Evaluating histopathology transfer learning with ChampKit
This work addresses the problem of fragmented and non-generalizable model development in histopathology for researchers and clinicians, but it is incremental as it provides a tool rather than a new method.
The authors tackled the lack of systematic evaluation for transfer learning in histopathology by introducing ChampKit, a reproducible benchmarking toolkit with multiple patch-level classification tasks across cancers, which facilitates documenting performance impacts of model improvements.
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 .