首页|基于胸部三期计算机体层成像图像的纹理分析对鉴别肺内良恶性结节的价值

基于胸部三期计算机体层成像图像的纹理分析对鉴别肺内良恶性结节的价值

扫码查看
目的:分析胸部三期计算机体层成像(CT)图像的纹理分析对鉴别肺内良恶性结节的价值.方法:以2018年1月~2021年12月来本院就诊的109例肺结节病变的患者作为观察对象,上述患者均经病理证实,其结节共120个,对上述患者均实施平扫后进行胸部三期CT图像的纹理分析.结果:120个结节中,经病理证实,良性结节为69个,恶性结节51个,平扫结果的敏感度、特异度、准确率分别为47.06%、97.10%、75.83%,而胸部三期CT图像敏感度、特异度、准确率分别为49.02%、95.65%、75.83%,组间差异不存在统计学意义.结论:通过对一系列肺结节图像的纹理分析,能够得到结节的纹理特征参数集合,结合临床诊断结果,可为临床提供科学的数据,但在结节良恶性区分方面并无特殊价值.
The Value of Texture Analysis Based on Chest Three-Phase CT Images in Distinguishing Benign and Malignant Pulmonary Nodules
Objective:To analyze the value of texture analysis of third-stage CT images of chest in the identification of benign and malignant nodules in the lungs.Methods:A total of 109 patients with pulmonary nodule lesions who visited our hospital from January 2018 to December 2021 were selected as the observation subjects.All patients were confirmed by pathology and had a total of 120 nodules.Plain scans were performed on all patients and texture analysis of chest three-phase CT images was performed.Results:Among the 120 nodules,pathological confirmation showed 69 benign nodules and 51 malignant nodules.The sensitivity,specificity,and accuracy of plain scan results were 47.06%,97.10%,and 75.83%,respectively.However,the sensitivity,specificity,and accuracy of chest three-phase CT images were 49.02%,95.65%,and 75.83%,respectively.There was no statistically significant difference between the groups.Conclusion:Through the texture analysis of a series of pulmonary nodule images,the texture characteristic parameter set of nodules can be obtained,which can provide scientific data for clinical practice combined with clinical diagnosis results,but has no special value in distinguishing benign and malignant nodules.

chest three-phase CT imagestexture analysispulmonary benign and malignant nodules

刘建

展开 >

龙岩人民医院放射科(福建 龙岩 364000)

胸部三期CT图像 纹理分析 肺内良恶性结节

福建省龙岩市科技局联合资金项目

2020LYF17017

2024

中国医疗器械信息
中国医疗器械行业协会

中国医疗器械信息

影响因子:0.375
ISSN:1006-6586
年,卷(期):2024.30(7)
  • 27