Learning with less data via Weakly Labeled Patch Classification in Digital Pathology

TL;DR

This paper demonstrates that in digital pathology, transferable features learned from weakly labeled data collected by non-experts can achieve competitive patch classification results with significantly less labeled data.

Contribution

It introduces a method to learn transferable features from weakly labeled datasets in digital pathology, reducing the need for expert annotations.

Findings

Achieves high accuracy on CRC and PCam datasets

Uses significantly less labeled data than traditional methods

Features are transferable across different datasets

Abstract

In Digital Pathology (DP), labeled data is generally very scarce due to the requirement that medical experts provide annotations. We address this issue by learning transferable features from weakly labeled data, which are collected from various parts of the body and are organized by non-medical experts. In this paper, we show that features learned from such weakly labeled datasets are indeed transferable and allow us to achieve highly competitive patch classification results on the colorectal cancer (CRC) dataset [1] and the PatchCamelyon (PCam) dataset [2] while using an order of magnitude less labeled data.