Comparison of performances of artificial intelligence versus expert endoscopists for real-time assisted diagnosis esophageal sauamous cell carcinoma (with video)
Comparison of performances of artificial intelligence versus expert endoscopists for real-time assisted diagnosis esophageal sauamous cell carcinoma (with video)
复制标题
DOI：
10.1016/j.gie.2020.05.043
复制
发表时间：
2020-10-01
影响因子：
7.7
通讯作者：
Tada, Tomohiro
中科院分区：
文献类型：
--
作者：
Fukuda, Hiromu;Ishihara, Ryu;Tada, Tomohiro
背景和目的：窄带成像（NBI）目前被认为是诊断食管鳞状细胞癌（SCC）的标准方法。我们开发了一个计算机图像分析系统NBI诊断食管鳞癌和评估其性能与视频images. Altogether，23,746图像从1544病理证实的浅表食管SCC和4587图像从4587非癌和正常组织被用来构建一个人工智能（AI）系统。通过NBI或蓝光成像捕获的来自144名患者的5至9秒视频片段被用作验证数据集。这些视频图像由AI系统和13名委员会认证的专家（专家）进行诊断。结果：诊断过程分为2部分：检测（识别可疑病变）和表征（区分癌症和非癌症）。AI系统检测SCC的灵敏度、特异性和准确性分别为91%、51%和63%，专家分别为79%、72%和75%。AI系统的灵敏度明显高于专家，但其特异性明显低于专家。AI系统对SCC表征的敏感性、特异性和准确性分别为86%、89%和88%，专家分别为74%、76%和75%。受试者工作特征曲线显示，AI系统有显着更好的诊断性能比experts.Conclusions：我们的AI系统显示出显着更高的灵敏度检测SCC和更高的准确性，从非癌组织SCC特征比内镜专家。
Background and Aims: Narrow-band imaging (NBI) is currently regarded as the standard modality for diagnosing esophageal squamous cell carcinoma (SCC). We developed a computerized image-analysis system for diagnosing esophageal SCC by NBI and estimated its performance with video images.Methods: Altogether, 23,746 images from 1544 pathologically proven superficial esophageal SCCs and 4587 images from 4587 noncancerous and normal tissue were used to construct an artificial intelligence (AI) system. Five- to 9-second video clips from 144 patients captured by NBI or blue-light imaging were used as the validation dataset. These video images were diagnosed by the AI system and 13 board-certified specialists (experts).Results: The diagnostic process was divided into 2 parts: detection (identify suspicious lesions) and characterization (differentiate cancer from noncancer). The sensitivities, specificities, and accuracies for the detection of SCC were, respectively, 91%, 51%, and 63% for the AI system and 79%, 72%, and 75% for the experts. The sensitivity of the AI system was significantly higher than that of the experts, but its specificity was significantly lower. Sensitivities, specificities, and accuracy for the characterization of SCC were, respectively, 86%, 89%, and 88% for the AI system and 74%, 76%, and 75% for the experts. The receiver operating characteristic curve showed that the AI system had significantly better diagnostic performance than the experts.Conclusions: Our AI system showed significantly higher sensitivity for detecting SCC and higher accuracy for characterizing SCC from noncancerous tissue than endoscopic experts.