The Francis Crick Institute
Browse
s43018-023-00694-w (2).pdf (11.15 MB)

The artificial intelligence-based model ANORAK improves histopathological grading of lung adenocarcinoma.

Download (11.15 MB)
journal contribution
posted on 2024-02-29, 11:00 authored by Xiaoxi Pan, Khalid AbdulJabbar, Jose Coelho-Lima, Anca-Ioana Grapa, Hanyun Zhang, Alvin Ho Kwan Cheung, Juvenal Baena, Takahiro Karasaki, Claire Rachel Wilson, Marco Sereno, Selvaraju Veeriah, Sarah J Aitken, Allan Hackshaw, Andrew G Nicholson, Mariam Jamal-Hanjani, TRACERx Consortium, Charles Swanton, Yinyin Yuan, John Le Quesne, David A Moore
The introduction of the International Association for the Study of Lung Cancer grading system has furthered interest in histopathological grading for risk stratification in lung adenocarcinoma. Complex morphology and high intratumoral heterogeneity present challenges to pathologists, prompting the development of artificial intelligence (AI) methods. Here we developed ANORAK (pyrAmid pooliNg crOss stReam Attention networK), encoding multiresolution inputs with an attention mechanism, to delineate growth patterns from hematoxylin and eosin-stained slides. In 1,372 lung adenocarcinomas across four independent cohorts, AI-based grading was prognostic of disease-free survival, and further assisted pathologists by consistently improving prognostication in stage I tumors. Tumors with discrepant patterns between AI and pathologists had notably higher intratumoral heterogeneity. Furthermore, ANORAK facilitates the morphological and spatial assessment of the acinar pattern, capturing acinus variations with pattern transition. Collectively, our AI method enabled the precision quantification and morphology investigation of growth patterns, reflecting intratumoral histological transitions in lung adenocarcinoma.

Funding

Crick (Grant ID: CC2041, Grant title: Swanton CC2041) Crick (Grant ID: CC2008, Grant title: Van Loo CC2008) Crick (Grant ID: CC2088, Grant title: Kassiotis CC2088) Crick (Grant ID: CC1064, Grant title: STP Advanced Sequencing) Crick (Grant ID: CC1107, Grant title: STP Bioinformatics & Biostatistics) Crick (Grant ID: CC1061, Grant title: STP Experimental Histopathology) Crick (Grant ID: CC1062, Grant title: STP Flow Cytometry) Crick (Grant ID: CC1119, Grant title: STP Scientific Computing) Novo Nordisk UK Research Foundation (Grant ID: NNF15OC0016584, Grant title: NovoNordisk Foundation 16584) European Research Council (Grant ID: 835297 - PROTEUS, Grant title: ERC 835297 - PROTEUS)

History