期刊论文

Machine learning-based classification model of lymph node metastasis in nasopharyngeal carcinoma

中文

中国医学物理学杂志

1005-202X

2019

36

11

1350-1355

10.3969/j.issn.1005-202X.2019.11.020

国家自然科学基金（81770928）；

本校为其他机构

目的:研究使用机器学习与影像组学建立用于鼻咽癌CT图像中鉴别转移淋巴结的模型。方法:选择50例鼻咽癌患者初诊CT平扫及静脉灌注增强图像及18F-FGD-PET图像,患者均经病理及PET检查证实为鼻咽癌伴局部淋巴结转移。手动勾画患者CT图像中体积>1 cm3的淋巴结,由18F-FGD-PET图像中对应区域SUVmax>2.5及现行影像学标准作为转移与否的分类标准。研究中共获得143枚淋巴结,其中转移淋巴结103枚。使用机器学习方法对上述分类结果进行训练,其中列入训练组淋巴结100枚,验证组43枚,分组方式为随机分组以避免特定的分组方式造成的系统误差。结果:机器学习过程中获得由淋巴结体积、最大横截面短轴及数个影像组学...

Objective To establish a model for identifying metastatic lymph nodes in CT images of nasopharyngeal carcinoma with the use of machine learning and radiomics. Methods The plain CT, intravenous perfusion enhancement and ~(18)F-FGD-PET images of 50 pre-treatment patients with nasopharyngeal carcinoma were analyzed in the study.All patients were confirmed by pathological and PET examinations as nasopharyngeal carcinoma with local lymph node metastasis. The lymph nodes with a volume >1 cm~3 in CT image were manually delineated, and the maximum stan...