UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours

Tan, C; Hu, Y; Saeed, SU; (2025) SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours. In: Ali, S and Hogg, DC and Peckham, M, (eds.) Medical Image Understanding and Analysis: 29th Annual Conference, MIUA 2025, Leeds, UK, July 15–17, 2025, Proceedings, Part III. (pp. pp. 59-72). Springer: Cham, Switzerland.

[thumbnail of SPARS___MIUA_25-3.pdf] Text
SPARS___MIUA_25-3.pdf - Accepted Version
Access restricted to UCL open access staff until 16 July 2026.

Download (2MB)

Abstract

Accurate tumour segmentation is vital for various targeted diagnostic and therapeutic procedures for cancer, e.g., planning biopsies or tumour ablations. Manual delineation is extremely labour-intensive, requiring substantial expert time. Fully-supervised machine learning models aim to automate such localisation tasks, but require a large number of costly and often subjective 3D voxel-level labels for training. The high-variance and subjectivity in such labels impacts model generalisability, even when large datasets are available. Histopathology labels may offer more objective labels but the infeasibility of acquiring pixel-level annotations to develop tumour localisation methods based on histology remains challenging in-vivo. In this work, we propose a novel weakly-supervised semantic segmentation framework called SPARS (Self-Play Adversarial Reinforcement Learning for Segmentation), which utilises an object presence classifier, trained on a small number of image-level binary cancer presence labels, to localise cancerous regions on CT scans. Such binary labels of patient-level cancer presence can be sourced more feasibly from biopsies and histopathology reports, enabling a more objective cancer localisation on medical images. Evaluating with real patient data, we observed that SPARS yielded a mean dice score of 77.3±9.4, which outperformed other weakly-supervised methods by large margins. This performance was comparable with recent fully-supervised methods that require voxel-level annotations. Our results demonstrate the potential of using SPARS to reduce the need for extensive human-annotated labels to detect cancer in real-world healthcare settings. Code: https://github.com/catalinatan/SPARS.

Type: Proceedings paper
Title: SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours
Event: Medical Image Understanding and Analysis (MIUA 2025)
ISBN-13: 9783031986932
DOI: 10.1007/978-3-031-98694-9_5
Publisher version: https://doi.org/10.1007/978-3-031-98694-9_5
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10212299
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item