Open and reusable deep learning for pathology with WSInfer and QuPath.

Autor: Kaczmarzyk JR; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA. jakub.kaczmarzyk@stonybrookmedicine.edu., O'Callaghan A; Centre for Genomic & Experimental Medicine, Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK., Inglis F; Centre for Genomic & Experimental Medicine, Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK., Gat S; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA., Kurc T; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA., Gupta R; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA., Bremer E; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA., Bankhead P; Centre for Genomic & Experimental Medicine, Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK.; Edinburgh Pathology and CRUK Scotland Centre, Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK., Saltz JH; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA.
Jazyk: angličtina
Zdroj: NPJ precision oncology [NPJ Precis Oncol] 2024 Jan 10; Vol. 8 (1), pp. 9. Date of Electronic Publication: 2024 Jan 10.
DOI: 10.1038/s41698-024-00499-9
Abstrakt: Digital pathology has seen a proliferation of deep learning models in recent years, but many models are not readily reusable. To address this challenge, we developed WSInfer: an open-source software ecosystem designed to streamline the sharing and reuse of deep learning models for digital pathology. The increased access to trained models can augment research on the diagnostic, prognostic, and predictive capabilities of digital pathology.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: