Classification and diagnosis of cervical lesions based on colposcopy images using deep fully convolutional networks:A man-machine comparison cohort study  

作　　者：Binhua Dong Huifeng Xue Ye Li Ping Li Jiancui Chen Tao Zhang Lihua Chen Diling Pan Peizhong Liu Pengming Sun 

机构地区：[1]Laboratory of Gynecologic Oncology,Department of Gynecology,Fujian Maternity and Child Health Hospital,College of Clinical Medicine for Obstetrics&Gynecology and Pediatrics,Fujian Medical University,Fuzhou 350001,China [2]Fujian Key Laboratory of Women and Children's Critical Diseases Research,Fuzhou 350001,China [3]Medical Center of Cervical Disease and Colposcopy,Fujian Maternity and Child Health Hospital,Fuzhou 350001,China [4]Department of Gynecology and Obstetrics,Quanzhou First Hospital,Fujian Medical University,Quanzhou 362000,China [5]College of Computer Science and Technology,Huaqiao University,Xiamen 361021,China [6]Department of Pathology,Fujian Maternity and Child Health Hospital,Fuzhou 350001,China [7]College of Engineering,Huaqiao University,Quanzhou 362021,China [8]School of Medicine,Huaqiao University,Quanzhou 362021,China

出　　处：《Fundamental Research》2025年第1期419-428,共10页自然科学基础研究(英文版)

基　　金：supported by grants from the National Key R&D Program of China(2021YFC2701205);the National Natural Science Foundation of China(82271658);the Fujian Provincial Natural Science Foundation of China(2021J01408,2021J01403);the Fujian Provincial Health and Education Joint Project(2019-WJ-05);the Fujian Provincial Health Commission Innovation Project(2019-CX-7).

摘　　要：Colposcopy is an important technique in the diagnosis of cervical cancer.The development of computer-aided diagnosis methods can mitigate the shortage of colposcopists and improve the accuracy and efficiency of colposcopy examinations in China.This study proposes the Dense-U-Net model for colposcopy image recognition.This was a man–machine comparison cohort study.It presents a novel artificial intelligence(AI)model for the diagnosis of cervical lesions through colposcopy images using a Dense-U-Net image semantic segmentation algorithm.The Dense-U-Net model was created by applying the methods of“deepening the network structure,”“applying dropout”and“max pooling.”Moreover,image-based and population-based diagnostic performances of the AI algorithm and physicians with different levels of specialist experience were compared.In total,2,475 participants were recruited,and 13,084 colposcopy images were included in this study.The diagnostic accuracy of the Dense-U-Net model increased significantly with increasing colposcopy images per patient.As the number of images in the training set increased,the diagnostic accuracy of the Dense-U-Net model for cervical intraepithelial neoplasm 3 or worse(CIN3+)diagnosis increased(P=0.035).The rate of diagnostic accuracy(0.89 vs 0.85,P<0.001)of CIN3+lesions using the Dense-U-Net model was higher than that of expert colposcopists,and the missed diagnosis(0.06 vs 0.07,P=0.002)and false positive(0.05 vs 0.08,P<0.001)were lower.Moreover,Dense-U-Net is more accurate in diagnosing the type III cervical transformation zone,which is difficult to diagnose by experts(P<0.001).The Dense-U-Net model also showed higher diagnostic accuracy for CIN3+in an independent test set(P<0.001).To diagnose the same 870 test images,the Dense-U-Net system took 1.76±0.09 min,while the expert,senior,and junior colposcopists took 716.3±49.76,892.1±92.30,and 3034.7±259.51 min,respectively.The study successfully built a reliable,quick,and effective Dense-U-Net model to assist with colposcopy examin

关 键 词：Cervical lesions Dense-U-Net Colposcopic image Lesion segmentation Auxiliary diagnosis 

分 类 号：R711.74[医药卫生—妇产科学]