2025
2.
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.
2024
1.
Rahman, Md Mostafijur; Munir, Mustafa; Jha, Debesh; Bagci, Ulas; Marculescu, Radu
PP-SAM: Perturbed Prompts for Robust Adaption of Segment Anything Model for Polyp Segmentation Conference
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024.
Abstract | Links | BibTeX | Tags: Limited data, Perturbed prompts, Polyp segmentation, Robustness, SAM
@conference{ppsam@rahman,
title = {PP-SAM: Perturbed Prompts for Robust Adaption of Segment Anything Model for Polyp Segmentation},
author = {Md Mostafijur Rahman and Mustafa Munir and Debesh Jha and Ulas Bagci and Radu Marculescu},
url = {https://openaccess.thecvf.com/content/CVPR2024W/DEF-AI-MIA/papers/Rahman_PP-SAM_Perturbed_Prompts_for_Robust_Adaption_of_Segment_Anything_Model_CVPRW_2024_paper.pdf},
year = {2024},
date = {2024-06-17},
urldate = {2024-06-17},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
abstract = {The Segment Anything Model (SAM), originally designed for general-purpose segmentation tasks, has been used recently for polyp segmentation. Nonetheless, finetuning SAM with data from new imaging centers or clinics poses significant challenges. This is because this necessitates the creation of an expensive and time-intensive annotated dataset, along with the potential for variability in user prompts during inference. To address these issues, we propose a robust fine-tuning technique, PP-SAM, that allows SAM to adapt to the polyp segmentation task with limited images. To this end, we utilize variable perturbed bounding box prompts (BBP) to enrich the learning context and enhance the model’s robustness to BBP perturbations during inference. Rigorous experiments on polyp segmentation benchmarks reveal that our variable BBP perturbation significantly improves model resilience. Notably, on Kvasir, 1-shot fine-tuning boosts the DICE score by 20% and 37% with 50 and 100-pixel BBP perturbations during inference, respectively. Moreover, our experiments show that 1-shot, 5-shot, and 10-shot PP-SAM with 50-pixel perturbations during inference outperform a recent state-ofthe-art (SOTA) polyp segmentation method by 26%, 7%, and 5% DICE scores, respectively. Our results motivate the broader applicability of our PP-SAM for other medical imaging tasks with limited samples. Our implementation is available at https://github.com/SLDGroup/PP-SAM.},
keywords = {Limited data, Perturbed prompts, Polyp segmentation, Robustness, SAM},
pubstate = {published},
tppubtype = {conference}
}
The Segment Anything Model (SAM), originally designed for general-purpose segmentation tasks, has been used recently for polyp segmentation. Nonetheless, finetuning SAM with data from new imaging centers or clinics poses significant challenges. This is because this necessitates the creation of an expensive and time-intensive annotated dataset, along with the potential for variability in user prompts during inference. To address these issues, we propose a robust fine-tuning technique, PP-SAM, that allows SAM to adapt to the polyp segmentation task with limited images. To this end, we utilize variable perturbed bounding box prompts (BBP) to enrich the learning context and enhance the model’s robustness to BBP perturbations during inference. Rigorous experiments on polyp segmentation benchmarks reveal that our variable BBP perturbation significantly improves model resilience. Notably, on Kvasir, 1-shot fine-tuning boosts the DICE score by 20% and 37% with 50 and 100-pixel BBP perturbations during inference, respectively. Moreover, our experiments show that 1-shot, 5-shot, and 10-shot PP-SAM with 50-pixel perturbations during inference outperform a recent state-ofthe-art (SOTA) polyp segmentation method by 26%, 7%, and 5% DICE scores, respectively. Our results motivate the broader applicability of our PP-SAM for other medical imaging tasks with limited samples. Our implementation is available at https://github.com/SLDGroup/PP-SAM.
