基于人工智能深度学习算法辅助诊断早期ESCC的研究
Deep learning algorithm based on artificial intelligence to assist the diagnosis of early ESCC
王娜 1温静 2冯佳 3卢娜利 4刘翠华 2智佳 3王子阳 4黄锦4
作者信息
- 1. 新乡医学院研究生院,河南 新乡 453003;中国人民解放军联勤保障部队第九八八医院消化内科
- 2. 中国人民解放军联勤保障部队第九八四医院消化内科
- 3. 中国人民解放军联勤保障部队第九八〇医院消化内科
- 4. 中国人民解放军联勤保障部队第九八八医院消化内科
- 折叠
摘要
目的 探讨基于人工智能(artificial intelligence,AI)深度学习算法的内镜识别系统在胃镜诊疗过程中对早期ESCC检出率的研究.方法 选取中国人民解放军联勤保障部队第九八八医院、中国人民解放军联勤保障部队第九八四医院及中国人民解放军联勤保障部队第九八〇医院三个消化内镜中心 2018 年 6 月至 2020 年 6 月早期ESCC、ESCC、食管隆起性病变以及食管憩室的白光图像、碘染色图像.通过训练和验证不同的目标检测模型和实例分割模型,最终选取表现最优的目标检测模型Yolov 5 和实例分割模型Yolact++共同构建 AI"嵌合模型",评估该模型诊断早期 ESCC的性能.结果 AI"嵌合模型"对早期 ESCC诊断的敏感度为 95.60%,特异度为 91.60%,准确率为 90.70%,均优于单模型.结论 本研究构建的 AI"嵌合模型"可显著提高早期 ESCC的检出率.
Abstract
Objective To establish an artificial intelligence-aided diagnosis model to improve the detection rate of early ESCC.Methods White light images,iodine staining images and complete videos of early ESCC,ESCC,esopha-geal protuberant lesions and esophageal diverticulum were selected from 3 digestive endoscopic centers of the 988th Hos-pital of PLA Joint Logistics Support Force,the 984th Hospital of PLA Joint Logistics Support Force,and the 980th Hos-pital of PLA Joint Logistics Support Force from Jun.2018 to Jun.2020.The lesions in the picture were marked with rectangles and polygons,which were divided into training set,verification set and test set.Through training and verif-ying different target detection models and case segmentation models,the best target detection model Yolov 5 and case segmentation model Yolact++ were selected to construct AI ″chimera model″.Finally,the performance of AI ″chimeric model″ in the diagnosis of early ESCC was evaluated.Results The sensitivity,specificity and accuracy of AI ″chimeric model″ in the diagnosis of early ESCC were 95.60%,91.60%and 90.70%,respectively.Conclusion The AI ″chime-ric model″ constructed in this study can significantly improve the detection rate of early ESCC.
关键词
人工智能/深度学习/实例分割/食管鳞状细胞癌/碘染色Key words
Artificial intelligence/Deep learning/Instance segmentation/Esophageal squamous cell carcinoma/Iodine staining引用本文复制引用
基金项目
河南省医学科技攻关计划科研项目(LHGJ20190881)
出版年
2024
NETL
NSTL
维普
万方数据