基于残差网络自动识别肝脏增强CT期相的研究  

Automatic identification of liver CT contrast-enhanced phases based on residual network

作　　者：刘千荷 蒋佳慧 徐辉 吴柯薇 张艳[3] 孙楠 罗佳文[5] 巴特[6] 吕爱清 刘川鄂 尹祎宇 杨正汉 LIU Qianhe;JIANG Jiahui;XU Hui;WU Kewei;ZHANG Yan;SUN Nan;LUO Jiawen;BA Te;LüAiqing;LIU Chuan’e;YIN Yiyu;YANG Zhenghan(School of Medical Technology,Shaanxi University of Chinese Medicine,Xianyang,Shaanxi Province 712046,China;Department of Radiology,Beijing Friendship Hospital,Capital Medical University,Beijing 100050,China;Department of Radiology,Peking University Third Hospital,Beijing 100191,China;Department of Radiology,Peking University Cancer Hospital,Beijing 100142,China;Department of Radiology,the Second Affiliated Hospital of Dalian Medical University,Dalian 116023,China;Department of Radiology,the First Hospital of Fangshan District,Beijing 102400,China;Department of Radiology,Beijing Zhongguancun Hospital,Beijing 100190,China;Shanghai United Imaging Intelligence Co.,Ltd.,Shanghai 201807,China)

机构地区：[1]陕西中医药大学医学技术学院,陕西咸阳712046 [2]首都医科大学附属北京友谊医院放射科,北京100050 [3]北京大学第三医院放射科,北京100191 [4]北京大学肿瘤医院放射科,北京100142 [5]大连医科大学附属第二医院放射科,辽宁大连116023 [6]北京市房山区第一医院放射科,北京102400 [7]北京市中关村医院放射科,北京100190 [8]上海联影智能医疗科技有限公司,上海201807

出　　处：《实用放射学杂志》2024年第4期572-576,共5页Journal of Practical Radiology

基　　金：北京联影智能影像技术研究院基金项目(CRIBJQY202101);国家自然科学基金项目(62171298)。

摘　　要：目的开发并验证自动识别肝脏增强CT期相的深度学习模型。方法回顾性收集行肝脏增强CT患者图像766例,用于构建3期增强期相分类模型和动脉期(AP)分类模型,将肝脏增强CT各期相自动识别为动脉早期(EAP)或动脉晚期(LAP)、门脉期(PVP)、平衡期(EP)。此外,回顾性收集5家不同医院行肝脏增强CT患者图像221例,用于模型外部验证。以放射科医师标注结果为参考标准,评估模型效能。结果在外部验证集中,模型识别各增强期相准确率达到90.50%~99.70%。结论基于残差网络构建的肝脏增强CT期相自动识别模型有望提供高效、客观、统一的图像质量控制工具。Objective To develop and validate a deep learning model for automatic identification of liver CT contrast-enhanced phases.Methods A total of 766 patients with liver CT contrast-enhanced images were retrospectively collected.A three-phase classification model and an arterial phase(AP)classification model were developed,so as to automatically identify liver CT contrast-enhanced phases as early arterial phase(EAP)or late arterial phase(LAP),portal venous phase(PVP),and equilibrium phase(EP).In addition,221 patients with liver CT contrast-enhanced images in 5 different hospitals were used for external validation.The annotation results of radiologists were used as a reference standard to evaluate the model performances.Results In the external validation datasets,the accuracy in identifying each enhanced phase reached to 90.50%-99.70%.Conclusion The automatic identification model of liver CT contrast-enhanced phases based on residual network may provide an efficient,objective,and unified image quality control tool.

关 键 词：肝脏 深度学习 计算机体层成像 质量控制 

分 类 号：R333.4[医药卫生—人体生理学] TP181[医药卫生—基础医学] R814.42[自动化与计算机技术—控制理论与控制工程]