摘要
目的应用深度学习图像识别网络ResNet-18,基于临床拍摄视频,建立猝倒面容预测模型。方法本研究为横断面研究,收集2020至2023年在南昌大学第二附属医院首诊未经治疗的1型发作性睡病患者25例及健康对照25名,采集的图像预处理后,共获得1180张图片,其中583张猝倒面容,597张正常面容。从中抽取90%作为训练集与验证集,随后数据扩增5倍,扩充后的数据集抽取80%作为训练集,20%作为验证集,即训练集数量为(583+597)×0.9×0.8×5=4248,验证集数量为(583+597)×0.9×0.2×5=1062,训练集与验证集用于训练参数建立模型,并通过五折交叉验证法进行训练,构建采用迁移学习方式的ResNet-18猝倒面容识别模型。原未扩增前图像抽取10%(118张)作为测试集,测试集数据不参与数据增强和模型训练,仅用于测试模型最终效果。最后将ResNet-18与VGG-16、ResNet-34和Inception V3深度学习模型进行比较,用受试者工作特征曲线评估ResNet-18图像识别网络在猝倒面容识别中的价值。结果25例1型发作性睡病患者中,男15例,女10例,年龄[M(Q_(1),Q_(3))]为14.0(11.0,20.5)岁;25名健康对照者中,男14名,女11名,年龄16.0(14.4,23.0)岁。ResNet-18图像识别网络在测试集中的总体准确率为90.9%,灵敏度为96.4%,特异度为85.2%,受试者工作特征曲线下面积为0.99(95%CI:0.96~1.00)。ResNet-18模型参数量为11.69 M,浮点运算量为1824.03 M,单张图片识别时间为5.9 ms。结论基于深度学习图像识别网络ResNet-18构建的猝倒面容预测模型在猝倒面容的识别上有较高的准确率。
Objective To establish a prediction model for the identifying of cataplexy facial features based on clinical shooting videos by using a deep learning image recognition network ResNet-18.Methods A cross-sectional study.Twenty-five narcolepsy type 1 patients who were first diagnosed and never received treatment and 25 healthy controls recruited by advertisement in the Second Affiliated Hospital of Nanchang University from 2020 to 2023.After image preprocessing,a total of 1180 images were obtained,including 583 cataplexy faces and 597 normal faces.90%were selected as the training set and validation set,and then expanded the data by 5 times.80%of the expanded data set was extracted as the training set and 20%as the validation set,that is,the number of the training set was(583+597)×0.9×0.8×5=4248,the number of the validation set was(583+597)×0.9×0.2×5=1062.The data sets for training and validation were used train parameters to establish the model and were trained through the five-fold cross-validation method,to establish the ResNet-18 cataplexy face recognition model via transfer learning.10%(118 images)of the original non-amplified images were extracted as the test set.The test set data did not participate in data enhancement and model training,and was only used to evaluate the final performance of the model.Finally,ResNet-18 was compared with VGG-16,ResNet-34 and Inception V3 deep learning models,and the receiver operating characteristic curve was used to evaluate the value of ResNet-18 image recognition network in cataplexy face recognition.Results Among 25 patients with narcolepsy type 1,15 were males and 10 were females,aged[M(Q_(1),Q_(3))]of 14.0(11.0,20.5)years.Among 25 healthy controls,14 were males and 11 were females,with a median age of 16.0(14.4,23.0)years.The overall accuracy of ResNet-18 image recognition network in the test set was 90.9%,the sensitivity was 96.4%and the specificity was 85.2%.The area under the ROC curve was 0.99(95%CI:0.96-1.00).The ResNet-18 model parameter amount was 11.69 M,the floating point operation amount was 1824.03 M,and the single image recognition time was 5.9 ms.Conclusions The cataplexy face prediction model built based on the deep learning image recognition network ResNet-18 has a high accuracy in identifying cataplexy faces.
作者
袁于青
朱银
陈邦占
尹天天
柯青
谢亮
Yuan Yuqing;Zhu Yin;Chen Bangzhan;Yin Tiantian;Ke Qing;Xie Liang(Department of Neurology,the Second Affiliated Hospital,Jiangxi Medical College,Nanchang University,Nanchang 330006,China;School of Mathematics and Computer Sciences,Nanchang University,Nanchang 330006,China;Queen Mary University of London,Nanchang University,Nanchang 330006,China;Department of Neurology,the First Affiliated Hospital,Zhejiang University School of Medicine,Hangzhou 310003,China)
出处
《中华医学杂志》
CAS
CSCD
北大核心
2024年第27期2549-2555,共7页
National Medical Journal of China
基金
国家自然科学基金(32160194)
江西省双千人才课题(jxsp2023102164)
关键词
发作性睡病
猝倒
人工智能
图像处理
横断面研究
Narcolepsy
Cataplexy
Artificial intelligence
Image processing
Cross-sectional study
