An End-to-End Platform for Digital Pathology Using Hyperspectral Autofluorescence Microscopy and Deep Learning-Based Virtual Histology.

Autor:	McNeil C; Verily Life Sciences LLC, South San Francisco, California. Electronic address: cmcneil@verily.com., Wong PF; Verily Life Sciences LLC, South San Francisco, California., Sridhar N; Verily Life Sciences LLC, South San Francisco, California. Electronic address: nirsd@verily.com., Wang Y; Verily Life Sciences LLC, South San Francisco, California., Santori C; Verily Life Sciences LLC, South San Francisco, California., Wu CH; Verily Life Sciences LLC, South San Francisco, California., Homyk A; Verily Life Sciences LLC, South San Francisco, California., Gutierrez M; Verily Life Sciences LLC, South San Francisco, California., Behrooz A; Verily Life Sciences LLC, South San Francisco, California., Tiniakos D; Newcastle University, Newcastle upon Tyne, United Kingdom; Medical School, National and Kapodistrian University of Athens, Athens, Greece., Burt AD; Newcastle University, Newcastle upon Tyne, United Kingdom., Pai RK; Mayo Clinic, Phoenix, Arizona., Tekiela K; Verily Life Sciences LLC, South San Francisco, California., Patel H; Verily Life Sciences LLC, South San Francisco, California., Cameron Chen PH; Google LLC, Mountain View, California., Fischer L; Allergan plc., Parsippany, New Jersey., Martins EB; Allergan plc., Parsippany, New Jersey., Seyedkazemi S; Allergan plc., Parsippany, New Jersey., Freedman D; Verily Life Sciences LLC, South San Francisco, California., Kim CC; Verily Life Sciences LLC, South San Francisco, California., Cimermancic P; Verily Life Sciences LLC, South San Francisco, California.
Jazyk:	angličtina
Zdroj:	Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc [Mod Pathol] 2024 Feb; Vol. 37 (2), pp. 100377. Date of Electronic Publication: 2023 Nov 04.
DOI:	10.1016/j.modpat.2023.100377
Abstrakt:	Conventional histopathology involves expensive and labor-intensive processes that often consume tissue samples, rendering them unavailable for other analyses. We present a novel end-to-end workflow for pathology powered by hyperspectral microscopy and deep learning. First, we developed a custom hyperspectral microscope to nondestructively image the autofluorescence of unstained tissue sections. We then trained a deep learning model to use autofluorescence to generate virtual histologic stains, which avoids the cost and variability of chemical staining procedures and conserves tissue samples. We showed that the virtual images reproduce the histologic features present in the real-stained images using a randomized nonalcoholic steatohepatitis (NASH) scoring comparison study, where both real and virtual stains are scored by pathologists (D.T., A.D.B., R.K.P.). The test showed moderate-to-good concordance between pathologists' scoring on corresponding real and virtual stains. Finally, we developed deep learning-based models for automated NASH Clinical Research Network score prediction. We showed that the end-to-end automated pathology platform is comparable with an independent panel of pathologists for NASH Clinical Research Network scoring when evaluated against the expert pathologist consensus scores. This study provides proof of concept for this virtual staining strategy, which could improve cost, efficiency, and reliability in pathology and enable novel approaches to spatial biology research. (Copyright © 2023 United States & Canadian Academy of Pathology. Published by Elsevier Inc. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu