Teramoto Atsushi, Tsujimoto Masakazu, Inoue Takahiro, Tsukamoto Tetsuya, Imaizumi Kazuyoshi, Toyama Hiroshi, Saito Kuniaki, Fujita Hiroshi
Faculty of Radiological Technology, School of Health Sciences, Fujita Health University, Toyoake, Japan.
Fujita Health University Hospital, Toyoake, Japan.
Asia Ocean J Nucl Med Biol. 2019 Winter;7(1):29-37. doi: 10.22038/AOJNMB.2018.12014.
Positron emission tomography/computed tomography (PET/CT) examination is commonly used for the evaluation of pulmonary nodules since it provides both anatomical and functional information. However, given the dependence of this evaluation on physician's subjective judgment, the results could be variable. The purpose of this study was to develop an automated scheme for the classification of pulmonary nodules using early and delayed phase PET/CT and conventional CT images.
We analysed 36 early and delayed phase PET/CT images in patients who underwent both PET/CT scan and lung biopsy, following bronchoscopy. In addition, conventional CT images at maximal inspiration were analysed. The images consisted of 18 malignant and 18 benign nodules. For the classification scheme, 25 types of shape and functional features were first calculated from the images. The random forest algorithm, which is a machine learning technique, was used for classification.
The evaluation of the characteristic features and classification accuracy was accomplished using collected images. There was a significant difference between the characteristic features of benign and malignant nodules with regard to standardised uptake value and texture. In terms of classification performance, 94.4% of the malignant nodules were identified correctly assuming that 72.2% of the benign nodules were diagnosed accurately. The accuracy rate of benign nodule detection by means of CT plus two-phase PET images was 44.4% and 11.1% higher than those obtained by CT images alone and CT plus early phase PET images, respectively.
Based on the findings, the proposed method may be useful to improve the accuracy of malignancy analysis.
正电子发射断层扫描/计算机断层扫描（PET/CT）检查常用于评估肺结节，因为它能提供解剖学和功能信息。然而，鉴于这种评估依赖于医生的主观判断，结果可能存在差异。本研究的目的是开发一种利用PET/CT早期和延迟期图像以及传统CT图像对肺结节进行分类的自动化方案。
我们分析了36例接受PET/CT扫描和肺活检（支气管镜检查后）患者的PET/CT早期和延迟期图像。此外，还分析了最大吸气时的传统CT图像。图像包括18个恶性结节和18个良性结节。对于分类方案，首先从图像中计算出25种形状和功能特征。采用随机森林算法（一种机器学习技术）进行分类。
利用收集到的图像完成了特征评估和分类准确性分析。良性和恶性结节在标准化摄取值和纹理方面的特征存在显著差异。在分类性能方面，假设72.2%的良性结节被准确诊断，94.4%的恶性结节被正确识别。通过CT加双期PET图像检测良性结节的准确率分别比单独使用CT图像和CT加早期PET图像高44.4%和11.1%。
基于这些发现，所提出的方法可能有助于提高恶性分析的准确性。
