# Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images

arXiv: https://arxiv.org/abs/2402.13778 · HTML: https://mlsanity.com/paper/2402.13778/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Data Valuation using Reinforcement Learning](https://mlsanity.com/paper/1909.11671/) (2019)
- [An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization](https://mlsanity.com/paper/2002.07613/) (2020)
- [Domain-adversarial neural networks to address the appearance variability of histopathology images](https://mlsanity.com/paper/1707.06183/) (2017)
- [Is segmentation uncertainty useful?](https://mlsanity.com/paper/2103.16265/) (2021)
- [Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images](https://mlsanity.com/paper/1710.03778/) (2017)
- [Learning to detect chest radiographs containing lung nodules using visual attention networks](https://mlsanity.com/paper/1712.00996/) (2017)
- [Prostate Cancer Detection using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1905.13145/) (2019)
- [Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation](https://mlsanity.com/paper/2202.09798/) (2022)
- [Breast Cancer Histopathology Image Classification and Localization using Multiple Instance Learning](https://mlsanity.com/paper/2003.00823/) (2020)
- [Adaptable image quality assessment using meta-reinforcement learning of task amenability](https://mlsanity.com/paper/2108.04359/) (2021)
- [The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation](https://mlsanity.com/paper/2203.16415/) (2022)

## Built on by (most cited first, 4 of 4)

- [Promptable cancer segmentation using minimal expert-curated data](https://mlsanity.com/paper/2505.17915/) (2025)
- [SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours](https://mlsanity.com/paper/2505.18989/) (2025)
- [Reasoning in machine vision by learning fast and slow thinking](https://mlsanity.com/paper/2506.22075/) (2025)
- [Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learning](https://mlsanity.com/paper/2509.04886/) (2025)

## Abstract (arXiv)

In this paper we propose a reinforcement learning based weakly supervised system for localisation. We train a controller function to localise regions of interest within an image by introducing a novel reward definition that utilises non-binarised classification probability, generated by a pre-trained binary classifier which classifies object presence in images or image crops. The object-presence classifier may then inform the controller of its localisation quality by quantifying the likelihood of the image containing an object. Such an approach allows us to minimize any potential labelling or human bias propagated via human labelling for fully supervised localisation. We evaluate our proposed approach for a task of cancerous lesion localisation on a large dataset of real clinical bi-parametric MR images of the prostate. Comparisons to the commonly used multiple-instance learning weakly supervised localisation and to a fully supervised baseline show that our proposed method outperforms the multi-instance learning and performs comparably to fully-supervised learning, using only image-level classification labels for training.