ChampKit: A framework for rapid evaluation of deep neural networks for patch-based histopathology classification.

• We present ChampKit, a Python-based software package that enables rapid exploration and evaluation of deep learning models for patch-level classification of histopathology data. It is open source and available at https://github.com/SBU-BMI/champkit. ChampKit is designed to be highly reproducible and enables systematic, unbiased evaluation of patch-level histopathology classification. It incorporates public datasets for six clinically important tasks and access to hundreds of (pre-trained) deep learning models. It can easily be extended to custom patch classification datasets and custom deep learning architectures. • The users are intended to be (1) biomedical research groups interested in finding and fine-tuning the best models to analyze a broad collection of whole slide images, and (2) deep learning methods research groups interested in systematically and quickly evaluating their methods against a set of state-of-the-art methods with different pretraining and transfer learning configurations. • We demonstrate the utility of ChampKit by evaluating two ResNet models and one vision transformer on the six diverse classification tasks for patch-level histopathology datasets. We did not find consistent benefits from pretrained models versus random initialization across the different datasets, which suggests that a thorough exploration of model architectures is important to identify optimal models for a given dataset. Histopathology is the gold standard for diagnosis of many cancers. Recent advances in computer vision, specifically deep learning, have facilitated the analysis of histopathology images for many tasks, including the detection of immune cells and microsatellite instability. However, it remains difficult to identify optimal models and training configurations for different histopathology classification tasks due to the abundance of available architectures and the lack of systematic evaluations. Our objective in this work is to present a software tool that addresses this need and enables robust, systematic evaluation of neural network models for patch classification in histology in a light-weight, easy-to-use package for both algorithm developers and biomedical researchers. Here we present ChampKit (Comprehensive Histopathology Assessment of Model Predictions toolKit): an extensible, fully reproducible evaluation toolkit that is a one-stop-shop to train and evaluate deep neural networks for patch classification. ChampKit curates a broad range of public datasets. It enables training and evaluation of models supported by timm directly from the command line, without the need for users to write any code. External models are enabled through a straightforward API and minimal coding. As a result, Champkit facilitates the evaluation of existing and new models and deep learning architectures on pathology datasets, making it more accessible to the broader scientific community. To demonstrate the utility of ChampKit, we establish baseline performance for a subset of possible models that could be employed with ChampKit, focusing on several popular deep learning models, namely ResNet18, ResNet50, and R26-ViT, a hybrid vision transformer. In addition, we compare each model trained either from random weight initialization or with transfer learning from ImageNet pretrained models. For ResNet18, we also consider transfer learning from a self-supervised pretrained model. The main result of this paper is the ChampKit software. Using ChampKit, we were able to systemically evaluate multiple neural networks across six datasets. We observed mixed results when evaluating the benefits of pretraining versus random intialization, with no clear benefit except in the low data regime, where transfer learning was found to be beneficial. Surprisingly, we found that transfer learning from self-supervised weights rarely improved performance, which is counter to other areas of computer vision. Choosing the right model for a given digital pathology dataset is nontrivial. ChampKit provides a valuable tool to fill this gap by enabling the evaluation of hundreds of existing (or user-defined) deep learning models across a variety of pathology tasks. Source code and data for the tool are freely accessible at https://github.com/SBU-BMI/champkit. [ABSTRACT FROM AUTHOR]