Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus
Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus
复制标题
DOI：
10.1007/s10388-018-0651-7
复制
发表时间：
2019-04-01
期刊：
影响因子：
2.4
通讯作者：
Tada, Tomohiro
中科院分区：
文献类型：
--
作者：
Kumagai, Youichi;Takubo, Kaiyo;Tada, Tomohiro
背景与目的内吞镜系统（ECS）有助于组织的虚拟实现，有助于在体内确定组织诊断。我们建议用ECS代替食管鳞状细胞癌（ESCC）的活检组织学。我们应用深度学习人工智能（AI）来分析食管的ECS图像，以确定AI是否可以支持内窥镜医生替代基于活检的组织学。方法基于GoogLeNet构建基于卷积神经网络的人工智能，并使用4715张食管ECS图像（1141张为恶性图像，3574张为非恶性图像）进行训练。为了评估AI的诊断准确性，我们对55例连续患者（27例escc和28例良性食管病变）的1520张ECS图像进行了独立测试。结果经受体-工作特征曲线分析，总图像、高倍率图像和低倍率图像的曲线下面积分别为0.85、0.90和0.72。在27例ESCC病例中，人工智能正确诊断了25例，总体敏感性为92.6%。28个非癌性病变中有25个被诊断为非恶性，特异性为89.3%，总体准确率为90.9%。2例恶性病变被人工智能误诊为非恶性，经内镜医师正确诊断为恶性。在3例经人工智能诊断为恶性的非癌性病变中，2例为放射相关性食管炎，1例为胃食管反流病。结论人工智能有望支持内镜医师根据ECS图像诊断ESCC，而无需基于活检的组织学参考。
Background and aimsThe endocytoscopic system (ECS) helps in virtual realization of histology and can aid in confirming histological diagnosis in vivo. We propose replacing biopsy-based histology for esophageal squamous cell carcinoma (ESCC) by using the ECS. We applied deep-learning artificial intelligence (AI) to analyse ECS images of the esophagus to determine whether AI can support endoscopists for the replacement of biopsy-based histology.MethodsA convolutional neural network-based AI was constructed based on GoogLeNet and trained using 4715 ECS images of the esophagus (1141 malignant and 3574 non-malignant images). To evaluate the diagnostic accuracy of the AI, an independent test set of 1520 ECS images, collected from 55 consecutive patients (27 ESCCs and 28 benign esophageal lesions) were examined.ResultsOn the basis of the receiver-operating characteristic curve analysis, the areas under the curve of the total images, higher magnification pictures, and lower magnification pictures were 0.85, 0.90, and 0.72, respectively. The AI correctly diagnosed 25 of the 27 ESCC cases, with an overall sensitivity of 92.6%. Twenty-five of the 28 non-cancerous lesions were diagnosed as non-malignant, with a specificity of 89.3% and an overall accuracy of 90.9%. Two cases of malignant lesions, misdiagnosed as non-malignant by the AI, were correctly diagnosed as malignant by the endoscopist. Among the 3 cases of non-cancerous lesions diagnosed as malignant by the AI, 2 were of radiation-related esophagitis and one was of gastroesophageal reflux disease.ConclusionAI is expected to support endoscopists in diagnosing ESCC based on ECS images without biopsy-based histological reference.