Humaira Noor, Yuanning Zheng, Adam B Mantz, Ryle Zhou, Andrew Kozlov, Wendy B DeMartini, Shu-Tian Chen, Satoko Okamoto, Debra M Ikeda, Melinda L Telli, Allison W Kurian, James M Ford, Shaveta Vinayak, Mina Satoyoshi, Vishal Joshi, Sarah A Mattonen, Kevin Lee, Olivier Gevaert, George W Sledge, Haruka Itakura
{"title":"三阴性乳腺癌的20个特征放射特征确定了死亡风险高的患者。","authors":"Humaira Noor, Yuanning Zheng, Adam B Mantz, Ryle Zhou, Andrew Kozlov, Wendy B DeMartini, Shu-Tian Chen, Satoko Okamoto, Debra M Ikeda, Melinda L Telli, Allison W Kurian, James M Ford, Shaveta Vinayak, Mina Satoyoshi, Vishal Joshi, Sarah A Mattonen, Kevin Lee, Olivier Gevaert, George W Sledge, Haruka Itakura","doi":"10.1038/s41523-025-00790-3","DOIUrl":null,"url":null,"abstract":"<p><p>A substantial proportion of patients with non-metastatic triple-negative breast cancer (TNBC) experience disease progression and death despite treatment. However, no tool currently exists to discriminate those at higher risk of death. To identify high-risk TNBC, we conducted a retrospective analysis of 749 patients from two independent cohorts. We built a prediction model that leverages breast magnetic resonance imaging (MRI) features to predict risk groups based on a 50-gene Transcriptomics Signature (TS). The TS distinguished patients with high-risk for death in multivariate survival analysis (Transcriptomic cohort: [HR] = 13.6, 95% confidence interval [CI] = 1.56-1, p = 0.02; SCAN-B cohort: HR = 1.45, CI 1.04-2.03, p = 0.02). The model identified a 20-feature radiomic signature derived from breast MRI that predicted the TS-based risk groups. This imaging-based classifier was applied to a validation cohort (log rank p = 0.013, accuracy 0.72, AUC 0.71, F1 0.74, precision 0.67, and recall 0.82), detecting a 25% absolute survival difference between high- and low-risk groups after 5 years.</p>","PeriodicalId":19247,"journal":{"name":"NPJ Breast Cancer","volume":"11 1","pages":"79"},"PeriodicalIF":7.6000,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12297616/pdf/","citationCount":"0","resultStr":"{\"title\":\"A 20-feature radiomic signature of triple-negative breast cancer identifies patients at high risk of death.\",\"authors\":\"Humaira Noor, Yuanning Zheng, Adam B Mantz, Ryle Zhou, Andrew Kozlov, Wendy B DeMartini, Shu-Tian Chen, Satoko Okamoto, Debra M Ikeda, Melinda L Telli, Allison W Kurian, James M Ford, Shaveta Vinayak, Mina Satoyoshi, Vishal Joshi, Sarah A Mattonen, Kevin Lee, Olivier Gevaert, George W Sledge, Haruka Itakura\",\"doi\":\"10.1038/s41523-025-00790-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>A substantial proportion of patients with non-metastatic triple-negative breast cancer (TNBC) experience disease progression and death despite treatment. However, no tool currently exists to discriminate those at higher risk of death. To identify high-risk TNBC, we conducted a retrospective analysis of 749 patients from two independent cohorts. We built a prediction model that leverages breast magnetic resonance imaging (MRI) features to predict risk groups based on a 50-gene Transcriptomics Signature (TS). The TS distinguished patients with high-risk for death in multivariate survival analysis (Transcriptomic cohort: [HR] = 13.6, 95% confidence interval [CI] = 1.56-1, p = 0.02; SCAN-B cohort: HR = 1.45, CI 1.04-2.03, p = 0.02). The model identified a 20-feature radiomic signature derived from breast MRI that predicted the TS-based risk groups. This imaging-based classifier was applied to a validation cohort (log rank p = 0.013, accuracy 0.72, AUC 0.71, F1 0.74, precision 0.67, and recall 0.82), detecting a 25% absolute survival difference between high- and low-risk groups after 5 years.</p>\",\"PeriodicalId\":19247,\"journal\":{\"name\":\"NPJ Breast Cancer\",\"volume\":\"11 1\",\"pages\":\"79\"},\"PeriodicalIF\":7.6000,\"publicationDate\":\"2025-07-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12297616/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"NPJ Breast Cancer\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1038/s41523-025-00790-3\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"NPJ Breast Cancer","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1038/s41523-025-00790-3","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
非转移性三阴性乳腺癌(TNBC)患者的很大一部分经历疾病进展和死亡,尽管治疗。然而,目前没有任何工具可以区分那些死亡风险较高的人。为了确定高危TNBC,我们对来自两个独立队列的749例患者进行了回顾性分析。我们建立了一个预测模型,该模型利用乳房磁共振成像(MRI)特征来预测基于50个基因转录组学特征(TS)的风险群体。多变量生存分析中,TS可区分死亡高危患者(转录组组队列:[HR] = 13.6, 95%可信区间[CI] = 1.56-1, p = 0.02;SCAN-B队列:HR = 1.45,置信区间1.04 - -2.03,p = 0.02)。该模型确定了来自乳房MRI的20个特征放射特征,预测了基于ts的风险群体。该基于图像的分类器应用于验证队列(log rank p = 0.013,准确率0.72,AUC 0.71, F1 0.74,精度0.67,召回率0.82),检测出5年后高风险组和低风险组之间的绝对生存差异为25%。
A 20-feature radiomic signature of triple-negative breast cancer identifies patients at high risk of death.
A substantial proportion of patients with non-metastatic triple-negative breast cancer (TNBC) experience disease progression and death despite treatment. However, no tool currently exists to discriminate those at higher risk of death. To identify high-risk TNBC, we conducted a retrospective analysis of 749 patients from two independent cohorts. We built a prediction model that leverages breast magnetic resonance imaging (MRI) features to predict risk groups based on a 50-gene Transcriptomics Signature (TS). The TS distinguished patients with high-risk for death in multivariate survival analysis (Transcriptomic cohort: [HR] = 13.6, 95% confidence interval [CI] = 1.56-1, p = 0.02; SCAN-B cohort: HR = 1.45, CI 1.04-2.03, p = 0.02). The model identified a 20-feature radiomic signature derived from breast MRI that predicted the TS-based risk groups. This imaging-based classifier was applied to a validation cohort (log rank p = 0.013, accuracy 0.72, AUC 0.71, F1 0.74, precision 0.67, and recall 0.82), detecting a 25% absolute survival difference between high- and low-risk groups after 5 years.
期刊介绍:
npj Breast Cancer publishes original research articles, reviews, brief correspondence, meeting reports, editorial summaries and hypothesis generating observations which could be unexplained or preliminary findings from experiments, novel ideas, or the framing of new questions that need to be solved. Featured topics of the journal include imaging, immunotherapy, molecular classification of disease, mechanism-based therapies largely targeting signal transduction pathways, carcinogenesis including hereditary susceptibility and molecular epidemiology, survivorship issues including long-term toxicities of treatment and secondary neoplasm occurrence, the biophysics of cancer, mechanisms of metastasis and their perturbation, and studies of the tumor microenvironment.