MedNet-FS: a few-shot learning framework for 3D MRI-based knee injury classification.
Authors
Affiliations (4)
Affiliations (4)
- Department of Orthopedics, Xiangyang No.1 People's Hospital, Hubei University of Medicine, Xiangyang, Hubei, 441000, China.
- Department of Rehabilitation Medicine, Hyperbaric Oxygen Room, Xiangyang First People's Hospital, Hubei Medical College, Xiangyang, Hubei, 441000, China.
- Department of Emergency, Xiangyang No.1 People's Hospital, Hubei University of Medicine, Xiangyang, Hubei, 441000, China. [email protected].
- Department of Emergency, Xiangyang No.1 People's Hospital, Hubei University of Medicine, Xiangyang, Hubei, 441000, China.
Abstract
The development of deep learning models for 3D knee MRI analysis is critically constrained by the scarcity of large, annotated datasets. Few-shot learning (FSL) offers a promising pathway to leverage small data, but its effective application to volumetric medical imaging remains underexplored. This study introduces MedNet-FS, a 3D FSL framework that strategically integrates domain-specific pre-training on knee MRI data with a Generalized End-to-End (GE2E) loss to create a highly effective solution for data-scarce environments. Our central finding is that this targeted combination is paramount; MedNet-FS significantly outperforms models using generic pre-training or standard cross-entropy loss. On the internal MRNet dataset, our framework achieved an AUC of 0.76 for ACL tear detection using only 40 samples per class, demonstrating performance competitive with supervised learning. External validation on the KneeMRI dataset confirmed its generalizability for distinguishing clear cases (AUC of 0.62 for intact vs. fully ruptured ACLs), while also highlighting a key limitation: performance decreased for ambiguous partial tears (AUC 0.58), reflecting a known diagnostic challenge. While the current performance is below the threshold for autonomous clinical deployment, this work provides a robust proof-of-concept and a strong baseline, establishing a practical and scalable FSL framework that effectively reduces annotation dependency and charts a course for future development in data-efficient medical image analysis.