基于PET/CT影像的放射组学机器学习与深度学习鉴别非小细胞肺癌组织学亚型
本研究回顾性分析867例腺癌(ADC)和552例鳞状细胞癌(SCC)患者,从肿瘤区域提取688个特征,评估10种特征选择方法、10种机器学习模型及VGG16深度学习算法构建分类模型。结果显示VGG16深度学习算法(AUROC 0.903;准确率0.841)优于所有传统机器学习方法,LDA和SVM结合ℓ2,1NR特征选择方法达到传统方法中最优性能(AUROC 0.863)。
要点
- VGG16深度学习算法鉴别ADC与SCC的AUROC为0.903,准确率0.841。
- LDA与SVM结合ℓ2,1NR特征选择方法AUROC均为0.863,准确率分别为0.794和0.792。
- 放射组学机器学习/深度学习算法可辅助放射科医生通过PET/CT图像区分NSCLC组织学亚型。
核心结论
- 采用放射组学机器学习/深度学习算法可帮助放射科医生通过PET/CT图像区分非小细胞肺癌的组织学亚型。
研究设计与样本
- 回顾性分析867例腺癌(ADC)和552例鳞状细胞癌(SCC)患者,按分层随机抽样283例(20%)作为测试集(173例ADC和110例SCC),其余为训练集。
- 从每个勾画的肿瘤区域提取688个特征,评估10种特征选择技术、10种机器学习模型和VGG16深度学习算法以构建最优分类模型。
- 采用十折交叉验证和网格搜索技术在训练集上评估和优化模型超参数,在测试集上使用AUROC、准确率、精确率、敏感性和特异性评估模型性能。
主要发现
- 线性判别分析(LDA)(AUROC 0.863;准确率0.794)和支持向量机(SVM)(AUROC 0.863;准确率0.792)分类器均结合ℓ2,1NR特征选择方法达到最优性能。
- 随机森林(RF)分类器(AUROC 0.824;准确率0.775)和ℓ2,1NR特征选择方法(AUROC 0.815;准确率0.764)分别在所用分类器和特征选择方法中表现出优异的平均性能。
- VGG16深度学习算法(AUROC 0.903;准确率0.841)优于所有结合放射组学的传统机器学习方法。
关键数值与推荐
- VGG16深度学习算法在测试集上的AUROC为0.903,准确率为0.841。
- LDA结合ℓ2,1NR特征选择方法在测试集上的AUROC为0.863,准确率为0.794。
- SVM结合ℓ2,1NR特征选择方法在测试集上的AUROC为0.863,准确率为0.792。
- RF分类器在测试集上的AUROC为0.824,准确率为0.775。
- ℓ2,1NR特征选择方法在测试集上的AUROC为0.815,准确率为0.764。
临床怎么用
- 放射组学机器学习/深度学习算法可作为辅助工具,帮助放射科医生通过PET/CT图像鉴别非小细胞肺癌的腺癌与鳞状细胞癌组织学亚型。
- VGG16深度学习算法在鉴别性能上优于传统机器学习方法,但需进一步临床验证。
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
PURPOSES: To evaluate the capability of PET/CT images for differentiating the histologic subtypes of non-small cell lung cancer (NSCLC) and to identify the optimal model from radiomics-based machine learning/deep learning algorithms. METHODS: In this study, 867 patients with adenocarcinoma (ADC) and 552 patients with squamous cell carcinoma (SCC) were retrospectively analysed. A stratified random sample of 283 patients (20%) was used as the testing set (173 ADC and 110 SCC); the remaining data were used as the training set. A total of 688 features were extracted from each outlined tumour region. Ten feature selection techniques, ten machine learning (ML) models and the VGG16 deep learning (DL) algorithm were evaluated to construct an optimal classification model for the differential diagnosis of ADC and SCC. Tenfold cross-validation and grid search technique were employed to evaluate and optimize the model hyperparameters on the training dataset. The area under the receiver operating characteristic curve (AUROC), accuracy, precision, sensitivity and specificity was used to evaluate the performance of the models on the test dataset. RESULTS: Fifty top-ranked subset features were selected by each feature selection technique for classification. The linear discriminant analysis (LDA) (AUROC, 0.863; accuracy, 0.794) and support vector machine (SVM) (AUROC, 0.863; accuracy, 0.792) classifiers, both of which coupled with the ℓ2,1NR feature selection method, achieved optimal performance. The random forest (RF) classifier (AUROC, 0.824; accuracy, 0.775) and ℓ2,1NR feature selection method (AUROC, 0.815; accuracy, 0.764) showed excellent average performance among the classifiers and feature selection methods employed in our study, respectively. Furthermore, the VGG16 DL algorithm (AUROC, 0.903; accuracy, 0.841) outperformed all conventional machine learning methods in combination with radiomics. CONCLUSION: Employing radiomic machine learning/deep learning algorithms could help radiologists to differentiate the histologic subtypes of NSCLC via PET/CT images.
引用
- Han Y, Ma Y, Wu Z, et al. Histologic subtype classification of non-small cell lung cancer using PET/CT images. Eur J Nucl Med Mol Imaging. 2020. PMID: 32776232. doi:10.1007/s00259-020-04771-5
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。