Daimiel Naranjo Isaac, Gibbs Peter, Reiner Jeffrey S, Lo Gullo Roberto, Thakur Sunitha B, Jochelson Maxine S, Thakur Nikita, Baltzer Pascal A T, Helbich Thomas H, Pinker Katja
Memorial Sloan Kettering Cancer Center, Department of Radiology, Breast Imaging Service, New York, NY 10065, USA.
Department of Radiology, Breast Imaging Service, Guy's and St. Thomas' NHS Trust, Great Maze Pond, London SE1 9RT, UK.
Cancers (Basel). 2022 Mar 29;14(7):1743. doi: 10.3390/cancers14071743.
This multicenter retrospective study compared the performance of radiomics analysis coupled with machine learning (ML) with that of radiologists for the classification of breast tumors. A total of 93 consecutive women (mean age: 49 ± 12 years) with 104 histopathologically verified enhancing lesions (mean size: 22.8 ± 15.1 mm), classified as suspicious on multiparametric breast MRIs were included. Two experienced breast radiologists assessed all of the lesions, assigning a Breast Imaging Reporting and Database System (BI-RADS) suspicion category, providing a diffusion-weighted imaging (DWI) score based on lesion signal intensity, and determining the apparent diffusion coefficient (ADC). Ten predictive models for breast lesion discrimination were generated using radiomic features extracted from the multiparametric MRI. The area under the receiver operating curve (AUC) and the accuracy were compared using McNemar's test. Multiparametric radiomics with DWI score and BI-RADS (accuracy = 88.5%; AUC = 0.93) and multiparametric radiomics with ADC values and BI-RADS (accuracy= 88.5%; AUC = 0.96) models showed significant improvements in diagnostic accuracy compared to the multiparametric radiomics (DWI + DCE data) model ( = 0.01 and = 0.02, respectively), but performed similarly compared to the multiparametric assessment by radiologists (accuracy = 85.6%; AUC = 0.03; = 0.39). In conclusion, radiomics analysis coupled with the ML of multiparametric MRI could assist in breast lesion discrimination, especially for less experienced readers of breast MRIs.
这项多中心回顾性研究比较了将放射组学分析与机器学习（ML）相结合与放射科医生对乳腺肿瘤进行分类的性能。共纳入93例连续女性（平均年龄：49±12岁），她们有104个经组织病理学证实的强化病变（平均大小：22.8±15.1mm），这些病变在多参数乳腺磁共振成像（MRI）上被分类为可疑病变。两名经验丰富的乳腺放射科医生评估了所有病变，给出乳腺影像报告和数据系统（BI-RADS）可疑类别，根据病变信号强度提供扩散加权成像（DWI）评分，并测定表观扩散系数（ADC）。利用从多参数MRI中提取的放射组学特征生成了10个用于乳腺病变鉴别的预测模型。使用McNemar检验比较受试者操作特征曲线（AUC）下的面积和准确性。与多参数放射组学（DWI+DCE数据）模型相比，结合DWI评分和BI-RADS的多参数放射组学（准确率=88.5%；AUC=0.93）以及结合ADC值和BI-RADS的多参数放射组学（准确率=88.5%；AUC=0.96）模型在诊断准确性上有显著提高（分别为P=0.01和P=0.02），但与放射科医生的多参数评估相比表现相似（准确率=85.6%；AUC=0.93；P=0.39）。总之，多参数MRI的放射组学分析与ML相结合有助于乳腺病变的鉴别，特别是对于经验较少的乳腺MRI阅片者。
