Wagner Andrej, Zandanell Stephan, Ziachehabi Alexander, Mitrakov Alexander, Klieser Eckhard, Neureiter Daniel, Kiesslich Tobias, Mayr Christian, Berr Frieder, Fedoruk Michael, Singhartinger Franz, Holzinger Josef
Department of Internal Medicine I, University Clinics Salzburg, Paracelsus Medical University, Salzburg, Austria.
Department of Medicine II, Kepler Medical University, Linz, Austria.
Endosc Int Open. 2022 Aug 15;10(8):E1147-E1154. doi: 10.1055/a-1847-2820. eCollection 2022 Aug.
Endoscopic optical diagnosis is crucial to the therapeutic strategy for early gastrointestinal cancer. It accurately (> 85 %) predicts pT category based on microsurface (SP) and vascular patterns (VP). However, interobserver variability is a major problem. We have visualized and digitalized the graded irregularities based on bioinformatically enhanced quantitative endoscopic image analysis (BEE) of high-definition white-light images. In a pilot study of 26 large colorectal lesions (LCLs, mean diameter 39 mm), we retrospectively compared BEE variables with corresponding histopathology of the resected LCLs. We included 10 adenomas with low-grade intraepithelial neoplasia (LGIN), nine with high-grade intraepithelial neoplasia (HGIN) and early adenocarcinoma (EAC), and seven deeply submucosal invasive carcinomas. Quantified density (d) and nonuniformity (C ) of vascular and surface structures correlated with histology (r d VP: -0.77, r C VP: 0.13, r d SP: -0.76, and r C SP: 0.45, respectively). A computed BEE score showed a sensitivity and specificity of 90 % and 100 % in the group with LGINs, 89 % and 41 % in the group with HGINs and EACs, and 100 % and 95 % in the group with deeply invasive carcinoma, respectively. In this pilot study, BEE showed promise as a tool for endoscopic characterization of LCLs during routine endoscopy. Prospective clinical studies are needed.
内镜光学诊断对于早期胃肠道癌的治疗策略至关重要。它基于微观表面（SP）和血管形态（VP）能准确（>85%）预测pT分期。然而，观察者间的变异性是一个主要问题。我们通过对高清白光图像进行生物信息增强定量内镜图像分析（BEE），对分级不规则性进行了可视化和数字化处理。在一项对26个大肠大病变（LCL，平均直径39mm）的初步研究中，我们回顾性地比较了BEE变量与切除的LCL相应的组织病理学结果。我们纳入了10个伴有低级别上皮内瘤变（LGIN）的腺瘤、9个伴有高级别上皮内瘤变（HGIN）和早期腺癌（EAC）的病变，以及7个深度黏膜下浸润癌。血管和表面结构的量化密度（d）和不均匀性（C）与组织学相关（r d VP：-0.77，r C VP：0.13，r d SP：-0.76，r C SP：0.45）。计算得出的BEE评分在LGIN组的敏感性和特异性分别为90%和100%，在HGIN和EAC组分别为89%和41%，在深度浸润癌组分别为100%和95%。在这项初步研究中，BEE显示出有望成为常规内镜检查中LCL内镜特征化的工具。需要进行前瞻性临床研究。
