Semi-supervised Pathology Segmentation with Disentangled Representations
This work addresses data scarcity in clinical pathology segmentation, which is an incremental improvement for medical imaging applications.
The paper tackles the problem of automated pathology segmentation with limited labeled data by proposing APD-Net, a semi-supervised model that disentangles anatomy, modality, and pathology, and it outperforms related deep learning methods on cardiac infarction segmentation datasets.
Automated pathology segmentation remains a valuable diagnostic tool in clinical practice. However, collecting training data is challenging. Semi-supervised approaches by combining labelled and unlabelled data can offer a solution to data scarcity. An approach to semi-supervised learning relies on reconstruction objectives (as self-supervision objectives) that learns in a joint fashion suitable representations for the task. Here, we propose Anatomy-Pathology Disentanglement Network (APD-Net), a pathology segmentation model that attempts to learn jointly for the first time: disentanglement of anatomy, modality, and pathology. The model is trained in a semi-supervised fashion with new reconstruction losses directly aiming to improve pathology segmentation with limited annotations. In addition, a joint optimization strategy is proposed to fully take advantage of the available annotations. We evaluate our methods with two private cardiac infarction segmentation datasets with LGE-MRI scans. APD-Net can perform pathology segmentation with few annotations, maintain performance with different amounts of supervision, and outperform related deep learning methods.