Promptable cancer segmentation using minimal expert-curated data

TL;DR

This paper introduces a promptable cancer segmentation method that achieves high accuracy with minimal expert-annotated data, reducing labeling costs and variability, and outperforming existing promptable models.

Contribution

The authors propose a novel promptable segmentation approach that requires only 24 fully-segmented and 8 weakly-labelled images, significantly reducing data annotation needs.

Findings

Outperforms existing promptable segmentation methods.

Performs comparably to fully-supervised methods with much less data.

Requires up to 100X less annotated data.

Abstract

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.