Jiang, Haochuan and Chartsias, Agisilaos and Papanastasiou, Giorgos and Zhang, Xinheng and Dweck, Marc and Semple, Scott and Newby, David and Dharmakumar, Rohan and Tsaftaris, Sotirios (2020) Semi-supervised Pathology Segmentation with Disentangled Representations. In: MICCAI 2020 (under review in the DART workshop), 2020-10-04 - 2020-10-08, Lima, Peru.
Jiang, Haochuan and Chartsias, Agisilaos and Papanastasiou, Giorgos and Zhang, Xinheng and Dweck, Marc and Semple, Scott and Newby, David and Dharmakumar, Rohan and Tsaftaris, Sotirios (2020) Semi-supervised Pathology Segmentation with Disentangled Representations. In: MICCAI 2020 (under review in the DART workshop), 2020-10-04 - 2020-10-08, Lima, Peru.
Jiang, Haochuan and Chartsias, Agisilaos and Papanastasiou, Giorgos and Zhang, Xinheng and Dweck, Marc and Semple, Scott and Newby, David and Dharmakumar, Rohan and Tsaftaris, Sotirios (2020) Semi-supervised Pathology Segmentation with Disentangled Representations. In: MICCAI 2020 (under review in the DART workshop), 2020-10-04 - 2020-10-08, Lima, Peru.
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.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Published proceedings: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning Second MICCAI Workshop, DART 2020, and First MICCAI Workshop, DCL 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4–8, 2020, Proceedings |
Uncontrolled Keywords: | Pathology segmentation; Disentangled representations; Semi-supervised learning |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 04 Dec 2020 20:19 |
Last Modified: | 30 Oct 2024 21:17 |
URI: | http://repository.essex.ac.uk/id/eprint/28163 |
Available files
Filename: 2009.02564.pdf