Integrating radiomics into predictive models for low nuclear grade DCIS using machine learning

Abstract Predicting low nuclear grade DCIS before surgery can improve treatment choices and patient care, thereby reducing unnecessary treatment. Due to the high heterogeneity of DCIS and the limitations of biopsies in fully characterizing tumors, current diagnostic methods relying on invasive biops...

Full description

Saved in:
Bibliographic Details
Main Authors: Yimin Wu, Daojing Xu, Zongyu Zha, Li Gu, Jieqing Chen, Jiagui Fang, Ziyang Dou, Pingyang Zhang, Chaoxue Zhang, Junli Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92080-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850252098579464192
author Yimin Wu
Daojing Xu
Zongyu Zha
Li Gu
Jieqing Chen
Jiagui Fang
Ziyang Dou
Pingyang Zhang
Chaoxue Zhang
Junli Wang
author_facet Yimin Wu
Daojing Xu
Zongyu Zha
Li Gu
Jieqing Chen
Jiagui Fang
Ziyang Dou
Pingyang Zhang
Chaoxue Zhang
Junli Wang
author_sort Yimin Wu
collection DOAJ
description Abstract Predicting low nuclear grade DCIS before surgery can improve treatment choices and patient care, thereby reducing unnecessary treatment. Due to the high heterogeneity of DCIS and the limitations of biopsies in fully characterizing tumors, current diagnostic methods relying on invasive biopsies face challenges. Here, we developed an ensemble machine learning model to assist in the preoperative diagnosis of low nuclear grade DCIS. We integrated preoperative clinical data, ultrasound images, mammography images, and Radiomic scores from 241 DCIS cases. The ensemble model, based on Elastic Net, Generalized Linear Models with Boosting (glmboost), and Ranger, improved the ability to predict low nuclear grade DCIS preoperatively, achieving an AUC of 0.92 on the validation set, outperforming the model using clinical data alone. The comprehensive model also demonstrated notable enhancements in integrated discrimination improvement and net reclassification improvement (p < 0.001). Furthermore, the Radiomic ensemble model effectively stratified DCIS patients by risk based on disease-free survival. Our findings emphasize the importance of integrating Radiomic into DCIS prediction models, offering fresh perspectives for personalized treatment and clinical management of DCIS.
format Article
id doaj-art-d65cb13fca1c48ff830508a48e3946e3
institution OA Journals
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d65cb13fca1c48ff830508a48e3946e32025-08-20T01:57:44ZengNature PortfolioScientific Reports2045-23222025-03-0115111410.1038/s41598-025-92080-yIntegrating radiomics into predictive models for low nuclear grade DCIS using machine learningYimin Wu0Daojing Xu1Zongyu Zha2Li Gu3Jieqing Chen4Jiagui Fang5Ziyang Dou6Pingyang Zhang7Chaoxue Zhang8Junli Wang9Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Department of Echocardiography, Nanjing First Hospital, Nanjing Medical UniversityDepartment of Ultrasound, The First Affiliated Hospital of Anhui Medical UniversityDepartment of Ultrasound, WuHu Hospital, East China Normal University (The Second People’s Hospital, WuHu)Abstract Predicting low nuclear grade DCIS before surgery can improve treatment choices and patient care, thereby reducing unnecessary treatment. Due to the high heterogeneity of DCIS and the limitations of biopsies in fully characterizing tumors, current diagnostic methods relying on invasive biopsies face challenges. Here, we developed an ensemble machine learning model to assist in the preoperative diagnosis of low nuclear grade DCIS. We integrated preoperative clinical data, ultrasound images, mammography images, and Radiomic scores from 241 DCIS cases. The ensemble model, based on Elastic Net, Generalized Linear Models with Boosting (glmboost), and Ranger, improved the ability to predict low nuclear grade DCIS preoperatively, achieving an AUC of 0.92 on the validation set, outperforming the model using clinical data alone. The comprehensive model also demonstrated notable enhancements in integrated discrimination improvement and net reclassification improvement (p < 0.001). Furthermore, the Radiomic ensemble model effectively stratified DCIS patients by risk based on disease-free survival. Our findings emphasize the importance of integrating Radiomic into DCIS prediction models, offering fresh perspectives for personalized treatment and clinical management of DCIS.https://doi.org/10.1038/s41598-025-92080-yDuctal carcinoma in situMachine learningRadiomicUltrasoundMammography
spellingShingle Yimin Wu
Daojing Xu
Zongyu Zha
Li Gu
Jieqing Chen
Jiagui Fang
Ziyang Dou
Pingyang Zhang
Chaoxue Zhang
Junli Wang
Integrating radiomics into predictive models for low nuclear grade DCIS using machine learning
Scientific Reports
Ductal carcinoma in situ
Machine learning
Radiomic
Ultrasound
Mammography
title Integrating radiomics into predictive models for low nuclear grade DCIS using machine learning
title_full Integrating radiomics into predictive models for low nuclear grade DCIS using machine learning
title_fullStr Integrating radiomics into predictive models for low nuclear grade DCIS using machine learning
title_full_unstemmed Integrating radiomics into predictive models for low nuclear grade DCIS using machine learning
title_short Integrating radiomics into predictive models for low nuclear grade DCIS using machine learning
title_sort integrating radiomics into predictive models for low nuclear grade dcis using machine learning
topic Ductal carcinoma in situ
Machine learning
Radiomic
Ultrasound
Mammography
url https://doi.org/10.1038/s41598-025-92080-y
work_keys_str_mv AT yiminwu integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT daojingxu integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT zongyuzha integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT ligu integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT jieqingchen integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT jiaguifang integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT ziyangdou integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT pingyangzhang integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT chaoxuezhang integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning
AT junliwang integratingradiomicsintopredictivemodelsforlownucleargradedcisusingmachinelearning