Department of Gastrointestinal Oncology, Osaka International Cancer Institute, Osaka, Japan.
Department of Gastroenterology and Hepatology, Faculty of Life Sciences, Kumamoto University, Kumamoto, Japan.
Dig Endosc. 2021 Nov;33(7):1101-1109. doi: 10.1111/den.13934. Epub 2021 Feb 27.
Artificial intelligence (AI) systems have shown favorable performance in the detection of esophageal squamous cell carcinoma (ESCC). However, previous studies were limited by the quality of their validation methods. In this study, we evaluated the performance of an AI system with videos simulating situations in which ESCC has been overlooked.
We used 17,336 images from 1376 superficial ESCCs and 1461 images from 196 noncancerous and normal esophagi to construct the AI system. To record validation videos, the endoscope was passed through the esophagus at a constant speed without focusing on the lesion to simulate situations in which ESCC has been missed. Validation videos were evaluated by the AI system and 21 endoscopists.
We prepared 100 video datasets, including 50 superficial ESCCs, 22 noncancerous lesions, and 28 normal esophagi. The AI system had sensitivity of 85.7% (54 of 63 ESCCs) and specificity of 40%. Initial evaluation by endoscopists conducted with plain video (without AI support) had average sensitivity of 75.0% (47.3 of 63 ESCC) and specificity of 91.4%. Subsequent evaluation by endoscopists was conducted with AI assistance, which improved their sensitivity to 77.7% (P = 0.00696) without changing their specificity (91.6%, P = 0.756).
Our AI system had high sensitivity for the detection of ESCC. As a support tool, the system has the potential to enhance detection of ESCC without reducing specificity. (UMIN000039645).
人工智能（AI）系统在食管鳞状细胞癌（ESCC）的检测中表现出良好的性能。然而，之前的研究受到其验证方法质量的限制。在本研究中，我们评估了一个 AI 系统在模拟 ESCC 被忽视情况下的性能。
我们使用来自 1376 例浅层 ESCC 和 1461 例非癌和正常食管的 17336 张图像构建了 AI 系统。为了记录验证视频，内窥镜以恒定的速度穿过食管，不关注病变，以模拟 ESCC 被遗漏的情况。验证视频由 AI 系统和 21 名内镜医生进行评估。
我们准备了 100 个视频数据集，包括 50 例浅层 ESCC、22 例非癌病变和 28 例正常食管。AI 系统的敏感性为 85.7%（63 例 ESCC 中的 54 例），特异性为 40%。内镜医生在使用普通视频（无 AI 支持）进行初步评估时，敏感性平均为 75.0%（63 例 ESCC 中的 47.3 例），特异性为 91.4%。随后，内镜医生在 AI 辅助下进行评估，提高了敏感性至 77.7%（P=0.00696），而特异性不变（91.6%，P=0.756）。
我们的 AI 系统对 ESCC 的检测具有很高的敏感性。作为一种支持工具，该系统有可能在不降低特异性的情况下提高 ESCC 的检测率。（UMIN000039645）。
