3D Cross-Pseudo Supervision (3D-CPS): A semi-supervised nnU-Net architecture for abdominal organ segmentation
This addresses the challenge of reducing annotation costs for medical image segmentation, though it appears incremental as it builds on existing nnU-Net and Cross-Pseudo Supervision methods.
The paper tackles the problem of segmenting abdominal organs in medical images by proposing a semi-supervised method called 3D-CPS, which achieves an average dice similarity coefficient of 0.881 and normalized surface distance of 0.913 on the MICCAI FLARE2022 validation set.
Large curated datasets are necessary, but annotating medical images is a time-consuming, laborious, and expensive process. Therefore, recent supervised methods are focusing on utilizing a large amount of unlabeled data. However, to do so, is a challenging task. To address this problem, we propose a new 3D Cross-Pseudo Supervision (3D-CPS) method, a semi-supervised network architecture based on nnU-Net with the Cross-Pseudo Supervision method. We design a new nnU-Net based preprocessing. In addition, we set the semi-supervised loss weights to expand linearity with each epoch to prevent the model from low-quality pseudo-labels in the early training process. Our proposed method achieves an average dice similarity coefficient (DSC) of 0.881 and an average normalized surface distance (NSD) of 0.913 on the MICCAI FLARE2022 validation set (20 cases).