Comparing foundation models and nnU-Net for segmentation of primary brain lymphoma on clinical routine post-contrast T1-weighted MRI
Authors:
- Guanghui FuGFGuanghui Fu
- Lucia NichelliLNLucia Nichelli
- Dario HerranDHDario Herran
- Romain ValabregueRVRomain Valabregue
- Agusti AlentornAAAgusti Alentorn
- Khê Hoang-XuanKHKhê Hoang-Xuan
- Caroline HouillierCHCaroline Houillier
- Didier DormontDDDidier Dormont
- Stéphane LehéricySLStéphane Lehéricy
- Olivier ColliotOCOlivier Colliot
Preprint
Abstract
Primary Central Nervous System (PCNS) lymphoma is an aggressive brain tumor with variable response rates to current therapeutic strategies. Segmentation of PCNS lymphoma on magnetic resonance imaging (MRI) is important to enhance diagnosis and follow-up. However, it is a difficult task due to the highly variable presentation of lymphoma lesions and the heterogeneity of acquisitions in clinical routine. The recent rise of foundation models (FM) for segmentation, such as Segment Anything Model (SAM), offers a potential alternative to classical supervised deep learning approaches. Nevertheless, their value on challenging tasks such as lymphoma segmentation on clinical routine data has not been thoroughly studied. In this paper, we assessed the performance of several FMs (SAM, MedSAM, UniverSeg) for lymphoma segmentation and compared them to a classical supervised learning with nnU-net. In addition, we performed experiments on the public dataset MSD-BraTS so that others can reproduce our findings. We found that nnU-net outperformed FMs by vast and statistically significant margins. For the lymphoma clinical routine dataset, the difference between nnU-Net and the best FM was about 19 percent points of Dice. For MSD-BraTS, it was about 10 percent points. Our findings suggest that current FMs fall short in handling complex segmentation tasks in particular on clinical routine data and that 3D supervised learning (e.g. with nnU-Net) is essential at present. Trained models for both tasks, code and box prompts (for MSD-BraTS) are available at: https://github.com/GuanghuiFU/medical_cv_foundation_eval.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- I-MedSAM: Implicit Medical Image Segmentation with Segment Anything2024
- EviPrompt: A Training-Free Evidential Prompt Generation Method for Adapting Segment Anything Model in Medical ImagesIEEE Transactions on Image Processing, 2024
- SAMIHS: Adaptation of Segment Anything Model for Intracranial Hemorrhage Segmentation2024
- Segment anything model for medical images?Medical Image Analysis, 2023
- TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningComputer Methods and Programs in Biomedicine, 2021
- CANet: Context Aware Network for Brain Glioma SegmentationIEEE Transactions on Medical Imaging, 2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- Primary Central Nervous System Lymphoma: Clinical Evaluation of Automated Segmentation on Multiparametric MRI Using Deep LearningJournal of Magnetic Resonance Imaging, 2020
- Automated Brain Tumor Segmentation Using Multimodal Brain Scans: A Survey Based on Models Submitted to the BraTS 2012–2018 ChallengesIEEE Reviews in Biomedical Engineering, 2019