Open and reusable deep learning for pathology with WSInfer and QuPath
This addresses the issue for pathologists and researchers who struggle to access and apply published models, though it is incremental as it builds on existing software and standards.
The authors tackled the problem of limited accessibility and reusability of deep learning models in digital pathology by introducing WSInfer, an open-source software ecosystem that includes tools for efficient inference, a user-friendly QuPath extension, and a model zoo, resulting in streamlined application and sharing of models without requiring coding experience.
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.