Diagonal Hierarchical Consistency Learning for Semi-supervised Medical Image Segmentation
This work addresses the annotation bottleneck in medical image segmentation, offering a robust solution that is incremental but effective for clinical applications.
The paper tackles the problem of costly manual annotation for medical image segmentation by proposing a semi-supervised learning framework called DiHC-Net, which uses diagonal hierarchical consistency learning to achieve state-of-the-art performance on public benchmarks for organ and tumour segmentation.
Medical image segmentation, which is essential for many clinical applications, has achieved almost human-level performance via data-driven deep learning technologies. Nevertheless, its performance is predicated upon the costly process of manually annotating a vast amount of medical images. To this end, we propose a novel framework for robust semi-supervised medical image segmentation using diagonal hierarchical consistency learning (DiHC-Net). First, it is composed of multiple sub-models with identical multi-scale architecture but with distinct sub-layers, such as up-sampling and normalisation layers. Second, with mutual consistency, a novel consistency regularisation is enforced between one model's intermediate and final prediction and soft pseudo labels from other models in a diagonal hierarchical fashion. A series of experiments verifies the efficacy of our simple framework, outperforming all previous approaches on public benchmark dataset covering organ and tumour.