Open and reusable deep learning for pathology with WSInfer and QuPath

TL;DR

WSInfer is an open-source ecosystem that simplifies sharing, applying, and exploring deep learning models in digital pathology, making advanced tools more accessible to researchers and pathologists without coding expertise.

Contribution

The paper introduces WSInfer, a comprehensive platform combining software tools and a model zoo to enhance accessibility and reuse of deep learning models in pathology.

Findings

Facilitates easy application of deep learning to whole slide images

Enables sharing of models and metadata in a standardized format

Provides user-friendly interfaces for pathologists

Abstract

The field of digital pathology has seen a proliferation of deep learning models in recent years. Despite substantial progress, it remains rare for other researchers and pathologists to be able to access models published in the literature and apply them to their own images. This is due to difficulties in both sharing and running models. To address these concerns, we introduce WSInfer: a new, open-source software ecosystem designed to make deep learning for pathology more streamlined and accessible. WSInfer comprises three main elements: 1) a Python package and command line tool to efficiently apply patch-based deep learning inference to whole slide images; 2) a QuPath extension that provides an alternative inference engine through user-friendly and interactive software, and 3) a model zoo, which enables pathology models and metadata to be easily shared in a standardized form. Together, these contributions aim to encourage wider reuse, exploration, and interrogation of deep learning models for research purposes, by putting them into the hands of pathologists and eliminating a need for coding experience when accessed through QuPath. The WSInfer source code is hosted on GitHub and documentation is available at https://wsinfer.readthedocs.io.