Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling.

Details

Serval ID
serval:BIB_7E52FA6DFCFD
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling.
Journal
Nature machine intelligence
Author(s)
Pati P., Karkampouna S., Bonollo F., Compérat E., Radić M., Spahn M., Martinelli A., Wartenberg M., Kruithof-de Julio M., Rapsomaniki M.
ISSN
2522-5839 (Electronic)
ISSN-L
2522-5839
Publication state
Published
Issued date
2024
Peer-reviewed
Oui
Volume
6
Number
9
Pages
1077-1093
Language
english
Notes
Publication types: Journal Article
Publication Status: ppublish
Abstract
Understanding the spatial heterogeneity of tumours and its links to disease initiation and progression is a cornerstone of cancer biology. Presently, histopathology workflows heavily rely on hematoxylin and eosin and serial immunohistochemistry staining, a cumbersome, tissue-exhaustive process that results in non-aligned tissue images. We propose the VirtualMultiplexer, a generative artificial intelligence toolkit that effectively synthesizes multiplexed immunohistochemistry images for several antibody markers (namely AR, NKX3.1, CD44, CD146, p53 and ERG) from only an input hematoxylin and eosin image. The VirtualMultiplexer captures biologically relevant staining patterns across tissue scales without requiring consecutive tissue sections, image registration or extensive expert annotations. Thorough qualitative and quantitative assessment indicates that the VirtualMultiplexer achieves rapid, robust and precise generation of virtually multiplexed imaging datasets of high staining quality that are indistinguishable from the real ones. The VirtualMultiplexer is successfully transferred across tissue scales and patient cohorts with no need for model fine-tuning. Crucially, the virtually multiplexed images enabled training a graph transformer that simultaneously learns from the joint spatial distribution of several proteins to predict clinically relevant endpoints. We observe that this multiplexed learning scheme was able to greatly improve clinical prediction, as corroborated across several downstream tasks, independent patient cohorts and cancer types. Our results showcase the clinical relevance of artificial intelligence-assisted multiplexed tumour imaging, accelerating histopathology workflows and cancer biology.
Keywords
Cancer imaging, Machine learning
Pubmed
Web of science
Open Access
Yes
Create date
27/09/2024 15:32
Last modification date
28/09/2024 7:09
Usage data