Semi-supervised Pathology Segmentation with Disentangled Representations

Abstract

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.

12 Pages, 4 figures

References in corpus (4)

• Disentangled Representation Learning in Cardiac Image Analysis
• Pseudo-healthy synthesis with pathology disentanglement and adversarial learning
• 3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin
• Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function