The result prediction of fluorescence in situ hybridization for breast cancer patients based on machine learning and deep learning models - a multicenter study

Q: What is the primary goal of this study?

To develop and validate a multicenter ultrasound-based model that predicts FISH results in HER2 (2+) breast cancer patients, supporting clinical decision-making with a convenient and cost-effective tool.

Q: Which model performed best and how was performance evaluated?

The fusion model combining ViT and radiomics signatures outperformed individual models across training, test, and external validation cohorts. Performance was evaluated using AUC, with the DeLong test for model comparison.

Sep 23, 2026

Uploaded by Riley West

Objective focuses on building and validating a multicenter ultrasound-based predictive model for fluorescence in situ hybridization (FISH) outcomes in HER2 (2+) breast cancer patients, targeting convenient, cost-effective decision support. A retrospective cohort includes 5,888 patients from six institutions. Ultrasound radiomics features are extracted with PyRadiomics and deep learning features are learned using a Vision Transformer (ViT); LASSO selects features, multiple ML models are trained, compared with AUC using the DeLong test, and assessed across training, test, and external validation cohorts.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Objective

Materials and methods

Results

Conclusion

Introduction

Jiang et al. Cancer Imaging (2026) 26:52 [https://doi.org/10.1186/s40644-026-01015-x](https://doi.org/10.1186/s40644-026-01015-x) Cancer Imaging RESEARCH Open Access The result prediction of fluorescence in situ hybridization for breast cancer patients based on machine learning and deep learning models: a multicenter study Cong Jiang1†, Dong Chen2†, Xiao Yu3†, Shentao Zhang4†, Yuting Xiu1†, Ningbin Luo5, Jingjing Wu5, Xuefang Zhang6, Man Chen1, Dechun Yang1, Ziyu Zhu7*, Yuanxi Huang8*, Shipeng Ning9* and Shicong Tang1* Abstract Objective To develop and validate a multicenter ultrasound-based predictive model for fluorescence in situ hybridization (FISH) results in HER2 (2+) breast cancer patients, aiming to provide a convenient and cost-effective tool to support clinical decision-making. Materials and methods In this retrospective multicenter study, 5,888 breast cancer patients from six institutions were included. Radiomics features were extracted from ultrasound images using PyRadiomics, and deep learning features were obtained using a Vision Transformer (ViT) . Feature selection was performed using least absolute shrinkage and selection operator (LASSO) regression. Multiple machine learning models were developed, and their performance was evaluated with the area under the curve (AUC) . The DeLong test was used for model comparison. Results The proportion of FISH-positive cases ranged from 9. 7% to 20. 0% across the six centers. The fusion model combining ViT and radiomics signatures consistently outperformed the individual models in the training, test, and all external validation cohorts. The AUCs ofthe fusion model were 0.887 in the training cohort, 0.799 in the test cohort, and 0 . 763, 0 . 796, 0 . 734, and 0.632 in the four external validation cohorts, respectively (all P < 0. 05) . Conclusion The proposed ultrasound-based fusion model enables accurate prediction of FISH assay results in HER2 (2+) breast cancer patients and may serve as a reliable decision-support tool to reduce unnecessary FISH testing in clinical practice. †Cong Jiang, Dong Chen, Xiao Yu, Shentao Zhang andYuting Xiu contributed equally to this work. *Correspondence: Ziyu Zhu [243823456@qq.com](243823456@qq.com)[ ](243823456@qq.com)Yuanxi Huang [rxwk@163.com](rxwk@163.com) Shipeng Ning [nspdoctor@sr.gxmu.edu.cn](nspdoctor@sr.gxmu.edu.cn)[ ](nspdoctor@sr.gxmu.edu.cn)Shicong Tang [tang_shicong@126.com](tang_shicong@126.com) Full list of author information is available at the end of the article © The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creati](http://creati)[vecommons.org/licenses/by-nc-nd/4.0/](vecommons.org/licenses/by-nc-nd/4.0/.)[.](vecommons.org/licenses/by-nc-nd/4.0/.) Jiang et al. Cancer Imaging (2026) 26:52 Page 2 of 13 Keywords FISH, ViT, Breast cancer, Machine learning Introduction Breast cancer is one of the most common cancers and the leading cause of cancer-related mortality among women worldwide [1]. Based on hematoxylin-eosin (H&E) staining of the tissue and his

FAQs

What is the primary goal of this study?

To develop and validate a multicenter ultrasound-based model that predicts FISH results in HER2 (2+) breast cancer patients, supporting clinical decision-making with a convenient and cost-effective tool.

How were ultrasound images and features used to build the models?

Radiomics features were extracted from ultrasound images using PyRadiomics, while deep learning features were obtained using a Vision Transformer (ViT). Feature selection used LASSO regression.

Which model performed best and how was performance evaluated?

The fusion model combining ViT and radiomics signatures outperformed individual models across training, test, and external validation cohorts. Performance was evaluated using AUC, with the DeLong test for model comparison.

Sep 23, 2026

Uploaded by Riley West