基于PET影像组学的机器学习方法预测肺癌组织学亚型
该研究回顾性分析396例治疗前接受FDG PET/CT的肺癌患者(210例腺癌、186例鳞癌),提取40个影像组学特征和4个临床特征,比较多种机器学习算法预测组织学亚型的能力。逻辑回归模型表现最佳(AUC=0.859),神经网络模型紧随其后(AUC=0.854)。基于PET的影像组学特征有望无创辅助组织病理诊断。
要点
- 逻辑回归模型预测肺腺癌的AUC为0.859,优于其他机器学习分类器。
- 性别、SUVmax、灰度区域长度非均匀性、区域灰度非均匀性和总病灶糖酵解是前5位预测因子。
- 基于PET的影像组学模型可无创辅助鉴别肺腺癌与鳞癌。
核心结论
- 基于PET影像组学的机器学习方法能成功鉴别肺癌组织学亚型,逻辑回归模型表现最佳(AUC=0.859)。
研究设计与样本
- 回顾性分析396例治疗前接受FDG PET/CT的肺癌患者,其中腺癌210例、鳞癌186例。
- 研究4个临床特征(年龄、性别、肿瘤大小、吸烟状态)和40个影像组学特征,使用LIFEx软件包从分割肿瘤的PET图像中提取影像组学特征。
- 基于基尼系数评分筛选特征后,比较随机森林、神经网络、朴素贝叶斯、逻辑回归和支持向量机等多种机器学习算法的分类性能,并通过随机抽样进行验证。
主要发现
- 性别、SUVmax、灰度区域长度非均匀性、区域灰度非均匀性和总病灶糖酵解是预测肺腺癌的5个最佳预测因子。
- 逻辑回归模型表现优于所有其他分类器(AUC=0.859,准确率=0.769,F1分数=0.774,精确率=0.804,召回率=0.746)。
- 神经网络模型次之(AUC=0.854,准确率=0.772,F1分数=0.777,精确率=0.807,召回率=0.750)。
关键数值与推荐
- 逻辑回归模型AUC=0.859,准确率=0.769,F1分数=0.774,精确率=0.804,召回率=0.746。
- 神经网络模型AUC=0.854,准确率=0.772,F1分数=0.777,精确率=0.807,召回率=0.750。
临床怎么用
- 基于PET的影像组学特征可帮助临床医生以无创方式改进组织病理诊断。
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)。
原文
PURPOSE: We sought to distinguish lung adenocarcinoma (ADC) from squamous cell carcinoma using a machine-learning algorithm with PET-based radiomic features. METHODS: A total of 396 patients with 210 ADCs and 186 squamous cell carcinomas who underwent FDG PET/CT prior to treatment were retrospectively analyzed. Four clinical features (age, sex, tumor size, and smoking status) and 40 radiomic features were investigated in terms of lung ADC subtype prediction. Radiomic features were extracted from the PET images of segmented tumors using the LIFEx package. The clinical and radiomic features were ranked, and a subset of useful features was selected based on Gini coefficient scores in terms of associations with histological class. The areas under the receiver operating characteristic curves (AUCs) of classifications afforded by several machine-learning algorithms (random forest, neural network, naive Bayes, logistic regression, and a support vector machine) were compared and validated via random sampling. RESULTS: We developed and validated a PET-based radiomic model predicting the histological subtypes of lung cancer. Sex, SUVmax, gray-level zone length nonuniformity, gray-level nonuniformity for zone, and total lesion glycolysis were the 5 best predictors of lung ADC. The logistic regression model outperformed all other classifiers (AUC = 0.859, accuracy = 0.769, F1 score = 0.774, precision = 0.804, recall = 0.746) followed by the neural network model (AUC = 0.854, accuracy = 0.772, F1 score = 0.777, precision = 0.807, recall = 0.750). CONCLUSIONS: A machine-learning approach successfully identified the histological subtypes of lung cancer. A PET-based radiomic features may help clinicians improve the histopathologic diagnosis in a noninvasive manner.
引用
- Hyun SH, Ahn MS, Koh YW, et al. A Machine-Learning Approach Using PET-Based Radiomics to Predict the Histological Subtypes of Lung Cancer. Clin Nucl Med. 2019. PMID: 31689276. doi:10.1097/RLU.0000000000002810
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。