WT-BCP: Wavelet Transform based Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation
This work addresses semi-supervised segmentation for medical imaging, offering incremental improvements to reduce reliance on labeled data.
The paper tackles challenges in semi-supervised medical image segmentation, such as distribution mismatches and inadequate use of image frequency components, by proposing WT-BCP, a framework that improves upon Mean Teacher with wavelet transform and bidirectional copy-paste, achieving state-of-the-art results on 2D and 3D datasets.
Semi-supervised medical image segmentation (SSMIS) shows promise in reducing reliance on scarce labeled medical data. However, SSMIS field confronts challenges such as distribution mismatches between labeled and unlabeled data, artificial perturbations causing training biases, and inadequate use of raw image information, especially low-frequency (LF) and high-frequency (HF) components.To address these challenges, we propose a Wavelet Transform based Bidirectional Copy-Paste SSMIS framework, named WT-BCP, which improves upon the Mean Teacher approach. Our method enhances unlabeled data understanding by copying random crops between labeled and unlabeled images and employs WT to extract LF and HF details.We propose a multi-input and multi-output model named XNet-Plus, to receive the fused information after WT. Moreover, consistency training among multiple outputs helps to mitigate learning biases introduced by artificial perturbations. During consistency training, the mixed images resulting from WT are fed into both models, with the student model's output being supervised by pseudo-labels and ground-truth. Extensive experiments conducted on 2D and 3D datasets confirm the effectiveness of our model.Code: https://github.com/simzhangbest/WT-BCP.