Department of Ophthalmology, Seoul Metropolitan Government Seoul National University Boramae Medical Centre, Seoul, Republic of Korea.
VUNO Inc., Seoul, Republic of Korea.
Transl Vis Sci Technol. 2024 Oct 1;13(10):34. doi: 10.1167/tvst.13.10.34.
To evaluate the clinical usefulness of a deep learning-based detection device for multiple abnormal findings on retinal fundus photographs for readers with varying expertise.
Fourteen ophthalmologists (six residents, eight specialists) assessed 399 fundus images with respect to 12 major ophthalmologic findings, with or without the assistance of a deep learning algorithm, in two separate reading sessions. Sensitivity, specificity, and reading time per image were compared.
With algorithmic assistance, readers significantly improved in sensitivity for all 12 findings (P < 0.05) but tended to be less specific (P < 0.05) for hemorrhage, drusen, membrane, and vascular abnormality, more profoundly so in residents. Sensitivity without algorithmic assistance was significantly lower in residents (23.1%∼75.8%) compared to specialists (55.1%∼97.1%) in nine findings, but it improved to similar levels with algorithmic assistance (67.8%∼99.4% in residents, 83.2%∼99.5% in specialists) with only hemorrhage remaining statistically significantly lower. Variances in sensitivity were significantly reduced for all findings. Reading time per image decreased in images with fewer than three findings per image, more profoundly in residents. When simulated based on images acquired from a health screening center, average reading time was estimated to be reduced by 25.9% (from 16.4 seconds to 12.1 seconds per image) for residents, and by 2.0% (from 9.6 seconds to 9.4 seconds) for specialists.
Deep learning-based computer-assisted detection devices increase sensitivity, reduce inter-reader variance in sensitivity, and reduce reading time in less complicated images.
This study evaluated the influence that algorithmic assistance in detecting abnormal findings on retinal fundus photographs has on clinicians, possibly predicting its influence on clinical application.
评估一种基于深度学习的眼底照片多种异常发现检测设备对不同专业水平读者的临床应用价值。
14 名眼科医生（6 名住院医师，8 名专家）在两次独立的阅读会议中，分别评估了 399 张眼底图像是否存在 12 种主要眼科发现，并分别在有无深度学习算法辅助的情况下进行评估。比较了敏感性、特异性和每张图像的阅读时间。
在算法辅助下，所有 12 种发现的敏感性均显著提高（P<0.05），但特异性倾向于降低（P<0.05），尤其是对于出血、玻璃膜疣、膜和血管异常，住院医师的变化更为明显。在没有算法辅助的情况下，9 种发现中，住院医师的敏感性明显低于专家（23.1%∼75.8%），但在算法辅助下，敏感性提高到相似水平（住院医师 67.8%∼99.4%，专家 83.2%∼99.5%），仅出血的敏感性仍存在统计学差异。所有发现的敏感性变异性均显著降低。对于每张图像少于 3 种发现的图像，每张图像的阅读时间减少，住院医师的降幅更为明显。当基于健康筛查中心采集的图像进行模拟时，预计住院医师的平均阅读时间将减少 25.9%（从 16.4 秒减少至 12.1 秒/张），专家的阅读时间减少 2.0%（从 9.6 秒减少至 9.4 秒）。
基于深度学习的计算机辅助检测设备可提高敏感性，降低敏感性的读者间变异性，并减少较简单图像的阅读时间。
杨爽
