Dcl-Net: Dual Contrastive Learning Network for Semi-Supervised Multi-Organ Segmentation
This work addresses the challenge of reducing annotation needs for multi-organ segmentation, which is important for medical imaging applications, but it appears incremental as it builds on existing SSL methods.
The paper tackles the problem of semi-supervised multi-organ segmentation by proposing a dual contrastive learning network that uses global and local contrastive learning to improve relations among images and classes, achieving superior performance on public and in-house datasets.
Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation . However, most existing SSL methods predict pixels in a single image independently, ignoring the relations among images and categories. In this paper, we propose a two-stage Dual Contrastive Learning Network for semi-supervised MoS, which utilizes global and local contrastive learning to strengthen the relations among images and classes. Concretely, in Stage 1, we develop a similarity-guided global contrastive learning to explore the implicit continuity and similarity among images and learn global context. Then, in Stage 2, we present an organ-aware local contrastive learning to further attract the class representations. To ease the computation burden, we introduce a mask center computation algorithm to compress the category representations for local contrastive learning. Experiments conducted on the public 2017 ACDC dataset and an in-house RC-OARs dataset has demonstrated the superior performance of our method.