An immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks

Abstract Colorectal cancer (CRC) represents a major global disease burden with nearly 1 million cancer-related deaths annually. TNM staging has served as the foundation for predicting patient prognosis, despite variation across staging groups. The consensus molecular subtype (CMS) is a transcriptome...

Full description

Saved in:
Bibliographic Details
Main Authors: Tuomas Kaprio, Jaana Hagström, Jussi Kasurinen, Ioannis Gkekas, Sofia Edin, Ines Beilmann-Lehtonen, Karin Strigård, Richard Palmqvist, Ulf Gunnarson, Camilla Böckelman, Caj Haglund
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03618-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688142373715968
author Tuomas Kaprio
Jaana Hagström
Jussi Kasurinen
Ioannis Gkekas
Sofia Edin
Ines Beilmann-Lehtonen
Karin Strigård
Richard Palmqvist
Ulf Gunnarson
Camilla Böckelman
Caj Haglund
author_facet Tuomas Kaprio
Jaana Hagström
Jussi Kasurinen
Ioannis Gkekas
Sofia Edin
Ines Beilmann-Lehtonen
Karin Strigård
Richard Palmqvist
Ulf Gunnarson
Camilla Böckelman
Caj Haglund
author_sort Tuomas Kaprio
collection DOAJ
description Abstract Colorectal cancer (CRC) represents a major global disease burden with nearly 1 million cancer-related deaths annually. TNM staging has served as the foundation for predicting patient prognosis, despite variation across staging groups. The consensus molecular subtype (CMS) is a transcriptome-based system classifying CRC tumors into four subtypes with different characteristics: CMS1 (immune), CMS2 (canonical), CMS3 (metabolic), and CMS4 (mesenchymal). Transcriptomics is too complex and expensive for clinical implementation; therefore, an immunohistochemical method is needed. The prognostic impact of the immunohistochemistry-based four CMS-like subtypes remains unclear. Due to the complexity and costs associated with transcriptomics, we developed an immunohistochemistry (IHC)-based method supported by convolutional neural networks (CNNs) to define subgroups that resemble CMS biological characteristics. Building on previous IHC-classifiers and incorporating β-catenin to refine differentiation between CMS2- and CMS3-like profiles, we categorized CRC tumors in a cohort of 538 patients. Classification was successful in 89.4% and 15.9% of tumors were classified as CMS1-like, 35.1% as CMS2-like, 38.7% as CMS3-like, and 11.7% as CMS4-like. CMS2-like patients exhibited the best overall survival (p = 0.018), including when local and metastasized disease were analyzed separately. Our method offers an accessible and clinically feasible CMS-inspired classification, although it does not serve as a replacement for transcriptomic CMS classification.
format Article
id doaj-art-2dfc9254345140dfa598ea67edddef26
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2dfc9254345140dfa598ea67edddef262025-08-20T03:22:07ZengNature PortfolioScientific Reports2045-23222025-05-0115111010.1038/s41598-025-03618-zAn immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networksTuomas Kaprio0Jaana Hagström1Jussi Kasurinen2Ioannis Gkekas3Sofia Edin4Ines Beilmann-Lehtonen5Karin Strigård6Richard Palmqvist7Ulf Gunnarson8Camilla Böckelman9Caj Haglund10Department of Surgery, University of Helsinki and Helsinki University HospitalDepartment of Pathology, University of Helsinki and Helsinki University HospitalDepartment of Pathology, University of Helsinki and Helsinki University HospitalDepartment of Surgical and Perioperative Sciences, Umeå UniversityDepartment of Medical Biosciences, Pathology, Umeå UniversityDepartment of Surgery, University of Helsinki and Helsinki University HospitalDepartment of Surgical and Perioperative Sciences, Umeå UniversityDepartment of Medical Biosciences, Pathology, Umeå UniversityDepartment of Surgical and Perioperative Sciences, Umeå UniversityDepartment of Surgery, University of Helsinki and Helsinki University HospitalDepartment of Surgery, University of Helsinki and Helsinki University HospitalAbstract Colorectal cancer (CRC) represents a major global disease burden with nearly 1 million cancer-related deaths annually. TNM staging has served as the foundation for predicting patient prognosis, despite variation across staging groups. The consensus molecular subtype (CMS) is a transcriptome-based system classifying CRC tumors into four subtypes with different characteristics: CMS1 (immune), CMS2 (canonical), CMS3 (metabolic), and CMS4 (mesenchymal). Transcriptomics is too complex and expensive for clinical implementation; therefore, an immunohistochemical method is needed. The prognostic impact of the immunohistochemistry-based four CMS-like subtypes remains unclear. Due to the complexity and costs associated with transcriptomics, we developed an immunohistochemistry (IHC)-based method supported by convolutional neural networks (CNNs) to define subgroups that resemble CMS biological characteristics. Building on previous IHC-classifiers and incorporating β-catenin to refine differentiation between CMS2- and CMS3-like profiles, we categorized CRC tumors in a cohort of 538 patients. Classification was successful in 89.4% and 15.9% of tumors were classified as CMS1-like, 35.1% as CMS2-like, 38.7% as CMS3-like, and 11.7% as CMS4-like. CMS2-like patients exhibited the best overall survival (p = 0.018), including when local and metastasized disease were analyzed separately. Our method offers an accessible and clinically feasible CMS-inspired classification, although it does not serve as a replacement for transcriptomic CMS classification.https://doi.org/10.1038/s41598-025-03618-zColorectal cancerImmunohistochemistryConsensus molecular subtypesPrognosisConvoluted neural network
spellingShingle Tuomas Kaprio
Jaana Hagström
Jussi Kasurinen
Ioannis Gkekas
Sofia Edin
Ines Beilmann-Lehtonen
Karin Strigård
Richard Palmqvist
Ulf Gunnarson
Camilla Böckelman
Caj Haglund
An immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks
Scientific Reports
Colorectal cancer
Immunohistochemistry
Consensus molecular subtypes
Prognosis
Convoluted neural network
title An immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks
title_full An immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks
title_fullStr An immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks
title_full_unstemmed An immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks
title_short An immunohistochemistry-based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks
title_sort immunohistochemistry based classification of colorectal cancer resembling the consensus molecular subtypes using convolutional neural networks
topic Colorectal cancer
Immunohistochemistry
Consensus molecular subtypes
Prognosis
Convoluted neural network
url https://doi.org/10.1038/s41598-025-03618-z
work_keys_str_mv AT tuomaskaprio animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT jaanahagstrom animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT jussikasurinen animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT ioannisgkekas animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT sofiaedin animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT inesbeilmannlehtonen animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT karinstrigard animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT richardpalmqvist animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT ulfgunnarson animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT camillabockelman animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT cajhaglund animmunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT tuomaskaprio immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT jaanahagstrom immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT jussikasurinen immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT ioannisgkekas immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT sofiaedin immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT inesbeilmannlehtonen immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT karinstrigard immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT richardpalmqvist immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT ulfgunnarson immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT camillabockelman immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks
AT cajhaglund immunohistochemistrybasedclassificationofcolorectalcancerresemblingtheconsensusmolecularsubtypesusingconvolutionalneuralnetworks