Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy

ObjectivesAccurate assessment of NAC efficacy is crucial for determining appropriate surgical strategies and guiding the extent of surgical resection in breast cancer. Therefore, this study aimed to design an integrated predictive model combining ultrasound imaging, deep learning features, and clini...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu Tenghui, Liu Xinyi, Si Ziyi, Zhang Yanting, Ma Ziqian, Zhu Yiwen, Gan Ling
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2025.1525285/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850131134435819520
author Wu Tenghui
Liu Xinyi
Si Ziyi
Zhang Yanting
Ma Ziqian
Zhu Yiwen
Gan Ling
author_facet Wu Tenghui
Liu Xinyi
Si Ziyi
Zhang Yanting
Ma Ziqian
Zhu Yiwen
Gan Ling
author_sort Wu Tenghui
collection DOAJ
description ObjectivesAccurate assessment of NAC efficacy is crucial for determining appropriate surgical strategies and guiding the extent of surgical resection in breast cancer. Therefore, this study aimed to design an integrated predictive model combining ultrasound imaging, deep learning features, and clinical characteristics to predict pCR in breast cancer patients undergoing NAC.MethodsA retrospective study was conducted, including 643 pathologically confirmed breast cancer patients who underwent NAC between January 2022 to February 2024 from two institutions (Center 1: 372 cases; Center 2: 271 cases). Ultrasound images before and after NAC were collected for each patient. A total of 2,920 radiomics features and 4,096 deep learning features were extracted from the ultrasound images. Multiple machine learning algorithms were employed to model and validate the diagnostic performance of different types of features. Finally, clinical data, radiomics, and deep learning features were integrated to form a fusion model, which was evaluated using receiver operating characteristic (ROC) analysis.ResultsThe combined model achieved the highest predictive performance for pathological complete response (pCR) across both cohorts. In the internal validation cohort, it reached an accuracy of 0.892 (95% CI: 0.862–0.912) and an AUC of 0.901 (95% CI: 0.854–0.948). In the external cohort, it maintained strong performance with an accuracy of 0.857 (95% CI: 0.822–0.928) and an AUC of 0.891 (95% CI: 0.848–0.934), significantly outperforming the individual models (DeLong test, p < 0.01).The deep learning model showed solid performance with accuracies of 0.875 and 0.833 in the internal and external cohorts, respectively, and AUCs of 0.870 and 0.874. The radiomics model displayed moderate accuracy and AUC in both cohorts, while the clinical model showed the lowest predictive capability among the models, with accuracy and AUC values around 0.67 in both cohorts.ConclusionsThe combined model, integrating clinical, radiomics, and deep learning features, demonstrated superior predictive accuracy for pCR following neoadjuvant chemotherapy (NAC) in breast cancer patients, outperforming individual models. This integrated approach highlights the value of combining diverse data types to improve prediction, offering a promising tool for guiding NAC response assessment and personalized treatment planning.
format Article
id doaj-art-e05e094c927f40a4ba59c26cc89ec5ca
institution OA Journals
issn 2234-943X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Oncology
spelling doaj-art-e05e094c927f40a4ba59c26cc89ec5ca2025-08-20T02:32:30ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-06-011510.3389/fonc.2025.15252851525285Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapyWu Tenghui0Liu Xinyi1Si Ziyi2Zhang Yanting3Ma Ziqian4Zhu Yiwen5Gan Ling6Department of Nuclear Medicine, Xiangyang No. 1 People’s Hospital, Hubei University of Medicine, Xiangyang, ChinaDepartment of Ultrasound, Xiangyang No.1 People’s Hospital, Hubei University of Medicine, Xiangyang, ChinaDepartment of Ultrasound, Xiangyang No.1 People’s Hospital, Hubei University of Medicine, Xiangyang, ChinaDepartment of Ultrasound, Xiangyang No.1 People’s Hospital, Hubei University of Medicine, Xiangyang, ChinaDepartment of Oncology, The People’s Hospital of Zouping City, Zouping, ChinaDepartment of Ultrasound, Xiangyang No.1 People’s Hospital, Hubei University of Medicine, Xiangyang, ChinaDepartment of Ultrasound, Xiangyang No.1 People’s Hospital, Hubei University of Medicine, Xiangyang, ChinaObjectivesAccurate assessment of NAC efficacy is crucial for determining appropriate surgical strategies and guiding the extent of surgical resection in breast cancer. Therefore, this study aimed to design an integrated predictive model combining ultrasound imaging, deep learning features, and clinical characteristics to predict pCR in breast cancer patients undergoing NAC.MethodsA retrospective study was conducted, including 643 pathologically confirmed breast cancer patients who underwent NAC between January 2022 to February 2024 from two institutions (Center 1: 372 cases; Center 2: 271 cases). Ultrasound images before and after NAC were collected for each patient. A total of 2,920 radiomics features and 4,096 deep learning features were extracted from the ultrasound images. Multiple machine learning algorithms were employed to model and validate the diagnostic performance of different types of features. Finally, clinical data, radiomics, and deep learning features were integrated to form a fusion model, which was evaluated using receiver operating characteristic (ROC) analysis.ResultsThe combined model achieved the highest predictive performance for pathological complete response (pCR) across both cohorts. In the internal validation cohort, it reached an accuracy of 0.892 (95% CI: 0.862–0.912) and an AUC of 0.901 (95% CI: 0.854–0.948). In the external cohort, it maintained strong performance with an accuracy of 0.857 (95% CI: 0.822–0.928) and an AUC of 0.891 (95% CI: 0.848–0.934), significantly outperforming the individual models (DeLong test, p < 0.01).The deep learning model showed solid performance with accuracies of 0.875 and 0.833 in the internal and external cohorts, respectively, and AUCs of 0.870 and 0.874. The radiomics model displayed moderate accuracy and AUC in both cohorts, while the clinical model showed the lowest predictive capability among the models, with accuracy and AUC values around 0.67 in both cohorts.ConclusionsThe combined model, integrating clinical, radiomics, and deep learning features, demonstrated superior predictive accuracy for pCR following neoadjuvant chemotherapy (NAC) in breast cancer patients, outperforming individual models. This integrated approach highlights the value of combining diverse data types to improve prediction, offering a promising tool for guiding NAC response assessment and personalized treatment planning.https://www.frontiersin.org/articles/10.3389/fonc.2025.1525285/fullultrasounddeep learningbreast cancerneoadjuvant chemotherapyradiomics
spellingShingle Wu Tenghui
Liu Xinyi
Si Ziyi
Zhang Yanting
Ma Ziqian
Zhu Yiwen
Gan Ling
Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy
Frontiers in Oncology
ultrasound
deep learning
breast cancer
neoadjuvant chemotherapy
radiomics
title Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy
title_full Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy
title_fullStr Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy
title_full_unstemmed Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy
title_short Combination of ultrasound-based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy
title_sort combination of ultrasound based radiomics and deep learning with clinical data to predict response in breast cancer patients treated with neoadjuvant chemotherapy
topic ultrasound
deep learning
breast cancer
neoadjuvant chemotherapy
radiomics
url https://www.frontiersin.org/articles/10.3389/fonc.2025.1525285/full
work_keys_str_mv AT wutenghui combinationofultrasoundbasedradiomicsanddeeplearningwithclinicaldatatopredictresponseinbreastcancerpatientstreatedwithneoadjuvantchemotherapy
AT liuxinyi combinationofultrasoundbasedradiomicsanddeeplearningwithclinicaldatatopredictresponseinbreastcancerpatientstreatedwithneoadjuvantchemotherapy
AT siziyi combinationofultrasoundbasedradiomicsanddeeplearningwithclinicaldatatopredictresponseinbreastcancerpatientstreatedwithneoadjuvantchemotherapy
AT zhangyanting combinationofultrasoundbasedradiomicsanddeeplearningwithclinicaldatatopredictresponseinbreastcancerpatientstreatedwithneoadjuvantchemotherapy
AT maziqian combinationofultrasoundbasedradiomicsanddeeplearningwithclinicaldatatopredictresponseinbreastcancerpatientstreatedwithneoadjuvantchemotherapy
AT zhuyiwen combinationofultrasoundbasedradiomicsanddeeplearningwithclinicaldatatopredictresponseinbreastcancerpatientstreatedwithneoadjuvantchemotherapy
AT ganling combinationofultrasoundbasedradiomicsanddeeplearningwithclinicaldatatopredictresponseinbreastcancerpatientstreatedwithneoadjuvantchemotherapy