腹部影像组学对乳腺癌相关骨质疏松机会性筛查的研究

Abdominal Radiomics Studies of Opportunistic Screening for Breast Cancerassociated Osteoporosis

目的:对单中心腹部CT的影像组学在乳腺癌相关骨质疏松机会性筛查中的应用进行研究。方法:分析我院治疗前分别接受腹部CT扫描和双能X线(DXA)检查的新发乳腺癌患者(共132例)资料。提取患者L3水平的CT影像组学特征,并按照7∶3比例将患者分为训练组(92例)和验证组(40例)。依次通过组内相关系数(ICC)、最大相关和最小冗余(mRMR)及最小绝对收缩和选择算法(LASSO)等方法对训练组的特征进行降维,建立影像组学模型和综合模型,诊断价值均通过验证组的ROC曲线来验证。结果:在132例患者中,经DXA诊断出的骨质疏松症41例。影像组学提取特征790个,对训练组病例进行特征降维后最终获得10个影像组学特征。决策曲线显示联合诊断模型可以使临床获益。结论:通过提取在常规腹部CT扫描上腰椎的组学特征,为骨质疏松提供了简单可靠机会性筛查方法。

Purpose:To study the application of single-center abdominal CT radiomics in opportunistic screening of breast cancer-related osteoporosis.Methods:A total of 132 patients with new-onset breast cancer who underwent abdominal CT scan and dual-energy X-ray(DXA)examination before treatment in our hospital were analyzed.The CT imaging characteristics of the patients at the L3 level were extracted,and the patients were divided into training group(92 cases)and validation group(40 cases)at a ratio of 7:3.The characteristics of the training group were reduced by interclass correlation coefficient(ICC),maximum relevance and minimum redundancy(mRMR)and least absolute shrinkage and selection operator(LASSO)methods,the radiomics model and comprehensive model were established,and the diagnostic value was verified by the ROC curve of the verification group.Results:Among the 132 patients,41 cases of osteoporosis were diagnosed with DXA.Seven hundred and ninety radiomics features were extracted,and 10 radiomics features were obtained after feature dimensionality reduction in the training group.The decision curve showed that a combined diagnostic model could have clinical benefits.Conclusion:By extracting the omics features of the lumbar spine on conventional abdominal CT scan,this paper provids a simple and reliable opportunistic screeningmethodforosteoporosis.