Patch Stitching Data Augmentation for Cancer Classification in Pathology Images

TL;DR

This paper proposes a simple data augmentation method called patch stitching to generate additional pathology images, improving colorectal cancer classification accuracy and addressing data scarcity and imbalance issues in computational pathology.

Contribution

The paper introduces a novel patch stitching data augmentation technique specifically designed for pathology images to enhance cancer classification performance.

Findings

Improved classification accuracy on colorectal cancer datasets

Effective in alleviating data scarcity and imbalance

Simple and efficient augmentation strategy

Abstract

Computational pathology, integrating computational methods and digital imaging, has shown to be effective in advancing disease diagnosis and prognosis. In recent years, the development of machine learning and deep learning has greatly bolstered the power of computational pathology. However, there still remains the issue of data scarcity and data imbalance, which can have an adversarial effect on any computational method. In this paper, we introduce an efficient and effective data augmentation strategy to generate new pathology images from the existing pathology images and thus enrich datasets without additional data collection or annotation costs. To evaluate the proposed method, we employed two sets of colorectal cancer datasets and obtained improved classification results, suggesting that the proposed simple approach holds the potential for alleviating the data scarcity and imbalance in computational pathology.