Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images
详细信息 查看全文
- 作者：Hongkai Wang ; Zongwei Zhou ; Yingci Li ; Zhonghua Chen ; Peiou Lu…
- 关键词：Computer ; aided diagnosis ; Non ; small cell lung cancer ; Positron ; emission tomography ; Machine learning ; Deep learning
- 刊名：EJNMMI Research
- 出版年：2017
- 出版时间：December 2017
- 年：2017
- 卷：7
- 期：1
- 全文大小：1194KB
- 刊物主题：Nuclear Medicine; Imaging / Radiology; Orthopedics; Cardiology; Oncology;
- 出版者：Springer Berlin Heidelberg
- ISSN：2191-219X
- 卷排序：7
文摘
BackgroundThis study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute.