【打印本页】 【下载PDF全文】 【HTML】 查看/发表评论下载PDF阅读器关闭

←前一篇|后一篇→

过刊浏览    高级检索

本文已被:浏览 1601次   下载 1317 本文二维码信息
码上扫一扫!
基于迁移学习的胃镜图像识别模型的构建及其在胃癌诊断中的应用
张菁1,钟绿1,杜岗2,江向武1,汤绍辉1*
0
(1. 暨南大学附属第一医院消化内科, 广州 510630;
2. 南方医科大学珠江医院检验医学部, 广州 510515
*通信作者)
摘要:
目的 采用迁移学习技术构建胃镜图像识别模型,探讨其对胃癌的诊断价值。方法 收集2 001例胃癌、2 119例胃溃疡、2 168例慢性胃炎患者的普通清晰白光胃镜图像,将其分为训练集图像组(1 851例胃癌、1 969例胃溃疡和2 018例慢性胃炎图像)和测试集图像组(胃癌、胃溃疡及慢性胃炎各150例图像)。选择在ILSVRC(ImageNet Large-Scale Visual Recognition Challenge)赛中的冠军模型VGG19、ResNet50和Inception-V3作为预训练模型,将其改造后进行模型训练,用训练集图像训练上述3个模型,用测试集图像对模型进行验证,整个模型训练过程分成预训练和微调2个步骤。结果 在3个模型中,ResNet50模型验证准确度最高,对胃癌、胃溃疡及慢性胃炎的诊断准确度分别达93%、92%及88%。结论 基于迁移学习技术,利用ResNet50模型建立的胃镜图像识别软件模型可以较准确地区分胃癌与良性胃疾病(胃溃疡和慢性胃炎)。
关键词:  人工智能  迁移学习  胃镜检查  图像识别模型  胃肿瘤
DOI:10.16781/j.0258-879x.2019.05.0483
投稿时间:2018-11-17修订日期:2019-01-26
基金项目:
Construction of gastroscopic image recognition model based on transfer learning and its application in gastric cancer diagnosis
ZHANG Jing1,ZHONG Lü1,DU Gang2,JIANG Xiang-wu1,TANG Shao-hui1*
(1. Department of Gastroenterology, the First Affiliated Hospital of Jinan University, Guangzhou 510630, Guangdong, China;
2. Division of Laboratory Medicine, Zhujiang Hospital, Southern Medical University, Guangzhou 510515, Guangdong, China
*Corresponding author)
Abstract:
Objective To construct a gastroscopic image recognition model based on transfer learning and to explore its diagnostic value for gastric cancer. Methods The clear white-light gastroscopic images from 2 001 gastric cancer patients, 2 119 gastric ulcer patients and 2 168 chronic gastritis patients were collected. All these images were divided into training set image group (1 851 gastric cancer, 1 969 gastric ulcer, and 2 018 chronic gastritis) and testing set image group (150 gastric cancer, 150 gastric ulcer, and 150 chronic gastritis). Champion models VGG19, ResNet50 and Inception-V3 in ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) competition were used as pre-trained models. These models were revised for model training. The training set images were assigned to train the above 3 models, and the testing set images were assigned to validate the models. The whole training process was divided into 2 steps (pre-training and finetuning). Results It was found that ResNet50 ranked No.1 in terms of testing accuracy. Its diagnostic accuracy for gastric cancer, gastric ulcer and chronic gastritis reached 93%, 92% and 88%, respectively. Conclusion Based on transfer learning, the gastroscopic image recognition software model constructed by ResNet50 model can more accurately differentiate gastric cancer from benign gastric diseases (gastric ulcer and chronic gastritis).
Key words:  artificial intelligence  transfer learning  gastroscopy  image recognition model  stomach neoplasms