A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk

Abstract Breast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for est...

Full description

Saved in:
Bibliographic Details
Main Authors: Manu Goyal, Jonathan D. Marotti, Adrienne A. Workman, Graham M. Tooker, Seth K. Ramin, Elaine P. Kuhn, Mary D. Chamberlin, Roberta M. diFlorio-Alexander, Saeed Hassanpour
Format: Article
Language:English
Published: Nature Portfolio 2024-10-01
Series:npj Breast Cancer
Online Access:https://doi.org/10.1038/s41523-024-00700-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181872558014464
author Manu Goyal
Jonathan D. Marotti
Adrienne A. Workman
Graham M. Tooker
Seth K. Ramin
Elaine P. Kuhn
Mary D. Chamberlin
Roberta M. diFlorio-Alexander
Saeed Hassanpour
author_facet Manu Goyal
Jonathan D. Marotti
Adrienne A. Workman
Graham M. Tooker
Seth K. Ramin
Elaine P. Kuhn
Mary D. Chamberlin
Roberta M. diFlorio-Alexander
Saeed Hassanpour
author_sort Manu Goyal
collection DOAJ
description Abstract Breast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for estrogen receptor positive/HER2 negative breast cancer that guides therapeutic strategies; however, such tests can be expensive, delay care, and are not widely available. The aim of this study was to develop a multi-model approach integrating the analysis of whole-slide images and clinicopathologic data to predict their associated breast cancer recurrence risks and categorize these patients into two risk groups according to the predicted score: low-risk and high-risk. The proposed novel methodology uses convolutional neural networks for feature extraction and vision transformers for contextual aggregation, complemented by a logistic regression model that analyzes clinicopathologic data for classification into two risk categories. This method was trained and tested on 956 hematoxylin and eosin-stained whole-slide images of 950 ER+/HER2− breast cancer patients with corresponding clinicopathological features that had prior Oncotype DX testing. The model’s performance was evaluated using an internal test set of 192 patients from Dartmouth Health and an external test set of 405 patients from the University of Chicago. The multi-model approach achieved an AUC of 0.91 (95% CI: 0.87–0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78–0.89) on the external cohort for predicting low- and high-breast cancer recurrence risk categories based on the Oncotype DX recurrence score. With further validation, the proposed methodology could provide an alternative to assist clinicians in personalizing treatment for breast cancer patients and potentially improving their outcomes.
format Article
id doaj-art-4aec1dd558254a0ead2e78cc0bb20ed7
institution OA Journals
issn 2374-4677
language English
publishDate 2024-10-01
publisher Nature Portfolio
record_format Article
series npj Breast Cancer
spelling doaj-art-4aec1dd558254a0ead2e78cc0bb20ed72025-08-20T02:17:48ZengNature Portfolionpj Breast Cancer2374-46772024-10-011011910.1038/s41523-024-00700-zA multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence riskManu Goyal0Jonathan D. Marotti1Adrienne A. Workman2Graham M. Tooker3Seth K. Ramin4Elaine P. Kuhn5Mary D. Chamberlin6Roberta M. diFlorio-Alexander7Saeed Hassanpour8Department of Biomedical Data Science, Dartmouth CollegeDepartment of Pathology and Laboratory Medicine, Dartmouth HealthDepartment of Pathology and Laboratory Medicine, Dartmouth HealthDepartment of Radiology, Dartmouth HealthGeisel School of Medicine, Dartmouth CollegeGeisel School of Medicine, Dartmouth CollegeDepartment of Medicine, Dartmouth HealthDepartment of Radiology, Dartmouth HealthDepartment of Biomedical Data Science, Dartmouth CollegeAbstract Breast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for estrogen receptor positive/HER2 negative breast cancer that guides therapeutic strategies; however, such tests can be expensive, delay care, and are not widely available. The aim of this study was to develop a multi-model approach integrating the analysis of whole-slide images and clinicopathologic data to predict their associated breast cancer recurrence risks and categorize these patients into two risk groups according to the predicted score: low-risk and high-risk. The proposed novel methodology uses convolutional neural networks for feature extraction and vision transformers for contextual aggregation, complemented by a logistic regression model that analyzes clinicopathologic data for classification into two risk categories. This method was trained and tested on 956 hematoxylin and eosin-stained whole-slide images of 950 ER+/HER2− breast cancer patients with corresponding clinicopathological features that had prior Oncotype DX testing. The model’s performance was evaluated using an internal test set of 192 patients from Dartmouth Health and an external test set of 405 patients from the University of Chicago. The multi-model approach achieved an AUC of 0.91 (95% CI: 0.87–0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78–0.89) on the external cohort for predicting low- and high-breast cancer recurrence risk categories based on the Oncotype DX recurrence score. With further validation, the proposed methodology could provide an alternative to assist clinicians in personalizing treatment for breast cancer patients and potentially improving their outcomes.https://doi.org/10.1038/s41523-024-00700-z
spellingShingle Manu Goyal
Jonathan D. Marotti
Adrienne A. Workman
Graham M. Tooker
Seth K. Ramin
Elaine P. Kuhn
Mary D. Chamberlin
Roberta M. diFlorio-Alexander
Saeed Hassanpour
A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk
npj Breast Cancer
title A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk
title_full A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk
title_fullStr A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk
title_full_unstemmed A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk
title_short A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk
title_sort multi model approach integrating whole slide imaging and clinicopathologic features to predict breast cancer recurrence risk
url https://doi.org/10.1038/s41523-024-00700-z
work_keys_str_mv AT manugoyal amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT jonathandmarotti amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT adrienneaworkman amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT grahammtooker amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT sethkramin amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT elainepkuhn amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT marydchamberlin amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT robertamdiflorioalexander amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT saeedhassanpour amultimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT manugoyal multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT jonathandmarotti multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT adrienneaworkman multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT grahammtooker multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT sethkramin multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT elainepkuhn multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT marydchamberlin multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT robertamdiflorioalexander multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk
AT saeedhassanpour multimodelapproachintegratingwholeslideimagingandclinicopathologicfeaturestopredictbreastcancerrecurrencerisk