基于机器学习的直肠癌MRI影像组学分析预测异时性肝转移
本研究回顾性分析108例直肠癌患者(异时性肝转移组54例、无转移组54例),从T2WI和静脉期序列提取影像组学特征并用最小绝对收缩和选择算子法筛选,构建支持向量机与逻辑回归预测模型。逻辑回归算法下基于2058个特征筛选出22个最优特征构建的模型预测性能最佳,准确度0.80、敏感度0.83、特异度0.76、AUC 0.87。
要点
- 基于基线直肠MRI的影像组学模型对异时性肝转移具有较高预测潜力,最优模型采用逻辑回归算法。
- 最优模型(Modeloptimal)准确度0.80、敏感度0.83、特异度0.76、AUC 0.87。
- 静脉期序列模型中逻辑回归优于支持向量机(P=0.0303),其余模型未见此优势。
核心结论
- 基于基线直肠MRI的影像组学模型对异时性肝转移具有较高预测潜力,尤其是采用逻辑回归算法的最优模型。
研究设计与样本
- 回顾性分析108例直肠癌患者(异时性肝转移组54例、无转移组54例),从T2WI和静脉期序列分别提取影像组学特征,并用最小绝对收缩和选择算子法在含2058个特征的组合特征集中筛选。
诊断标准与关键数值
- 从1029个T2WI特征、1029个静脉期特征和2058个组合特征中分别筛选出5个、8个和22个最优特征。
- 构建四组模型:ModelT2(5个T2WI特征)、ModelVP(8个静脉期特征)、Modelcombined(组合的13个最优特征)、Modeloptimal(从2058个特征中筛选的22个最优特征)。
- Modeloptimal采用逻辑回归算法,准确度0.80、敏感度0.83、特异度0.76、AUC 0.87,预测性能最佳(P=0.0019–0.0081)。
- 在ModelVP中,逻辑回归优于支持向量机算法(P=0.0303)。
- 除ModelVP外,逻辑回归在模型构建中未优于支持向量机算法。
临床应用与阅片要点
- 作者认为基于基线直肠MRI的影像组学模型对异时性肝转移具有较高预测潜力,尤其是采用逻辑回归算法的最优模型。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: To use machine learning-based magnetic resonance imaging radiomics to predict metachronous liver metastases (MLM) in patients with rectal cancer.
MATERIALS AND METHODS: This study retrospectively analyzed 108 patients with rectal cancer (54 in MLM group and 54 in nonmetastases group). Feature selection were performed in the radiomic feature sets extracted from images of T2-weighted image (T2WI) and venous phase (VP) sequence respectively, and the combining feature set with 2058 radiomic features incorporating two sequences with the least absolute shrinkage and selection operator method. Five-fold cross-validation and two machine learning algorithms (support vector machine [SVM]; logistic regression [LR]) were utilized for predictive model constructing. The diagnostic performance of the models was evaluated by receiver operating characteristic curves with indicators of accuracy, sensitivity, specificity and area under the curve, and compared by DeLong test.
RESULTS: Five, 8, and 22 optimal features were selected from 1029 T2WI, 1029 VP, and 2058 combining features, respectively. Four-group models were constructed using the five T2WI features (ModelT2), the 8 VP features (ModelVP), the combined 13 optimal features (Modelcombined), and the 22 optimal features selected from 2058 features (Modeloptimal). In ModelVP, the LR was superior to the SVM algorithm (P = 0.0303). The Modeloptimal using LR algorithm showed the best prediction performance (P = 0.0019-0.0081) with accuracy, sensitivity, specificity, and area under the curve of 0.80, 0.83, 0.76, and 0.87, respectively.
CONCLUSION: Radiomics models based on baseline rectal magnetic resonance imaging has high potential for MLM prediction, especially the Modeloptimal using LR algorithm. Moreover, except for ModelVP, the LR was not superior to the SVM algorithm for model construction.
引用
- Liang M, Cai Z, Zhang H, et al. Machine Learning-based Analysis of Rectal Cancer MRI Radiomics for Prediction of Metachronous Liver Metastasis. Acad Radiol. 2019. PMID: 30711405. doi:10.1016/j.acra.2018.12.019
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。