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

arXiv: https://arxiv.org/abs/2505.18989 · HTML: https://mlsanity.com/paper/2505.18989/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 25 May 2025.

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](https://mlsanity.com/paper/1603.07485/) (2016)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Single-Stage Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2005.08104/) (2020)
- [Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation](https://mlsanity.com/paper/1805.04574/) (2018)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02909/) (2022)
- [Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.09653/) (2022)
- [Is segmentation uncertainty useful?](https://mlsanity.com/paper/2103.16265/) (2021)
- [Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace](https://mlsanity.com/paper/2102.09896/) (2021)
- [MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2304.09913/) (2023)
- [Active learning using adaptable task-based prioritisation](https://mlsanity.com/paper/2212.01703/) (2022)
- [Development and evaluation of intraoperative ultrasound segmentation with negative image frames and multiple observer labels](https://mlsanity.com/paper/2108.04114/) (2021)
- [Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images](https://mlsanity.com/paper/2402.13778/) (2024)
- [Boundary-RL: Reinforcement Learning for Weakly-Supervised Prostate Segmentation in TRUS Images](https://mlsanity.com/paper/2308.11376/) (2023)

## Built on by (most cited first, 1 of 1)

- [Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learning](https://mlsanity.com/paper/2509.04886/) (2025)

## Abstract (arXiv)

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.