用白光内镜检测早期胃癌的深度学习:系统性审查和元分析
Jixiang Liu1, Danyan Li1, Yudi Zhuo1
1Department of Gastroenterology, Beijing Traditional Chinese Medicine Hospital, Capital Medical University, Beijing, China.
Frontiers in artificial intelligence
|February 16, 2026
概括
深度学习算法在从内镜图像中诊断早期胃癌时显示出高准确度. 他们的表现与专家内镜师相当,使他们成为有价值的临床决策支持工具.
科学领域:
- 医疗成像医学成像
- 人工智能在医学中的应用
- 胃肠病学 胃肠病学
背景情况:
- 早期胃癌 (EGC) 诊断严重依赖于内镜成像.
- 准确检测EGC对于患者的治疗结果至关重要.
- 人类解释的局限性可能会影响诊断的准确性.
研究的目的:
- 评估深度学习 (DL) 算法用于EGC检测的诊断性能.
- 将DL模型的准确性与专家内镜师进行比较.
- 评估DL作为内镜临床决策支持工具的潜力.
主要方法:
- 在主要数据库 (PubMed,Embase,Cochrane,Web of Science) 进行系统的文献搜索,截至2025年7月.
- 对内部和外部验证集的敏感性和特异性的聚合分析.
- 超回归以确定异质性来源,并与使用森林地块的专家内镜师进行比较.
主要成果:
- 内部验证 (15项研究,37,037张图像) 显示聚合灵敏度为0.91和特异性为0.93.
- 外部验证 (4项研究,3,579张图像) 给出了0.82的综合灵敏度和0.83.8的特异性.
- 培训数据集的大小显著影响了异质性;DL模型的性能与专家内镜师相比.
结论:
- 深度学习算法通过白光内镜检测胃癌早期的高诊断性能.
- DL模型提供诊断准确度与专家内镜师相提并论.
- 作为EGC诊断的有效临床决策支持工具,DL显示出希望.
相关概念视频
01:29Endoscopic Procedures I: Esophagogastroduodenoscopy
1.3K
An Esophagogastroduodenoscopy (EGD) is a diagnostic procedure in which an endoscopist uses a flexible, lighted endoscope to visualize the upper gastrointestinal (GI) tract. The procedure includes visualizing the oropharynx, esophagus, stomach, and the first part of the small intestine, the duodenum.
During an EGD, the endoscope can be used to:
During an EGD, the endoscope can be used to:
1.3K
01:28Endoscopic Procedures III: Video Capsule Endoscopy
920
Capsule endoscopy, or wireless or video capsule endoscopy, is a diagnostic procedure for examining the entire gastrointestinal tract. Patients swallow a capsule about the size of a vitamin tablet. The capsule is equipped with a transmitter, a battery, an LED light source, and a color video camera to capture images throughout the gastrointestinal tract. This procedure is particularly useful for diagnosing conditions such as Crohn's disease, ulcerative colitis, tumors, polyps, ulcers,...
920