UnCLe SAM: Unleashing SAM’s Potential for Continual Prostate MRI Segmentation

Amin Ranem, Mohamed Afham Mohamed Aflal, Moritz Fuchs, Anirban Mukhopadhyay
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1207-1220, 2024.

Abstract

Continual medical image segmentation primarily explores the utilization of U-Net and its derivatives within the realm of medical imaging, posing significant challenges in meeting the demands of shifting domains over time. Foundation models serve as robust knowledge repositories, offering unique advantages such as general applicability, knowledge transferability, and continuous improvements. By leveraging pre-existing domain insights, adaptability, generalization, and performance across diverse tasks can be enhanced.In this work, we show how to deploy Segment Anything Modelś (SAM) natural image pretraining for the continual medical image segmentation, where data is sparse.We introduce UnCLe SAM, a novel approach that uses the knowledge of the pre-trained SAM foundation model to make it suitable for continual segmentation in dynamic environments.We demonstrate that UnCLe SAM is a robust alternative to U-Net-based approaches and showcase its state-of-the-art (SOTA) continual medical segmentation capabilities.The primary objective of UnCLe SAM is to strike a delicate balance between model rigidity and plasticity, effectively addressing prevalent pitfalls within CL methodologies.We assess UnCLe SAM through a series of prostate segmentation tasks, applying a set of different CL methods. Comparative evaluations against the SOTA Lifelong nnU-Net framework reveal the potential application of UnCLe SAM in dynamically changing environments like healthcare.Our code base will be made public upon acceptance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-ranem24a, title = {UnCLe SAM: Unleashing SAM’s Potential for Continual Prostate MRI Segmentation}, author = {Ranem, Amin and Aflal, Mohamed Afham Mohamed and Fuchs, Moritz and Mukhopadhyay, Anirban}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1207--1220}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/ranem24a/ranem24a.pdf}, url = {https://proceedings.mlr.press/v250/ranem24a.html}, abstract = {Continual medical image segmentation primarily explores the utilization of U-Net and its derivatives within the realm of medical imaging, posing significant challenges in meeting the demands of shifting domains over time. Foundation models serve as robust knowledge repositories, offering unique advantages such as general applicability, knowledge transferability, and continuous improvements. By leveraging pre-existing domain insights, adaptability, generalization, and performance across diverse tasks can be enhanced.In this work, we show how to deploy Segment Anything Modelś (SAM) natural image pretraining for the continual medical image segmentation, where data is sparse.We introduce UnCLe SAM, a novel approach that uses the knowledge of the pre-trained SAM foundation model to make it suitable for continual segmentation in dynamic environments.We demonstrate that UnCLe SAM is a robust alternative to U-Net-based approaches and showcase its state-of-the-art (SOTA) continual medical segmentation capabilities.The primary objective of UnCLe SAM is to strike a delicate balance between model rigidity and plasticity, effectively addressing prevalent pitfalls within CL methodologies.We assess UnCLe SAM through a series of prostate segmentation tasks, applying a set of different CL methods. Comparative evaluations against the SOTA Lifelong nnU-Net framework reveal the potential application of UnCLe SAM in dynamically changing environments like healthcare.Our code base will be made public upon acceptance.} }
Endnote
%0 Conference Paper %T UnCLe SAM: Unleashing SAM’s Potential for Continual Prostate MRI Segmentation %A Amin Ranem %A Mohamed Afham Mohamed Aflal %A Moritz Fuchs %A Anirban Mukhopadhyay %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-ranem24a %I PMLR %P 1207--1220 %U https://proceedings.mlr.press/v250/ranem24a.html %V 250 %X Continual medical image segmentation primarily explores the utilization of U-Net and its derivatives within the realm of medical imaging, posing significant challenges in meeting the demands of shifting domains over time. Foundation models serve as robust knowledge repositories, offering unique advantages such as general applicability, knowledge transferability, and continuous improvements. By leveraging pre-existing domain insights, adaptability, generalization, and performance across diverse tasks can be enhanced.In this work, we show how to deploy Segment Anything Modelś (SAM) natural image pretraining for the continual medical image segmentation, where data is sparse.We introduce UnCLe SAM, a novel approach that uses the knowledge of the pre-trained SAM foundation model to make it suitable for continual segmentation in dynamic environments.We demonstrate that UnCLe SAM is a robust alternative to U-Net-based approaches and showcase its state-of-the-art (SOTA) continual medical segmentation capabilities.The primary objective of UnCLe SAM is to strike a delicate balance between model rigidity and plasticity, effectively addressing prevalent pitfalls within CL methodologies.We assess UnCLe SAM through a series of prostate segmentation tasks, applying a set of different CL methods. Comparative evaluations against the SOTA Lifelong nnU-Net framework reveal the potential application of UnCLe SAM in dynamically changing environments like healthcare.Our code base will be made public upon acceptance.
APA
Ranem, A., Aflal, M.A.M., Fuchs, M. & Mukhopadhyay, A.. (2024). UnCLe SAM: Unleashing SAM’s Potential for Continual Prostate MRI Segmentation. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1207-1220 Available from https://proceedings.mlr.press/v250/ranem24a.html.

Related Material