Gastroenterology and Hepatology, UZ Leuven, Leuven, Belgium
Translational Research in Gastrointestinal Diseases (TARGID), KU Leuven Biomedical Sciences Group, Leuven, Belgium.
Gut. 2024 Nov 11;73(12):1974-1983. doi: 10.1136/gutjnl-2024-331943.
Randomised trials show improved polyp detection with computer-aided detection (CADe), mostly of small lesions. However, operator and selection bias may affect CADe's true benefit. Clinical outcomes of increased detection have not yet been fully elucidated.
In this multicentre trial, CADe combining convolutional and recurrent neural networks was used for polyp detection. Blinded endoscopists were monitored in real time by a second observer with CADe access. CADe detections prompted reinspection. Adenoma detection rates (ADR) and polyp detection rates were measured prestudy and poststudy. Histological assessments were done by independent histopathologists. The primary outcome compared polyp detection between endoscopists and CADe.
In 946 patients (51.9% male, mean age 64), a total of 2141 polyps were identified, including 989 adenomas. CADe was not superior to human polyp detection (sensitivity 94.6% vs 96.0%) but outperformed them when restricted to adenomas. Unblinding led to an additional yield of 86 true positive polyp detections (1.1% ADR increase per patient; 73.8% were <5 mm). CADe also increased non-neoplastic polyp detection by an absolute value of 4.9% of the cases (1.8% increase of entire polyp load). Procedure time increased with 6.6±6.5 min (+42.6%). In 22/946 patients, the additional detection of adenomas changed surveillance intervals (2.3%), mostly by increasing the number of small adenomas beyond the cut-off.
Even if CADe appears to be slightly more sensitive than human endoscopists, the additional gain in ADR was minimal and follow-up intervals rarely changed. Additional inspection of non-neoplastic lesions was increased, adding to the inspection and/or polypectomy workload.
随机试验表明，计算机辅助检测（CADe）可提高息肉检测率，主要是针对小病变。然而，操作者和选择偏倚可能会影响 CADe 的实际获益。增加检测的临床获益尚未得到充分阐明。
在这项多中心试验中，使用结合卷积和递归神经网络的 CADe 进行息肉检测。盲法内镜医师实时由具有 CADe 访问权限的第二观察者进行监测。CADe 检测提示重新检查。在研究前和研究后测量腺瘤检测率（ADR）和息肉检测率。由独立的病理学家进行组织学评估。主要结局比较了内镜医师和 CADe 之间的息肉检测率。
在 946 例患者（51.9%为男性，平均年龄 64 岁）中，共发现 2141 个息肉，包括 989 个腺瘤。CADe 并不优于人类息肉检测（敏感性为 94.6%对 96.0%），但在限制为腺瘤时优于人类。解盲后额外增加了 86 个真阳性息肉检测（每位患者 ADR 增加 1.1%；73.8%的腺瘤<5mm）。CADe 还增加了 4.9%（整个息肉负荷增加 1.8%）的非肿瘤性息肉检测。手术时间增加了 6.6±6.5 分钟（增加 42.6%）。在 946 例患者中的 22 例中，腺瘤的额外检测改变了监测间隔（2.3%），主要是通过增加超出截止值的小腺瘤数量来实现。
即使 CADe 似乎比人类内镜医师更敏感，ADR 的额外获益也很小，随访间隔很少改变。增加了对非肿瘤性病变的检查，增加了检查和/或息肉切除术的工作量。
