Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features

Abstract Background In HR+/HER2- early breast cancer (EBC) patients, approximately one-third of stage II and 50% of stage III patients experience recurrence, with poor outcomes after recurrence. Given that these patients commonly undergo adjuvant chemo-endocrine therapy (C-ET), accurately predicting...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyan Wu, Yiman Li, Jilong Chen, Jie Chen, Wenchuan Zhang, Xunxi Lu, Xiaorong Zhong, Min Zhu, Yuhao Yi, Hong Bu
Format: Article
Language:English
Published: BMC 2025-03-01
Series:Breast Cancer Research
Subjects:
Online Access:https://doi.org/10.1186/s13058-025-01968-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850065283182493696
author Xiaoyan Wu
Yiman Li
Jilong Chen
Jie Chen
Wenchuan Zhang
Xunxi Lu
Xiaorong Zhong
Min Zhu
Yuhao Yi
Hong Bu
author_facet Xiaoyan Wu
Yiman Li
Jilong Chen
Jie Chen
Wenchuan Zhang
Xunxi Lu
Xiaorong Zhong
Min Zhu
Yuhao Yi
Hong Bu
author_sort Xiaoyan Wu
collection DOAJ
description Abstract Background In HR+/HER2- early breast cancer (EBC) patients, approximately one-third of stage II and 50% of stage III patients experience recurrence, with poor outcomes after recurrence. Given that these patients commonly undergo adjuvant chemo-endocrine therapy (C-ET), accurately predicting the recurrence risk is crucial for optimizing treatment strategies and improving patient outcomes. Methods We collected postoperative histopathological slides from 1095 HR+/HER2- EBC who received C-ET and were followed for more than five years at West China Hospital, Sichuan University. Two deep learning pipelines were developed and validated: ACMIL-based and CLAM-based. Both pipelines, designed to predict recurrence risk post-treatment, were based on pretrained feature encoders and multi-instance learning with attention mechanisms. Model performance was evaluated using a five-fold cross-validation approach and externally validated on HR+/HER2- EBC patients from the TCGA cohort. Results Both ACMIL-based and CLAM-based pipelines performed well in predicting recurrence risk, with UNI-ACMIL demonstrating superior performance across multiple metrics. The average area under the curve (AUC) for the UNI-ACMIL pipeline in the five-fold cross-validation test set was 0.86 ± 0.02, and 0.80 ± 0.04 in the TCGA cohort. In the five-fold cross-validation test sets, effectively stratified patients into high-risk and low-risk groups, demonstrating significant prognostic differences. Hazard ratios for recurrence-free survival (RFS) ranged from 5.32 (95% CI 1.86-15.12) to 15.16 (95% CI 3.61-63.56). Moreover, among six different multimodal recurrence risk models, the WSI-based risk score was identified as the most significant contributor. Conclusion Our multimodal recurrence risk prediction model is a practical and reliable tool that enhances the predictive power of existing systems relying solely on clinicopathological parameters. It offers improved recurrence risk prediction for HR+/HER2- EBC patients following adjuvant C-ET, supporting personalized treatment and better patient outcomes.
format Article
id doaj-art-57d49bf45cbb49ecb826b6f6be5d1c17
institution DOAJ
issn 1465-542X
language English
publishDate 2025-03-01
publisher BMC
record_format Article
series Breast Cancer Research
spelling doaj-art-57d49bf45cbb49ecb826b6f6be5d1c172025-08-20T02:49:02ZengBMCBreast Cancer Research1465-542X2025-03-0127111310.1186/s13058-025-01968-0Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological featuresXiaoyan Wu0Yiman Li1Jilong Chen2Jie Chen3Wenchuan Zhang4Xunxi Lu5Xiaorong Zhong6Min Zhu7Yuhao Yi8Hong Bu9Department of Pathology, West China Hospital, Sichuan UniversityCollege of Computer Science, Sichuan UniversityCollege of Computer Science, Sichuan UniversityInstitute of Clinical Pathology, West China Hospital, Sichuan UniversityDepartment of Pathology, West China Hospital, Sichuan UniversityDepartment of Pathology, West China Hospital, Sichuan UniversityInstitute for Breast Health Medicine, Cancer Center, Breast Center, West China Hospital, Sichuan UniversityCollege of Computer Science, Sichuan UniversityInstitute of Clinical Pathology, West China Hospital, Sichuan UniversityDepartment of Pathology, West China Hospital, Sichuan UniversityAbstract Background In HR+/HER2- early breast cancer (EBC) patients, approximately one-third of stage II and 50% of stage III patients experience recurrence, with poor outcomes after recurrence. Given that these patients commonly undergo adjuvant chemo-endocrine therapy (C-ET), accurately predicting the recurrence risk is crucial for optimizing treatment strategies and improving patient outcomes. Methods We collected postoperative histopathological slides from 1095 HR+/HER2- EBC who received C-ET and were followed for more than five years at West China Hospital, Sichuan University. Two deep learning pipelines were developed and validated: ACMIL-based and CLAM-based. Both pipelines, designed to predict recurrence risk post-treatment, were based on pretrained feature encoders and multi-instance learning with attention mechanisms. Model performance was evaluated using a five-fold cross-validation approach and externally validated on HR+/HER2- EBC patients from the TCGA cohort. Results Both ACMIL-based and CLAM-based pipelines performed well in predicting recurrence risk, with UNI-ACMIL demonstrating superior performance across multiple metrics. The average area under the curve (AUC) for the UNI-ACMIL pipeline in the five-fold cross-validation test set was 0.86 ± 0.02, and 0.80 ± 0.04 in the TCGA cohort. In the five-fold cross-validation test sets, effectively stratified patients into high-risk and low-risk groups, demonstrating significant prognostic differences. Hazard ratios for recurrence-free survival (RFS) ranged from 5.32 (95% CI 1.86-15.12) to 15.16 (95% CI 3.61-63.56). Moreover, among six different multimodal recurrence risk models, the WSI-based risk score was identified as the most significant contributor. Conclusion Our multimodal recurrence risk prediction model is a practical and reliable tool that enhances the predictive power of existing systems relying solely on clinicopathological parameters. It offers improved recurrence risk prediction for HR+/HER2- EBC patients following adjuvant C-ET, supporting personalized treatment and better patient outcomes.https://doi.org/10.1186/s13058-025-01968-0HR+/HER2- early breast cancerRecurrence riskAdjuvant chemo-endocrine therapyDeep learning pipelinesPathology image
spellingShingle Xiaoyan Wu
Yiman Li
Jilong Chen
Jie Chen
Wenchuan Zhang
Xunxi Lu
Xiaorong Zhong
Min Zhu
Yuhao Yi
Hong Bu
Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features
Breast Cancer Research
HR+/HER2- early breast cancer
Recurrence risk
Adjuvant chemo-endocrine therapy
Deep learning pipelines
Pathology image
title Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features
title_full Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features
title_fullStr Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features
title_full_unstemmed Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features
title_short Multimodal recurrence risk prediction model for HR+/HER2- early breast cancer following adjuvant chemo-endocrine therapy: integrating pathology image and clinicalpathological features
title_sort multimodal recurrence risk prediction model for hr her2 early breast cancer following adjuvant chemo endocrine therapy integrating pathology image and clinicalpathological features
topic HR+/HER2- early breast cancer
Recurrence risk
Adjuvant chemo-endocrine therapy
Deep learning pipelines
Pathology image
url https://doi.org/10.1186/s13058-025-01968-0
work_keys_str_mv AT xiaoyanwu multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT yimanli multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT jilongchen multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT jiechen multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT wenchuanzhang multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT xunxilu multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT xiaorongzhong multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT minzhu multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT yuhaoyi multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures
AT hongbu multimodalrecurrenceriskpredictionmodelforhrher2earlybreastcancerfollowingadjuvantchemoendocrinetherapyintegratingpathologyimageandclinicalpathologicalfeatures