白光内镜下实时人工智能检测胃局灶性病变并诊断肿瘤
本研究开发了基于深度学习的ENDOANGEL-LD系统,用于白光内镜下检测胃局灶性病变并预测肿瘤。回顾性图像来自武汉大学人民医院用于开发、验证和内测,另在5家医院进行外部测试。超过10000例接受上消化道内镜的患者纳入研究,内外部患者检测胃病变的敏感度分别为96.9%和95.6%,诊断肿瘤的敏感度分别为92.9%和91.7%。在100个视频中,ENDOANGEL-LD检测胃肿瘤的敏感度和阴性预测值优于专家(100% vs 85.5%±3.4% [P=.003] 和 100% vs 86.4%±2.8% [P=.002])。在2010例前瞻性连续患者中,检测胃病变的敏感度为92.8%,每次胃镜假阳性数为3.04±3.04,诊断肿瘤的敏感度和特异度分别为91.8%和92.4%。结论认为ENDOANGEL-LD在辅助内镜医师筛查胃病变和可疑肿瘤方面具有很大潜力。
要点
- ENDOANGEL-LD在白光内镜下检测胃局灶性病变敏感度达96.9%(内测)和95.6%(外测)。
- 诊断胃肿瘤敏感度内测92.9%、外测91.7%,前瞻性达91.8%且特异度92.4%。
- 在视频对比中,系统检测胃肿瘤的敏感度和阴性预测值均优于专家。
核心结论
- ENDOANGEL-LD在白光内镜下检测胃局灶性病变和诊断肿瘤具有较高敏感度,有潜力辅助内镜医师筛查。
研究设计与样本
- 回顾性收集武汉大学人民医院内镜图像用于系统开发、验证和内测,并在5家其他医院进行外部测试。
- 使用武汉大学人民医院存储视频比较ENDOANGEL-LD与专家的性能。
- 前瞻性连续纳入2021年5月6日至2021年8月2日在武汉大学人民医院接受上消化道内镜的患者评估临床适用性。
- 研究纳入超过10000例接受上消化道内镜的患者。
主要发现
- 内测和外测患者检测胃病变的敏感度分别为96.9%和95.6%,诊断肿瘤的敏感度分别为92.9%和91.7%。
- 在100个视频中,ENDOANGEL-LD检测胃肿瘤的敏感度为100%,专家为85.5%±3.4%(P=.003);阴性预测值系统为100%,专家为86.4%±2.8%(P=.002)。
- 在2010例前瞻性连续患者中,检测胃病变的敏感度为92.8%,每次胃镜假阳性数为3.04±3.04。
- 前瞻性队列中诊断肿瘤的敏感度为91.8%,特异度为92.4%。
临床怎么用
- ENDOANGEL-LD可作为白光内镜筛查胃局灶性病变和可疑肿瘤的辅助工具,帮助内镜医师提高检出和诊断能力。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND AND AIMS: White-light endoscopy (WLE) is the most pivotal tool to detect gastric cancer in an early stage. However, the skill among endoscopists varies greatly. Here, we aim to develop a deep learning-based system named ENDOANGEL-LD (lesion detection) to assist in detecting all focal gastric lesions and predicting neoplasms by WLE. METHODS: Endoscopic images were retrospectively obtained from Renmin Hospital of Wuhan University (RHWU) for the development, validation, and internal test of the system. Additional external tests were conducted in 5 other hospitals to evaluate the robustness. Stored videos from RHWU were used for assessing and comparing the performance of ENDOANGEL-LD with that of experts. Prospective consecutive patients undergoing upper endoscopy were enrolled from May 6, 2021 to August 2, 2021 in RHWU to assess clinical practice applicability. RESULTS: Over 10,000 patients undergoing upper endoscopy were enrolled in this study. The sensitivities were 96.9% and 95.6% for detecting gastric lesions and 92.9% and 91.7% for diagnosing neoplasms in internal and external patients, respectively. In 100 videos, ENDOANGEL-LD achieved superior sensitivity and negative predictive value for detecting gastric neoplasms from that of experts (100% vs 85.5% ± 3.4% [P = .003] and 100% vs 86.4% ± 2.8% [P = .002], respectively). In 2010 prospective consecutive patients, ENDOANGEL-LD achieved a sensitivity of 92.8% for detecting gastric lesions with 3.04 ± 3.04 false positives per gastroscopy and a sensitivity of 91.8% and specificity of 92.4% for diagnosing neoplasms. CONCLUSIONS: Our results show that ENDOANGEL-LD has great potential for assisting endoscopists in screening gastric lesions and suspicious neoplasms in clinical work. (Clinical trial registration number: ChiCTR2100045963.).
引用
- Wu L, Xu M, Jiang X, et al. Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos). Gastrointest Endosc. 2021. PMID: 34547254. doi:10.1016/j.gie.2021.09.017
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。