munir and Radu Marculescu },
url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Rahman_EMCAD_Efficient_Multi-scale_Convolutional_Attention_Decoding_for_Medical_Image_Segmentation_CVPR_2024_paper.pdf},
year = {2024},
date = {2024-06-17},
urldate = {2024-06-17},
publisher = {Proceedings of the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR)},
abstract = {An efficient and effective decoding mechanism is crucial in medical image segmentation, especially in scenarios with limited computational resources. However, these decoding mechanisms usually come with high computational costs. To address this concern, we introduce EMCAD, a new efficient multi-scale convolutional attention decoder, designed to optimize both performance and computational efficiency. EMCAD leverages a unique multi-scale depth-wise convolution block, significantly enhancing feature maps through multi-scale convolutions. EMCAD also employs channel, spatial, and grouped (large-kernel) gated attention mechanisms, which are highly effective at capturing intricate spatial relationships while focusing on salient regions. By employing group and depth-wise convolution, EMCAD is very efficient and scales well (e.g., only 1.91M parameters and 0.381G FLOPs are needed when using a standard encoder). Our rigorous evaluations across 12 datasets that belong to six medical image segmentation tasks reveal that EMCAD achieves state-of-the-art (SOTA) performance with 79.4% and 80.3% reduction in #Params and #FLOPs, respectively. Moreover, EMCAD’s adaptability to different encoders and versatility across segmentation tasks further establish EMCAD as a promising tool, advancing the field towards more efficient and accurate medical image analysis. Our implementation is available at https://github.com/SLDGroup/EMCAD.},
keywords = {Deep Learning Architecture, Efficient Decoder, Medical Image Segmentation, Multi-scale Depth-wise Convolutions, Vision Transformer},
pubstate = {published},
tppubtype = {conference}
}
An efficient and effective decoding mechanism is crucial in medical image segmentation, especially in scenarios with limited computational resources. However, these decoding mechanisms usually come with high computational costs. To address this concern, we introduce EMCAD, a new efficient multi-scale convolutional attention decoder, designed to optimize both performance and computational efficiency. EMCAD leverages a unique multi-scale depth-wise convolution block, significantly enhancing feature maps through multi-scale convolutions. EMCAD also employs channel, spatial, and grouped (large-kernel) gated attention mechanisms, which are highly effective at capturing intricate spatial relationships while focusing on salient regions. By employing group and depth-wise convolution, EMCAD is very efficient and scales well (e.g., only 1.91M parameters and 0.381G FLOPs are needed when using a standard encoder). Our rigorous evaluations across 12 datasets that belong to six medical image segmentation tasks reveal that EMCAD achieves state-of-the-art (SOTA) performance with 79.4% and 80.3% reduction in #Params and #FLOPs, respectively. Moreover, EMCAD’s adaptability to different encoders and versatility across segmentation tasks further establish EMCAD as a promising tool, advancing the field towards more efficient and accurate medical image analysis. Our implementation is available at https://github.com/SLDGroup/EMCAD.
3.
Rahman, Md Mostafijur; Marculescu, Radu
G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation Conference
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024.
Links | BibTeX | Tags: Deep Learning Architecture, Graph Neural Network, Medical Image Segmentation
@conference{WACV2024Mostafij,
title = {G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation},
author = {Md Mostafijur Rahman and Radu Marculescu},
url = {https://openaccess.thecvf.com/content/WACV2024/html/Rahman_G-CASCADE_Efficient_Cascaded_Graph_Convolutional_Decoding_for_2D_Medical_Image_WACV_2024_paper.html},
year = {2024},
date = {2024-01-04},
urldate = {2024-01-04},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages = {7728-7737},
keywords = {Deep Learning Architecture, Graph Neural Network, Medical Image Segmentation},
pubstate = {published},
tppubtype = {conference}
}
2023
2.
Rahman, Md Mostafijur; Marculescu, Radu
Medical Imaging with Deep Learning, 2023.
Links | BibTeX | Tags: Deep Learning Architecture, Medical Image Segmentation, Vision Transformer
@conference{MIDL2023,
title = {Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation},
author = {Rahman, Md Mostafijur and Marculescu, Radu},
url = {https://arxiv.org/abs/2303.16892},
year = {2023},
date = {2023-07-10},
urldate = {2023-07-10},
booktitle = {Medical Imaging with Deep Learning},
keywords = {Deep Learning Architecture, Medical Image Segmentation, Vision Transformer},
pubstate = {published},
tppubtype = {conference}
}
1.
Rahman, Md Mostafijur; Marculescu, Radu
Medical Image Segmentation via Cascaded Attention Decoding Proceedings Article
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 6222-6231, 2023.
Links | BibTeX | Tags: Deep Learning Architecture, Medical Image Segmentation
@inproceedings{cascade,
title = {Medical Image Segmentation via Cascaded Attention Decoding},
author = {Md Mostafijur Rahman and Radu Marculescu},
url = {https://ieeexplore.ieee.org/document/10030763},
year = {2023},
date = {2023-01-03},
urldate = {2023-01-03},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages = {6222-6231},
keywords = {Deep Learning Architecture, Medical Image Segmentation},
pubstate = {published},
tppubtype = {inproceedings}
}
