通过放射组学方法预测乳房x线微钙化的病理状态

IF 4.4 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Min Li , Liyu Zhu , Guangquan Zhou , Jianan He , Yanni Jiang , Yang Chen
{"title":"通过放射组学方法预测乳房x线微钙化的病理状态","authors":"Min Li ,&nbsp;Liyu Zhu ,&nbsp;Guangquan Zhou ,&nbsp;Jianan He ,&nbsp;Yanni Jiang ,&nbsp;Yang Chen","doi":"10.1016/j.imed.2021.05.003","DOIUrl":null,"url":null,"abstract":"<div><p><strong>Objective</strong> The study aimed to develop a machine learning (ML)-coupled interpretable radiomics signature to predict the pathological status of non-palpable suspicious breast microcalcifications (MCs).</p><p><strong>Methods</strong> We enrolled 463 digital mammographical view images from 260 consecutive patients detected with non-palpable MCs and BI-RADS scored at 4 (training cohort, <em>n</em> = 428; independent testing cohort, <em>n</em> = 35) in the First Affiliated Hospital of Nanjing Medical University between September 2010 and January 2019. Subsequently, 837 textures and 9 shape features were subsequently extracted from each view and finally selected by an XGBoost-embedded recursive feature elimination technique (RFE), followed by four machine learning-based classifiers to build the radiomics signature.</p><p><strong>Results</strong> Ten radiomic features constituted a malignancy-related signature for breast MCs as logistic regression (LR) and support vector machine (SVM) yielded better positive predictive value (PPV)/sensitivity (SE), 0.904 (95% CI, 0.865–0.949)/0.946 (95% CI, 0.929–0.977) and 0.891 (95% CI, 0.822–0.939)/0.939 (95% CI, 0.907–0.973) respectively, outperforming their negative predictive value (NPV)/specificity (SP) from 10-fold cross-validation (10FCV) of the training cohort. The optimal prognostic model was obtained by SVM with an area under the curve (AUC) of 0.906 (95% CI, 0.834–0.969) and accuracy (ACC) 0.787 (95% CI, 0.680–0.855) from 10FCV against AUC 0.810 (95% CI, 0.760–0.960) and ACC 0.800 from the testing cohort.</p><p><strong>Conclusion</strong> The proposed radiomics signature dependens on a set of ML-based advanced computational algorithms and is expected to identify pathologically cancerous cases from mammographically undecipherable MCs and thus offer prospective clinical diagnostic guidance.</p></div>","PeriodicalId":73400,"journal":{"name":"Intelligent medicine","volume":"1 3","pages":"Pages 95-103"},"PeriodicalIF":4.4000,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.imed.2021.05.003","citationCount":"3","resultStr":"{\"title\":\"Predicting the pathological status of mammographic microcalcifications through a radiomics approach\",\"authors\":\"Min Li ,&nbsp;Liyu Zhu ,&nbsp;Guangquan Zhou ,&nbsp;Jianan He ,&nbsp;Yanni Jiang ,&nbsp;Yang Chen\",\"doi\":\"10.1016/j.imed.2021.05.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p><strong>Objective</strong> The study aimed to develop a machine learning (ML)-coupled interpretable radiomics signature to predict the pathological status of non-palpable suspicious breast microcalcifications (MCs).</p><p><strong>Methods</strong> We enrolled 463 digital mammographical view images from 260 consecutive patients detected with non-palpable MCs and BI-RADS scored at 4 (training cohort, <em>n</em> = 428; independent testing cohort, <em>n</em> = 35) in the First Affiliated Hospital of Nanjing Medical University between September 2010 and January 2019. Subsequently, 837 textures and 9 shape features were subsequently extracted from each view and finally selected by an XGBoost-embedded recursive feature elimination technique (RFE), followed by four machine learning-based classifiers to build the radiomics signature.</p><p><strong>Results</strong> Ten radiomic features constituted a malignancy-related signature for breast MCs as logistic regression (LR) and support vector machine (SVM) yielded better positive predictive value (PPV)/sensitivity (SE), 0.904 (95% CI, 0.865–0.949)/0.946 (95% CI, 0.929–0.977) and 0.891 (95% CI, 0.822–0.939)/0.939 (95% CI, 0.907–0.973) respectively, outperforming their negative predictive value (NPV)/specificity (SP) from 10-fold cross-validation (10FCV) of the training cohort. The optimal prognostic model was obtained by SVM with an area under the curve (AUC) of 0.906 (95% CI, 0.834–0.969) and accuracy (ACC) 0.787 (95% CI, 0.680–0.855) from 10FCV against AUC 0.810 (95% CI, 0.760–0.960) and ACC 0.800 from the testing cohort.</p><p><strong>Conclusion</strong> The proposed radiomics signature dependens on a set of ML-based advanced computational algorithms and is expected to identify pathologically cancerous cases from mammographically undecipherable MCs and thus offer prospective clinical diagnostic guidance.</p></div>\",\"PeriodicalId\":73400,\"journal\":{\"name\":\"Intelligent medicine\",\"volume\":\"1 3\",\"pages\":\"Pages 95-103\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2021-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/j.imed.2021.05.003\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Intelligent medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2667102621000127\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Intelligent medicine","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667102621000127","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 3

摘要

目的建立一种机器学习(ML)耦合的可解释放射组学特征来预测不可触及的可疑乳房微钙化(MCs)的病理状态。方法:我们收集了260例连续检测到不可触及MCs的患者的463张数字乳房x线摄影图像,BI-RADS评分为4(训练队列,n = 428;独立检测队列,n = 35),于2010年9月至2019年1月在南京医科大学第一附属医院进行。随后,从每个视图中提取837个纹理和9个形状特征,最后通过嵌入xgboost的递归特征消除技术(RFE)进行选择,然后使用4个基于机器学习的分类器构建放射组学签名。结果10个放射学特征构成乳腺MCs的恶性相关特征,logistic回归(LR)和支持向量机(SVM)的阳性预测值(PPV)/敏感性(SE)更高,分别为0.904 (95% CI, 0.865-0.949)/0.946 (95% CI, 0.929-0.977)和0.891 (95% CI, 0.822-0.939)/0.939 (95% CI, 0.907-0.973),优于训练队列10倍交叉验证(10FCV)的阴性预测值(NPV)/特异性(SP)。通过支持向量机获得最佳预后模型,曲线下面积(AUC)为0.906 (95% CI, 0.834-0.969),准确度(ACC)为0.787 (95% CI, 0.680-0.855),而测试队列的AUC为0.810 (95% CI, 0.760-0.960), ACC为0.800。结论提出的放射组学特征依赖于一套基于ml的先进计算算法,有望从乳房x线摄影无法识别的MCs中识别病理癌病例,从而提供前瞻性临床诊断指导。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Predicting the pathological status of mammographic microcalcifications through a radiomics approach

Objective The study aimed to develop a machine learning (ML)-coupled interpretable radiomics signature to predict the pathological status of non-palpable suspicious breast microcalcifications (MCs).

Methods We enrolled 463 digital mammographical view images from 260 consecutive patients detected with non-palpable MCs and BI-RADS scored at 4 (training cohort, n = 428; independent testing cohort, n = 35) in the First Affiliated Hospital of Nanjing Medical University between September 2010 and January 2019. Subsequently, 837 textures and 9 shape features were subsequently extracted from each view and finally selected by an XGBoost-embedded recursive feature elimination technique (RFE), followed by four machine learning-based classifiers to build the radiomics signature.

Results Ten radiomic features constituted a malignancy-related signature for breast MCs as logistic regression (LR) and support vector machine (SVM) yielded better positive predictive value (PPV)/sensitivity (SE), 0.904 (95% CI, 0.865–0.949)/0.946 (95% CI, 0.929–0.977) and 0.891 (95% CI, 0.822–0.939)/0.939 (95% CI, 0.907–0.973) respectively, outperforming their negative predictive value (NPV)/specificity (SP) from 10-fold cross-validation (10FCV) of the training cohort. The optimal prognostic model was obtained by SVM with an area under the curve (AUC) of 0.906 (95% CI, 0.834–0.969) and accuracy (ACC) 0.787 (95% CI, 0.680–0.855) from 10FCV against AUC 0.810 (95% CI, 0.760–0.960) and ACC 0.800 from the testing cohort.

Conclusion The proposed radiomics signature dependens on a set of ML-based advanced computational algorithms and is expected to identify pathologically cancerous cases from mammographically undecipherable MCs and thus offer prospective clinical diagnostic guidance.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Intelligent medicine
Intelligent medicine Surgery, Radiology and Imaging, Artificial Intelligence, Biomedical Engineering
CiteScore
5.20
自引率
0.00%
发文量
19
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信