Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images

Classifying breast cancer molecular subtypes is crucial for tailoring treatment strategies. While immunohistochemistry (IHC) and gene expression profiling are standard methods for molecular subtyping, IHC can be subjective, and gene profiling is costly and not widely accessible in many regions. Prev...

Full description

Saved in:
Bibliographic Details
Main Authors: Masoud Tafavvoghi, Anders Sildnes, Mehrdad Rakaee, Nikita Shvetsov, Lars Ailo Bongo, Lill-Tove Rasmussen Busund, Kajsa Møllersen
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Journal of Pathology Informatics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S215335392400049X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849765421188644864
author Masoud Tafavvoghi
Anders Sildnes
Mehrdad Rakaee
Nikita Shvetsov
Lars Ailo Bongo
Lill-Tove Rasmussen Busund
Kajsa Møllersen
author_facet Masoud Tafavvoghi
Anders Sildnes
Mehrdad Rakaee
Nikita Shvetsov
Lars Ailo Bongo
Lill-Tove Rasmussen Busund
Kajsa Møllersen
author_sort Masoud Tafavvoghi
collection DOAJ
description Classifying breast cancer molecular subtypes is crucial for tailoring treatment strategies. While immunohistochemistry (IHC) and gene expression profiling are standard methods for molecular subtyping, IHC can be subjective, and gene profiling is costly and not widely accessible in many regions. Previous approaches have highlighted the potential application of deep learning models on hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) for molecular subtyping, but these efforts vary in their methods, datasets, and reported performance. In this work, we investigated whether H&E-stained WSIs could be solely leveraged to predict breast cancer molecular subtypes (luminal A, B, HER2-enriched, and Basal). We used 1433 WSIs of breast cancer in a two-step pipeline: first, classifying tumor and non-tumor tiles to use only the tumor regions for molecular subtyping; and second, employing a One-vs-Rest (OvR) strategy to train four binary OvR classifiers and aggregating their results using an eXtreme Gradient Boosting model. The pipeline was tested on 221 hold-out WSIs, achieving an F1 score of 0.95 for tumor vs non-tumor classification and a macro F1 score of 0.73 for molecular subtyping. Our findings suggest that, with further validation, supervised deep learning models could serve as supportive tools for molecular subtyping in breast cancer. Our codes are made available to facilitate ongoing research and development.
format Article
id doaj-art-93005a4b95ea4af69bc6c5805c67938c
institution DOAJ
issn 2153-3539
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Journal of Pathology Informatics
spelling doaj-art-93005a4b95ea4af69bc6c5805c67938c2025-08-20T03:04:51ZengElsevierJournal of Pathology Informatics2153-35392025-01-011610041010.1016/j.jpi.2024.100410Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide imagesMasoud Tafavvoghi0Anders Sildnes1Mehrdad Rakaee2Nikita Shvetsov3Lars Ailo Bongo4Lill-Tove Rasmussen Busund5Kajsa Møllersen6Department of Community Medicine, Uit The Arctic University of Norway, Tromsø, Norway; Corresponding author.Department of Computer Science, Uit The Arctic University of Norway, Tromsø, NorwayDepartment of Medical Biology, Uit The Arctic University of Norway, Tromsø, Norway; Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, USA; Department of Cancer Genetics, Oslo University Hospital, Oslo, NorwayDepartment of Computer Science, Uit The Arctic University of Norway, Tromsø, NorwayDepartment of Computer Science, Uit The Arctic University of Norway, Tromsø, NorwayDepartment of Medical Biology, Uit The Arctic University of Norway, Tromsø, Norway; Department of Clinical Pathology, University Hospital of North Norway, Tromsø, NorwayDepartment of Community Medicine, Uit The Arctic University of Norway, Tromsø, NorwayClassifying breast cancer molecular subtypes is crucial for tailoring treatment strategies. While immunohistochemistry (IHC) and gene expression profiling are standard methods for molecular subtyping, IHC can be subjective, and gene profiling is costly and not widely accessible in many regions. Previous approaches have highlighted the potential application of deep learning models on hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) for molecular subtyping, but these efforts vary in their methods, datasets, and reported performance. In this work, we investigated whether H&E-stained WSIs could be solely leveraged to predict breast cancer molecular subtypes (luminal A, B, HER2-enriched, and Basal). We used 1433 WSIs of breast cancer in a two-step pipeline: first, classifying tumor and non-tumor tiles to use only the tumor regions for molecular subtyping; and second, employing a One-vs-Rest (OvR) strategy to train four binary OvR classifiers and aggregating their results using an eXtreme Gradient Boosting model. The pipeline was tested on 221 hold-out WSIs, achieving an F1 score of 0.95 for tumor vs non-tumor classification and a macro F1 score of 0.73 for molecular subtyping. Our findings suggest that, with further validation, supervised deep learning models could serve as supportive tools for molecular subtyping in breast cancer. Our codes are made available to facilitate ongoing research and development.http://www.sciencedirect.com/science/article/pii/S215335392400049XBreast cancerClassificationDeep learningMolecular subtypesWhole-slide images
spellingShingle Masoud Tafavvoghi
Anders Sildnes
Mehrdad Rakaee
Nikita Shvetsov
Lars Ailo Bongo
Lill-Tove Rasmussen Busund
Kajsa Møllersen
Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images
Journal of Pathology Informatics
Breast cancer
Classification
Deep learning
Molecular subtypes
Whole-slide images
title Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images
title_full Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images
title_fullStr Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images
title_full_unstemmed Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images
title_short Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images
title_sort deep learning based classification of breast cancer molecular subtypes from h e whole slide images
topic Breast cancer
Classification
Deep learning
Molecular subtypes
Whole-slide images
url http://www.sciencedirect.com/science/article/pii/S215335392400049X
work_keys_str_mv AT masoudtafavvoghi deeplearningbasedclassificationofbreastcancermolecularsubtypesfromhewholeslideimages
AT anderssildnes deeplearningbasedclassificationofbreastcancermolecularsubtypesfromhewholeslideimages
AT mehrdadrakaee deeplearningbasedclassificationofbreastcancermolecularsubtypesfromhewholeslideimages
AT nikitashvetsov deeplearningbasedclassificationofbreastcancermolecularsubtypesfromhewholeslideimages
AT larsailobongo deeplearningbasedclassificationofbreastcancermolecularsubtypesfromhewholeslideimages
AT lilltoverasmussenbusund deeplearningbasedclassificationofbreastcancermolecularsubtypesfromhewholeslideimages
AT kajsamøllersen deeplearningbasedclassificationofbreastcancermolecularsubtypesfromhewholeslideimages