Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2024 Jan 10;8:9. doi: 10.1038/s41698-024-00499-9

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2024

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 1 — The WSInfer ecosystem streamlines the deployment of trained deep neural networks on whole slide images through three steps. a In Step 1, users begin by selecting their WSIs and specifying the platform for model inference along with the choice of a pretrained model. If employing the WSInfer Python Runtime, the dataset is expected to be a directory containing WSI files. Alternatively, when using the WSInfer QuPath extension, the image currently open in QuPath serves as the input. QuPath users also have the option to designate a region of interest for model inference. The pretrained model can be selected from the WSInfer Model Zoo or users can provide their own model in TorchScript format. b In Step 2, WSInfer performs a series of processing steps, including the computation of patch coordinates at the patch size and spacing prescribed by the model. Image patches are loaded directly from the WSI and used as input to the patch classification model. The model outputs are aggregated and saved to CSV and GeoJSON files. c In Step 3, model outputs can be visualized and analyzed in QuPath or other software. This example shows breast tumor patch classification on a slide from TCGA.