Machine learning prediction of pathological complete response to neoadjuvant chemotherapy with peritumoral breast tumor ultrasound radiomics: compare with intratumoral radiomics and clinicopathologic predictors.

IF 3 3区医学 Q2 ONCOLOGY

Breast Cancer Research and Treatment Pub Date : 2025-07-01 Epub Date: 2025-05-16 DOI:10.1007/s10549-025-07727-1

Jiejie Yao, Wei Zhou, Xiaohong Jia, Ying Zhu, Xiaosong Chen, Weiwei Zhan, Jianqiao Zhou

{"title":"Machine learning prediction of pathological complete response to neoadjuvant chemotherapy with peritumoral breast tumor ultrasound radiomics: compare with intratumoral radiomics and clinicopathologic predictors.","authors":"Jiejie Yao, Wei Zhou, Xiaohong Jia, Ying Zhu, Xiaosong Chen, Weiwei Zhan, Jianqiao Zhou","doi":"10.1007/s10549-025-07727-1","DOIUrl":null,"url":null,"abstract":"Purpose: Noninvasive, accurate and novel approaches to predict patients who will achieve pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) could assist treatment strategies. The aim of this study was to explore the application of machine learning (ML) based peritumoral ultrasound radiomics signature (PURS), compared with intratumoral radiomics (IURS) and clinicopathologic factors, for early prediction of pCR.Methods: We analyzed 358 locally advanced breast cancer patients (250 in the training set and 108 in the test set), who accepted NAC and post NAC surgery at our institution. The clinical and pathological data were analyzed using the independent t test and the Chi-square test to determine the factors associated with pCR. The PURS and IURS of baseline breast tumors were extracted by using 3D-slicer and PyRadiomics software. Five ML classifiers including linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF), logistic regression (LR), and adaptive boosting (AdaBoost) were applied to construct radiomics predictive models. The performance of PURS, IURS models and clinicopathologic predictors were assessed with respect to sensitivity, specificity, accuracy and the areas under the curve (AUCs).Results: Ninety-seven patients achieved pCR. The clinicopathologic predictors obtained an AUC of 0.759. Among PURS models, the RF classifier achieved better efficacy (AUC of 0.889) than LR (0.849), AdaBoost (0.823), SVM (0.746) and LDA (0.732). The RF classifier also obtained a maximum AUC of 0.931 than 0.920 (AdaBoost), 0.875 (LR), 0.825 (SVM), and 0.798 (LDA) in IURS models in the test set. The RF based PURS yielded higher predictive ability (AUC 0.889; 95% CI 0.814, 0.947) than clinicopathologic factors (AUC 0.759; 95% CI 0.657, 0.861; p < 0.05), but lower efficacy compared with IURS (AUC 0.931; 95% CI 0.865, 0.980; p < 0.05).Conclusion: The peritumoral US radiomics, as a novel potential biomarker, can assist clinical therapy decisions.","PeriodicalId":9133,"journal":{"name":"Breast Cancer Research and Treatment","volume":" ","pages":"325-336"},"PeriodicalIF":3.0000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12133900/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Breast Cancer Research and Treatment","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10549-025-07727-1","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/5/16 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: Noninvasive, accurate and novel approaches to predict patients who will achieve pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) could assist treatment strategies. The aim of this study was to explore the application of machine learning (ML) based peritumoral ultrasound radiomics signature (PURS), compared with intratumoral radiomics (IURS) and clinicopathologic factors, for early prediction of pCR.

Methods: We analyzed 358 locally advanced breast cancer patients (250 in the training set and 108 in the test set), who accepted NAC and post NAC surgery at our institution. The clinical and pathological data were analyzed using the independent t test and the Chi-square test to determine the factors associated with pCR. The PURS and IURS of baseline breast tumors were extracted by using 3D-slicer and PyRadiomics software. Five ML classifiers including linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF), logistic regression (LR), and adaptive boosting (AdaBoost) were applied to construct radiomics predictive models. The performance of PURS, IURS models and clinicopathologic predictors were assessed with respect to sensitivity, specificity, accuracy and the areas under the curve (AUCs).

Results: Ninety-seven patients achieved pCR. The clinicopathologic predictors obtained an AUC of 0.759. Among PURS models, the RF classifier achieved better efficacy (AUC of 0.889) than LR (0.849), AdaBoost (0.823), SVM (0.746) and LDA (0.732). The RF classifier also obtained a maximum AUC of 0.931 than 0.920 (AdaBoost), 0.875 (LR), 0.825 (SVM), and 0.798 (LDA) in IURS models in the test set. The RF based PURS yielded higher predictive ability (AUC 0.889; 95% CI 0.814, 0.947) than clinicopathologic factors (AUC 0.759; 95% CI 0.657, 0.861; p < 0.05), but lower efficacy compared with IURS (AUC 0.931; 95% CI 0.865, 0.980; p < 0.05).

Conclusion: The peritumoral US radiomics, as a novel potential biomarker, can assist clinical therapy decisions.

查看原文本刊更多论文

机器学习预测肿瘤周围乳腺肿瘤超声放射组学对新辅助化疗病理完全缓解：与肿瘤内放射组学和临床病理预测指标比较。

目的：无创、准确和新颖的方法预测患者在新辅助化疗（NAC）后是否会达到病理完全缓解（pCR），有助于制定治疗策略。本研究的目的是探讨基于机器学习（ML）的肿瘤周围超声放射组学特征（PURS）的应用，与肿瘤内放射组学（IURS）和临床病理因素进行比较，以早期预测pCR。方法：对我院接受NAC及术后手术的358例局部晚期乳腺癌患者（训练组250例，测试组108例）进行分析。采用独立t检验和卡方检验对临床和病理资料进行分析，确定与pCR相关的因素。利用3d -切片机和PyRadiomics软件提取基线乳腺肿瘤的PURS和IURS。采用线性判别分析（LDA）、支持向量机（SVM）、随机森林（RF）、逻辑回归（LR）和自适应增强（AdaBoost）等5种ML分类器构建放射组学预测模型。评估PURS、IURS模型和临床病理预测指标的敏感性、特异性、准确性和曲线下面积（auc）。结果：97例患者实现pCR。临床病理预测指标的AUC为0.759。在PURS模型中，RF分类器的AUC（0.889）优于LR（0.849）、AdaBoost（0.823）、SVM（0.746）和LDA（0.732）。与测试集中IURS模型的0.920 （AdaBoost）、0.875 （LR）、0.825 （SVM）和0.798 （LDA）相比，RF分类器的最大AUC为0.931。基于RF的PURS具有较高的预测能力(AUC 0.889；95% CI 0.814, 0.947)大于临床病理因素(AUC 0.759；95% ci 0.657, 0.861；结论：肿瘤周围US放射组学作为一种新的潜在生物标志物，可以辅助临床治疗决策。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Breast Cancer Research and Treatment 医学-肿瘤学

CiteScore

6.80

自引率

2.60%

发文量

342

审稿时长

1 months

期刊介绍： Breast Cancer Research and Treatment provides the surgeon, radiotherapist, medical oncologist, endocrinologist, epidemiologist, immunologist or cell biologist investigating problems in breast cancer a single forum for communication. The journal creates a "market place" for breast cancer topics which cuts across all the usual lines of disciplines, providing a site for presenting pertinent investigations, and for discussing critical questions relevant to the entire field. It seeks to develop a new focus and new perspectives for all those concerned with breast cancer.