# Promptable cancer segmentation using minimal expert-curated data

arXiv: https://arxiv.org/abs/2505.17915 · HTML: https://mlsanity.com/paper/2505.17915/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 15 of 15)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image](https://mlsanity.com/paper/2312.07381/) (2023)
- [Segment Anything in Medical Images and Videos: Benchmark and Deployment](https://mlsanity.com/paper/2408.03322/) (2024)
- [Is segmentation uncertainty useful?](https://mlsanity.com/paper/2103.16265/) (2021)
- [PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts](https://mlsanity.com/paper/2404.15028/) (2024)
- [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)
- [Weakly-Supervised Deep Learning Model for Prostate Cancer Diagnosis and Gleason Grading of Histopathology Images](https://mlsanity.com/paper/2212.12844/) (2022)
- [The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation](https://mlsanity.com/paper/2203.16415/) (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)
- [T2-Only Prostate Cancer Prediction by Meta-Learning from Bi-Parametric MR Imaging](https://mlsanity.com/paper/2411.07416/) (2024)
- [Mixed Supervision of Histopathology Improves Prostate Cancer Classification from MRI](https://mlsanity.com/paper/2212.06336/) (2022)
- [ProMISe: Promptable Medical Image Segmentation using SAM](https://mlsanity.com/paper/2403.04164/) (2024)

## Built on by (most cited first, 2 of 2)

- [Cryo-RL: automating prostate cancer cryoablation planning with reinforcement learning](https://mlsanity.com/paper/2509.04886/) (2025)
- [Promptable segmentation with region exploration enables minimal-effort expert-level prostate cancer delineation](https://mlsanity.com/paper/2602.17813/) (2026)

## Abstract (arXiv)

Automated segmentation of cancer on medical images can aid targeted diagnostic and therapeutic procedures. However, its adoption is limited by the high cost of expert annotations required for training and inter-observer variability in datasets. While weakly-supervised methods mitigate some challenges, using binary histology labels for training as opposed to requiring full segmentation, they require large paired datasets of histology and images, which are difficult to curate. Similarly, promptable segmentation aims to allow segmentation with no re-training for new tasks at inference, however, existing models perform poorly on pathological regions, again necessitating large datasets for training. In this work we propose a novel approach for promptable segmentation requiring only 24 fully-segmented images, supplemented by 8 weakly-labelled images, for training. Curating this minimal data to a high standard is relatively feasible and thus issues with the cost and variability of obtaining labels can be mitigated. By leveraging two classifiers, one weakly-supervised and one fully-supervised, our method refines segmentation through a guided search process initiated by a single-point prompt. Our approach outperforms existing promptable segmentation methods, and performs comparably with fully-supervised methods, for the task of prostate cancer segmentation, while using substantially less annotated data (up to 100X less). This enables promptable segmentation with very minimal labelled data, such that the labels can be curated to a very high standard.