Anatomy-Constrained Contrastive Learning for Synthetic Segmentation without Ground-truth
This work addresses the need for reducing manual segmentation efforts in medical imaging by enabling cross-modality adaptation, though it is incremental as it builds on existing contrastive learning and unsupervised adaptation techniques.
The paper tackled the problem of training segmentation networks for new imaging modalities without requiring manual segmentation in those modalities, by developing an anatomy-constrained contrastive synthetic segmentation network (AccSeg-Net) that achieved superior segmentation performances on CBCT, MRI, and PET data compared to previous methods.
A large amount of manual segmentation is typically required to train a robust segmentation network so that it can segment objects of interest in a new imaging modality. The manual efforts can be alleviated if the manual segmentation in one imaging modality (e.g., CT) can be utilized to train a segmentation network in another imaging modality (e.g., CBCT/MRI/PET). In this work, we developed an anatomy-constrained contrastive synthetic segmentation network (AccSeg-Net) to train a segmentation network for a target imaging modality without using its ground truth. Specifically, we proposed to use anatomy-constraint and patch contrastive learning to ensure the anatomy fidelity during the unsupervised adaptation, such that the segmentation network can be trained on the adapted image with correct anatomical structure/content. The training data for our AccSeg-Net consists of 1) imaging data paired with segmentation ground-truth in source modality, and 2) unpaired source and target modality imaging data. We demonstrated successful applications on CBCT, MRI, and PET imaging data, and showed superior segmentation performances as compared to previous methods.