Evaluating histopathology transfer learning with ChampKit

TL;DR

ChampKit is a benchmarking toolkit for histopathology image classification that enables systematic evaluation of model improvements across diverse cancer tasks, promoting better generalization and reproducibility.

Contribution

This work introduces ChampKit, a comprehensive, extensible benchmarking toolkit for histopathology transfer learning across multiple cancer classification tasks.

Findings

ChampKit facilitates systematic performance evaluation of models.

It promotes reproducibility in histopathology image analysis.

The toolkit covers a broad range of cancer classification tasks.

Abstract

Histopathology remains the gold standard for diagnosis of various cancers. Recent advances in computer vision, specifically deep learning, have facilitated the analysis of histopathology images for various tasks, including immune cell detection and microsatellite instability classification. The state-of-the-art for each task often employs base architectures that have been pretrained for image classification on ImageNet. The standard approach to develop classifiers in histopathology tends to focus narrowly on optimizing models for a single task, not considering the aspects of modeling innovations that improve generalization across tasks. Here we present ChampKit (Comprehensive Histopathology Assessment of Model Predictions toolKit): an extensible, fully reproducible benchmarking toolkit that consists of a broad collection of patch-level image classification tasks across different cancers. ChampKit enables a way to systematically document the performance impact of proposed improvements in models and methodology. ChampKit source code and data are freely accessible at https://github.com/kaczmarj/champkit .