Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan; Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama, Japan.
Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan.
Gastrointest Endosc. 2020 Feb;91(2):301-309.e1. doi: 10.1016/j.gie.2019.09.034. Epub 2019 Oct 1.
Diagnosing esophageal squamous cell carcinoma (SCC) depends on individual physician expertise and may be subject to interobserver variability. Therefore, we developed a computerized image-analysis system to detect and differentiate esophageal SCC.
A total of 9591 nonmagnified endoscopy (non-ME) and 7844 ME images of pathologically confirmed superficial esophageal SCCs and 1692 non-ME and 3435 ME images from noncancerous lesions or normal esophagus were used as training image data. Validation was performed using 255 non-ME white-light images, 268 non-ME narrow-band images/blue-laser images, and 204 ME narrow-band images/blue-laser images from 135 patients. The same validation test data were diagnosed by 15 board-certified specialists (experienced endoscopists).
Regarding diagnosis by non-ME with narrow-band imaging/blue-laser imaging, the sensitivity, specificity, and accuracy were 100%, 63%, and 77%, respectively, for the artificial intelligence (AI) system and 92%, 69%, and 78%, respectively, for the experienced endoscopists. Regarding diagnosis by non-ME with white-light imaging, the sensitivity, specificity, and accuracy were 90%, 76%, and 81%, respectively, for the AI system and 87%, 67%, and 75%, respectively, for the experienced endoscopists. Regarding diagnosis by ME, the sensitivity, specificity, and accuracy were 98%, 56%, and 77%, respectively, for the AI system and 83%, 70%, and 76%, respectively, for the experienced endoscopists. There was no significant difference in the diagnostic performance between the AI system and the experienced endoscopists.
Our AI system showed high sensitivity for detecting SCC by non-ME and high accuracy for differentiating SCC from noncancerous lesions by ME.
诊断食管鳞状细胞癌（SCC）取决于医生的个人专业知识，并且可能存在观察者间的差异。因此，我们开发了一种计算机图像分析系统来检测和区分食管 SCC。
共使用了 9591 张未经放大内镜（非-ME）和 7844 张 ME 图像，这些图像来自经病理证实的浅表食管 SCC 患者，以及 1692 张非癌性病变或正常食管的非-ME 和 3435 张 ME 图像，作为训练图像数据。使用 135 名患者的 255 张非-ME 白光图像、268 张非-ME 窄带成像/蓝激光图像和 204 张 ME 窄带成像/蓝激光图像进行了验证。15 名经过认证的专家（经验丰富的内镜医生）对相同的验证测试数据进行了诊断。
对于非-ME 窄带成像/蓝激光成像的诊断，人工智能（AI）系统的敏感性、特异性和准确性分别为 100%、63%和 77%，而经验丰富的内镜医生的分别为 92%、69%和 78%。对于非-ME 白光成像的诊断，AI 系统的敏感性、特异性和准确性分别为 90%、76%和 81%，而经验丰富的内镜医生的分别为 87%、67%和 75%。对于 ME 的诊断，AI 系统的敏感性、特异性和准确性分别为 98%、56%和 77%，而经验丰富的内镜医生的分别为 83%、70%和 76%。AI 系统和经验丰富的内镜医生在诊断性能方面没有显著差异。
我们的 AI 系统在非-ME 检测 SCC 方面具有高敏感性，在 ME 区分 SCC 与非癌性病变方面具有高准确性。
