Background:Breast cancer (BC) is the most frequently diagnosed cancer in women and the leading cause of cancer-related deaths in women globally. Carriers of P/LP variants in theBRCA1,BRCA2,TP53,PTEN,CDH1,PALB2, andSTK11genes have an increased risk of developing BC, which is why more and more guidelines recommend prophylactic mastectomy in this group of patients. Because traditional genetic testing is expensive and can cause delays in patient management, radiomics based on diagnostic imaging could be an alternative. This study aims to evaluate whether ultrasound-based radiomics features can predict P/LP variant status in BC patients.Methods: This retrospective study included 88 breast tumors in patients tested with multigene panel tests, including all seven above-mentioned genes. Ultrasound images were acquired prior to any treatment, and the tumoral and peritumoral areas were used to extract radiomics data. The study population was divided into P/LP and non-P/LP variant groups. Radiomics features were analyzed using machine learning models, alone or in combination with clinical features, with the aim of predicting the genetic status of BC patients.Results: We observed significant differences in radiomics features between P/LP- and non-P/LP-variant-driven tumors. The developed radiomics model achieved a maximum mean accuracy of 85.7% in identifying P/LP variant carriers. Including features from the peritumoral area yielded the same maximum accuracy.Conclusions: Radiomics models based on ultrasound images of breast tumors may provide a promising alternative for predicting P/LP variant status in BC patients. This approach could reduce dependence on costly genetic testing and expedite the diagnostic process. However, further validation in larger and more diverse populations is needed.
背景：乳腺癌是全球女性中诊断频率最高的癌症，也是女性癌症相关死亡的主要原因。携带BRCA1、BRCA2、TP53、PTEN、CDH1、PALB2和STK11基因致病/可能致病性变异的个体罹患乳腺癌的风险显著增加，因此越来越多的指南建议此类患者接受预防性乳房切除术。由于传统基因检测费用高昂且可能延误临床管理，基于诊断影像的影像组学技术或可成为一种替代方案。本研究旨在评估基于超声的影像组学特征能否预测乳腺癌患者的致病/可能致病性变异状态。 方法：本回顾性研究纳入了88例接受多基因检测（包含上述全部七个基因）的乳腺癌患者的肿瘤样本。所有超声图像均在治疗前获取，并基于肿瘤及瘤周区域提取影像组学数据。研究人群被分为致病/可能致病性变异组与非致病/可能致病性变异组。通过机器学习模型分析影像组学特征（单独或联合临床特征），以预测乳腺癌患者的基因变异状态。 结果：研究发现致病/可能致病性变异驱动型肿瘤与非变异驱动型肿瘤的影像组学特征存在显著差异。所构建的影像组学模型在识别致病/可能致病性变异携带者时达到最高平均准确率85.7%。纳入瘤周区域特征后获得了相同的最高准确率。 结论：基于乳腺肿瘤超声图像的影像组学模型可能为预测乳腺癌患者致病/可能致病性变异状态提供一种有前景的替代方法。该技术有望降低对昂贵基因检测的依赖并加速诊断流程，但尚需在更大规模及更多样化的人群中进行进一步验证。
Predicting Pathogenic Variants of Breast Cancer Using Ultrasound-Derived Machine Learning Models
肿瘤(癌症)患者之家