基于深度学习的X线造影中肾上腺血管关键帧识别算法  

Deep Learning-Based Key Frame Recognition Algorithm for Adrenal Vascular in X-Ray Imaging

作　　者：陶慧敏 黄淼 刘琮 刘永田 胡志华[1] 陶莉莉[1] 张淑平 TAO Huimin;HUANG Miao;LIU Cong;LIU Yongtian;HU Zhihua;TAO Lili;ZHANG Shuping(School of Intelligent Manufacturing and Control Engineering,Shanghai Polytechnic University,Shanghai,201209;School of Computer and Information Engineering,Shanghai Polytechnic University,Shanghai,201209;Department of Internet of Things Engineering,Shanghai Business School,Shanghai,201400;Urinary Surgery,Shandong First Medical University Affiliated Qingzhou Hospital,Qingzhou,262500)

机构地区：[1]上海第二工业大学智能制造与控制工程学院,上海市201209 [2]上海第二工业大学计算机与信息工程学院,上海市201209 [3]上海商学院物联网工程系,上海市201400 [4]山东第一医科大学附属青州医院泌尿科,青州市262500

出　　处：《中国医疗器械杂志》2024年第2期138-143,共6页Chinese Journal of Medical Instrumentation

基　　金：国家自然科学基金(62003205,62203291);中国博士后科学基金(2021M690481);上海市自然科学基金(20ZR1440300)。

摘　　要：原发性醛固酮增多症的分型诊断需进行肾上腺静脉取样,肾上腺静脉出现的帧称为关键帧。目前,关键帧的选取依赖于医生肉眼判断,耗时费力。该研究提出基于深度学习的关键帧识别算法。首先,采用小波去噪和多尺度血管增强滤波的方法,保留肾上腺静脉的形态特征。接着,结合自注意机制,得到改进的识别模型ResNet50-SA。与常用的迁移学习相比,新模型在准确率、精确度查准率、召回率、F1和AUC上都达到97.11%,优于其他模型,可帮临床医生快速识别肾上腺静脉中的关键帧。Adrenal vein sampling is required for the staging diagnosis of primary aldosteronism,and the frames in which the adrenal veins are presented are called key frames.Currently,the selection of key frames relies on the doctor's visual judgement which is time-consuming and laborious.This study proposes a key frame recognition algorithm based on deep learning.Firstly,wavelet denoising and multi-scale vessel-enhanced filtering are used to preserve the morphological features of the adrenal veins.Furthermore,by incorporating the self-attention mechanism,an improved recognition model called ResNet50-SA is obtained.Compared with commonly used transfer learning,the new model achieves 97.11%in accuracy,precision,recall,F1,and AUC,which is superior to other models and can help clinicians quickly identify key frames in adrenal veins.

关 键 词：迁移学习 自注意机制 小波变换 关键帧识别 肾上腺血管造影 

分 类 号：R445[医药卫生—影像医学与核医学] R814.43[医药卫生—诊断学]