Learning from Partial Label Proportions for Whole Slide Image Segmentation

TL;DR

This paper introduces a weakly supervised learning approach for tumor subtype segmentation in whole slide images using partial label proportions, combining multiple instance learning and label proportion learning for improved accuracy.

Contribution

The paper proposes a novel algorithm that integrates MIL and LLP to effectively utilize partial label proportions for WSI segmentation, addressing a common clinical data challenge.

Findings

Effective segmentation on two WSI datasets

Outperforms baseline weakly supervised methods

Demonstrates practical utility in clinical diagnosis

Abstract

In this paper, we address the segmentation of tumor subtypes in whole slide images (WSI) by utilizing incomplete label proportions. Specifically, we utilize `partial' label proportions, which give the proportions among tumor subtypes but do not give the proportion between tumor and non-tumor. Partial label proportions are recorded as the standard diagnostic information by pathologists, and we, therefore, want to use them for realizing the segmentation model that can classify each WSI patch into one of the tumor subtypes or non-tumor. We call this problem ``learning from partial label proportions (LPLP)'' and formulate the problem as a weakly supervised learning problem. Then, we propose an efficient algorithm for this challenging problem by decomposing it into two weakly supervised learning subproblems: multiple instance learning (MIL) and learning from label proportions (LLP). These subproblems are optimized efficiently in the end-to-end manner. The effectiveness of our algorithm is demonstrated through experiments conducted on two WSI datasets.