[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124423-en":3,"doc-seo-124423-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124423,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",7,"Healthcare","A dual-modality machine learning precision diagnostic model integrated radiomicsand proteomics for breast cancer","This original research builds a dual-modal machine learning precision diagnostic framework that integrates ultrasound radiomics with plasma proteomics to support accurate breast cancer diagnosis. Protein mass spectrometry and ultrasound data from TCGA, CPTAC, and a clinical cohort were combined to screen 10 plasma protein markers and 14 ultrasound radiomics features, then used to train a machine learning model. Results show strong discrimination by proteomics in primary screening, while single-protein and single-radiomics models show weaker benign–malignant separation. The combined dual-modal model achieves high diagnostic performance and improves accessibility and accuracy for stratified diagnosis of breast cancer.","TYPE Original Research PUBLISHED 06 November 2025 DOI 10.3389/fimmu.2025.1665459  \nOPEN ACCESS  \nEDITED BY  \nGiuseppe Palmieri,  \nUniversity of Sassari, Italy  \nREVIEWED BY  \nIshak Pacal,  \nI˘gdır Üniversitesi, Türkiye Michele Zanoletti,  \nNational Research Council (CNR), Italy  \n*CORRESPONDENCE  \nJunli Gao  \n gj[l_818@zuaa.zju.edu.cn](l_818@zuaa.zju.edu.cn)  \nZhenyu Wang  \n[wzyxshp@163.com](wzyxshp@163.com)  \n†These authors have contributed equally to this work  \nRECEIVED 14 July 2025  \nACCEPTED 24 October 2025  \nPUBLISHED 06 November 2025  \nCITATION  \nLi P, Liu Y, Liu R, Huang Y, Sun K, Yin K, Lu J, Li L, Zhang S, Tong CY, Liu J, Gao J and Wang Z (2025)  \nA dual-modality machine learning precision diagnostic model integrated radiomicsand proteomics for breast cancer.  \nFront. Immunol. 16:1665459 .  \ndoi: 10.3389/fimmu.2025.1665459  \nCOPYRIGHT  \n© 2025 Li, Liu, Liu, Huang, Sun, Yin, Lu, Li, Zhang, Tong, Liu, Gao and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nA dual-modality machine learning precision diagnostic model integrated radiomics and proteomics for breast cancer  \nPengping Li 1†, Yuan Liu 1†, Ren Liu 1,2†, Yuqin Huang 1, Ke Sun 1, Kexin Yin 1, Jiajia Lu 1, Lanqing Li 3, Shuirong Zhang 3,  \nClaire Y. Tong 4, Jiayi Liu 5, Junli Gao 3* and Zhenyu Wang 1,2*  \n1The First People’s Hospital of Xiaoshan District, Xiaoshan Affiliated Hospital of Wenzhou Medical University, Hangzhou, China, 2Zhejiang Chinese Medical University, Hangzhou, China, 3 Hangzhou Cosmos Wisdom Mass Spectrometry Center of Zhejiang University Medical School, Hangzhou, China, 4 Phillips Academy Andover, Boston, MA, United States, 5Salisbury School, Salisbury, MD, United States  \nBackground: This study aims to construct a dual-modal machine learning model that integrates ultrasound radiomics and plasma proteomics for the precise diagnosis of breast cancer.  \nMethods: Using a multi-source data integration strategy, 10 protein markers and 14 ultrasound radiomics features were screened from the TCGA, CPTAC databases, and the clinical cohort (including 60 healthy controls, 60 cases of benign breast diseases, and 60 cases of breast cancer) based on plasma protein mass spectrometry and ultrasound data. A dual-modal diagnostic model was constructed in combination with machine learning algorithms.  \nResults: The results showed that the protein marker detection model performed outstandingly in the primary screening of healthy people and breast diseases (with the highest AUC of 0 . 974) . Still, its diagnostic performance was limited in differentiating benign and malignant diseases (AUC\u003C0.8 under multiple algorithms) . The bi modal model demonstrated excellent performance (AUC = 0.938) in differentiating benign and malignant lesions, significantly outperforming the single proteomics model (AUC = 0.830) and the radiomics model (AUC = 0 . 841) .  \nConclusion: This study confirmed for the synergistic diagnostic value of plasma proteins and ultrasound images, providing a new strategy with both accuracy and accessibility for stratified diagnosis of breast cancer.  \nKEYWORDS  \nbreast cancer, proteomics, radiomics, machine learning, diagnosis model  \nFrontiers in Immunology 01 [frontiersin.org](frontiersin.org)  \n1 Introduction  \nBreast cancer is one of the most common malignant tumors in women. According to the 2024 China Cancer Report, the incidence rate (51.7%) of breast cancer is second only to lung cancer among female cancers, and its mortality rate (10.86%) ranks fifth (1) . Although significant progress has been made in treatment, precision detection remains a key ","cbCaipnWJCbgC9M8","https://ap.wps.com/l/cbCaipnWJCbgC9M8","pdf",3735290,1,14,"English","en",105,"# Introduction\n## Clinical diagnostic challenges and need for noninvasive techniques\n## Role of blood biomarkers and proteomics\n# Methods\n## Multi-source data integration and feature screening\n## Machine learning model construction\n# Results\n## Proteomics marker model performance\n## Benign versus malignant discrimination with dual modality\n# Conclusion\n## Synergistic value of plasma proteins and ultrasound images","[{\"question\":\"What is the main goal of this study for breast cancer diagnosis?\",\"answer\":\"To construct a dual-modal machine learning model that integrates ultrasound radiomics and plasma proteomics for precise breast cancer diagnosis.\"},{\"question\":\"How were the protein markers and radiomics features selected?\",\"answer\":\"Protein mass spectrometry and ultrasound radiomics features were screened from TCGA, CPTAC, and a clinical cohort to obtain 10 protein markers and 14 ultrasound radiomics features.\"},{\"question\":\"How does the dual-modal model perform compared with single-modality models?\",\"answer\":\"The dual-modal model shows excellent performance (AUC = 0.938) for distinguishing benign and malignant lesions, outperforming the proteomics-only model (AUC = 0.830) and the radiomics-only model (AUC = 0.841).\"}]","A dual-modality machine learning precision diagnostic model integrated radiomicsand proteomics for breast cancer | PDF",1785822225,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-dual-modality-machine-learning-precision-diagnostic-model-integrated-radiomicsand-proteomics-for-breast-cancer","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-dual-modality-machine-learning-precision-diagnostic-model-integrated-radiomicsand-proteomics-for-breast-cancer/124423/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of this study for breast cancer diagnosis?","Question",{"text":75,"@type":76},"To construct a dual-modal machine learning model that integrates ultrasound radiomics and plasma proteomics for precise breast cancer diagnosis.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the protein markers and radiomics features selected?",{"text":80,"@type":76},"Protein mass spectrometry and ultrasound radiomics features were screened from TCGA, CPTAC, and a clinical cohort to obtain 10 protein markers and 14 ultrasound radiomics features.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the dual-modal model perform compared with single-modality models?",{"text":84,"@type":76},"The dual-modal model shows excellent performance (AUC = 0.938) for distinguishing benign and malignant lesions, outperforming the proteomics-only model (AUC = 0.830) and the radiomics-only model (AUC = 0.841).","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]