Benefits of high-magnification and color information in computational pathology—An exploratory review

Abstract

Introduction

The analysis of gigapixel high-resolution whole-slide images (WSIs) with rich color information using deep learning (DL) models is a routine task in computational pathology (CPath). However, the necessity of such information-rich inputs remains insufficiently explored.

Objectives

This literature study aims to collect evidence for the benefit, or its absence, of using WSIs with high magnification levels and full color information in CPath DL models.

Methods

Due to the scarcity of domain-specific studies, the exploratory review includes research from related domains, such as broader medical imaging and computer vision in general. The search was conducted using different permutations of keywords in established databases such as IEEE Xplore and PubMed. The retrieved literature was pre-screened by a researcher and relevant work was screened by two researchers independently.

Results

The analyzed literature reinforces the lack of direct empirical evidence for using high magnification WSIs with full color information in CPath. Conversely, some findings suggest that reducing image resolution can often maintain high DL accuracy for many classification and detection tasks. Similarly, thoughtful reduction of color information, such as advanced grayscale conversions, can preserve critical diagnostic features with minimal impact on DL performance.

Conclusion

The review underscores the need to critically re-examine prevailing conventions on WSI magnification and color usage to optimize DL-driven CPath applications. The lack of direct evidence warrants further research and the establishment of reliable benchmarks in this domain.