基于3D卷积神经网络的中耳疾病高分辨率CT图像辅助分类诊断模型的应用  

Application of high resolution computed tomography image assisted classification model of middle ear diseases based on 3D-convolutional neural network

作　　者：粟日 宋剑 汪政 卯爽 毛弈韬[5] 吴学文[2,3,4] 侯木舟 SU Ri;SONG Jian;WANG Zheng;MAO Shuang;MAO Yitao;WU Xuewen;HOU Muzhou(School of Mathematics and Statistics,Central South University,Changsha 410083;Department of Otorhinolaryngology,Xiangya Hospital,Central South University,Changsha 410008;Hunan Provincial Key Laboratory of Major Otorhinolaryngology Diseases,Changsha 410008;National Clinical Research Center for Geriatric Diseases,Xiangya Hospital,Changsha 410008;Department of Imaging,Xiangya Hospital,Central South University,Changsha 410008,China)

机构地区：[1]中南大学数学与统计学院,长沙410083 [2]中南大学湘雅医院耳鼻咽喉科,长沙410008 [3]耳鼻咽喉重大疾病湖南省重点实验室,长沙410008 [4]国家老年疾病临床医学研究中心(湘雅医院),长沙410008 [5]中南大学湘雅医院影像科,长沙410008

出　　处：《中南大学学报（医学版）》2022年第8期1037-1048,共12页Journal of Central South University ：Medical Science

基　　金：国家自然科学基金(81700923);中国博士后科学基金(2021M693566,2021T140751);湖南省自然科学基金(2021JJ31108,2021JJ41017);湖南省科技创新人才计划(2020RC2013)。

摘　　要：目的:慢性化脓性中耳炎(chronic suppurative otitis media, CSOM)和中耳胆脂瘤(middle ear cholesteatoma,MEC)是两类临床上最常见的慢性中耳疾病。在诊疗过程中,该两类疾病因具有类似的临床表现,容易造成误诊及漏诊。高分辨率计算机断层扫描(high resolution computed tomography,HRCT)能清晰地显示颞骨的精细解剖结构,准确地反映中耳病变情况及病变范围,对慢性中耳疾病的鉴别诊断具有优势。本研究开发一种基于颞骨HRCT影像数据,对慢性中耳疾病实施自动信息提取与分类诊断的深度学习模型,旨在提高临床上对慢性中耳疾病的分类诊断效率,减少漏诊及误诊的发生。方法:回顾性收集2018年1月至2020年10月于湘雅医院耳鼻咽喉科住院的慢性中耳疾病患者的临床病历及颞骨HRCT影像资料。由2名经验丰富的耳鼻咽喉科医师独立审查患者的医疗记录,并对最终诊断达成一致结论。最终纳入499例患者(998侧耳),将998侧耳分为3组:MEC组(108侧耳)、CSOM组(622侧耳)、正常组(268侧耳)。使用不同方差的高斯噪声进行数据集样本扩增处理,以此消除组间样本数量的不平衡。经扩增后的实验数据集样本量为1 806侧耳,实验中随机选择75%(1 355侧耳)用于训练,10%(180侧耳)用于验证,剩余的15%(271侧耳)用于测试并评估模型性能。模型整体设计为串联式结构,设置具有3种不同功能的深度学习模型:第一种是区域推荐网络算法,从整体HRCT图像中搜索中耳部分的图像进行切割、保存;第二种是基于孪生网络结构的图像对比卷积神经网络(convolutional neural network,CNN),从切割好的图像中搜索与HRCT图像关键层面匹配的图像,并进行3D数据块的构建与保留;第三种是基于3D-CNN操作,用于对3D数据块进行分类诊断,并给出最后的预测概率。结果:基于孪生网络结构的特殊层面搜索网络在10个特殊层面上表现出了0.939的平均AUC值。基于3D-CObjective: Chronic suppurative otitis media(CSOM) and middle ear cholesteatoma(MEC) are the 2 most common chronic middle ear diseases. In the process of diagnosis and treatment, the 2 diseases are prone to misdiagnosis and missed diagnosis due to their similar clinical manifestations. High resolution computed tomography(HRCT) can clearly display the fine anatomical structure of the temporal bone, accurately reflect the middle ear lesions and the extent of the lesions, and has advantages in the differential diagnosis of chronic middle ear diseases. This study aims to develop a deep learning model for automatic information extraction and classification diagnosis of chronic middle ear diseases based on temporal bone HRCT image data to improve the classification and diagnosis efficiency of chronic middle ear diseases in clinical practice and reduce the occurrence of missed diagnosis and misdiagnosis.Methods: The clinical records and temporal bone HRCT imaging data for patients with chronic middle ear diseases hospitalized in the Department of Otorhinolaryngology,Xiangya Hospital from January 2018 to October 2020 were retrospectively collected. The patient’s medical records were independently reviewed by 2 experienced otorhinolaryngologist and the final diagnosis was reached a consensus. A total of 499patients(998 ears) were enrolled in this study. The 998 ears were divided into 3 groups: an MEC group(108 ears), a CSOM group(622 ears), and a normal group(268 ears). The Gaussian noise with different variances was used to amplify the samples of the dataset to offset the imbalance in the number of samples between groups. The sample size of the amplified experimental dataset was 1 806 ears. In the study, 75%(1 355) samples were randomly selected for training, 10%(180) samples for validation, and the remaining 15%(271) samples for testing and evaluating the model performance. The overall design for the model was a serial structure, and the deep learning model with 3 different functions was set up. The first model was the

关 键 词：慢性化脓性中耳炎 中耳胆脂瘤 孪生网络 3D卷积神经网络 

分 类 号：R764.21[医药卫生—耳鼻咽喉科]