A Deep Learning Approach for the Identification of the Molecular Subtypes of Pancreatic Ductal Adenocarcinoma Based on Whole Slide Pathology Images

Pouya Ahmadvand; Hossein Farahani; David Farnell; Amirali Darbandsari; James Topham; Joanna Karasinska; Jessica Nelson; Julia Naso; Steven J M Jones; Daniel Renouf; David F Schaeffer; Ali Bashashati

doi:10.1016/j.ajpath.2024.08.006

A Deep Learning Approach for the Identification of the Molecular Subtypes of Pancreatic Ductal Adenocarcinoma Based on Whole Slide Pathology Images

Am J Pathol. 2024 Dec;194(12):2302-2312. doi: 10.1016/j.ajpath.2024.08.006. Epub 2024 Aug 31.

Authors

Affiliations

¹ School of Biomedical Engineering, University of British Columbia, Vancouver, British Columbia, Canada.
² Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, British Columbia, Canada; Vancouver General Hospital, Vancouver, British Columbia, Canada.
³ Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada.
⁴ Pancreas Centre BC, Vancouver, British Columbia, Canada.
⁵ British Columbia Cancer Research Center, Vancouver, British Columbia, Canada.
⁶ Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, British Columbia, Canada.
⁷ Michael Smith Genome Sciences Center, British Columbia Cancer Research Center, Vancouver, British Columbia, Canada.
⁸ Department of Medicine, University of British Columbia, Vancouver, British Columbia, Canada.
⁹ Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, British Columbia, Canada; Vancouver General Hospital, Vancouver, British Columbia, Canada; Pancreas Centre BC, Vancouver, British Columbia, Canada. Electronic address: [email protected].
¹⁰ School of Biomedical Engineering, University of British Columbia, Vancouver, British Columbia, Canada; Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, British Columbia, Canada. Electronic address: [email protected].

PMID: 39222907
DOI: 10.1016/j.ajpath.2024.08.006

Abstract

Delayed diagnosis and treatment resistance result in high pancreatic ductal adenocarcinoma (PDAC) mortality rates. Identifying molecular subtypes can improve treatment, but current methods are costly and time-consuming. In this study, deep learning models were used to identify histologic features that classify PDAC molecular subtypes based on routine hematoxylin-eosin-stained histopathologic slides. A total of 97 histopathology slides associated with resectable PDAC from The Cancer Genome Atlas project were used to train a deep learning model and test the performance on 44 needle biopsy material (110 slides) from a local annotated patient cohort. The model achieved balanced accuracy of 96.19% and 83.03% in identifying the classical and basal subtypes of PDAC in The Cancer Genome Atlas and the local cohort, respectively. This study provides a promising method to cost-effectively and rapidly classify PDAC molecular subtypes based on routine hematoxylin-eosin-stained slides, potentially leading to more effective clinical management of this disease.

MeSH terms

Carcinoma, Pancreatic Ductal* / classification
Carcinoma, Pancreatic Ductal* / diagnosis
Carcinoma, Pancreatic Ductal* / genetics
Carcinoma, Pancreatic Ductal* / pathology
Deep Learning*
Humans
Pancreatic Neoplasms* / classification
Pancreatic Neoplasms* / diagnosis
Pancreatic Neoplasms* / genetics
Pancreatic Neoplasms* / pathology