A Self-ensembling Framework for Semi-supervised Knee Cartilage Defects Assessment with Dual-Consistency
This work addresses the high cost of annotated data for deep learning in medical imaging, specifically for knee osteoarthritis diagnosis, but it is incremental as it builds on existing semi-supervised and self-ensembling methods.
The paper tackles the problem of knee cartilage defects assessment, a subtask of osteoarthritis diagnosis, by proposing a self-ensembling framework with dual-consistency that improves classification and localization performance while reducing the need for annotated data.
Knee osteoarthritis (OA) is one of the most common musculoskeletal disorders and requires early-stage diagnosis. Nowadays, the deep convolutional neural networks have achieved greatly in the computer-aided diagnosis field. However, the construction of the deep learning models usually requires great amounts of annotated data, which is generally high-cost. In this paper, we propose a novel approach for knee cartilage defects assessment, including severity classification and lesion localization. This can be treated as a subtask of knee OA diagnosis. Particularly, we design a self-ensembling framework, which is composed of a student network and a teacher network with the same structure. The student network learns from both labeled data and unlabeled data and the teacher network averages the student model weights through the training course. A novel attention loss function is developed to obtain accurate attention masks. With dual-consistency checking of the attention in the lesion classification and localization, the two networks can gradually optimize the attention distribution and improve the performance of each other, whereas the training relies on partially labeled data only and follows the semi-supervised manner. Experiments show that the proposed method can significantly improve the self-ensembling performance in both knee cartilage defects classification and localization, and also greatly reduce the needs of annotated data.