Service d'ophtalmologie, hôpital Lariboisière, Assistance publique-hôpitaux de Paris, université Denis-Diderot Paris-7, 2, rue Ambroise-Paré, 75010 Paris, France.
Diabetes Metab. 2010 Jun;36(3):213-20. doi: 10.1016/j.diabet.2010.01.002. Epub 2010 Mar 10.
This study aimed to evaluate automated fundus photograph analysis algorithms for the detection of primary lesions and a computer-assisted diagnostic system for grading diabetic retinopathy (DR) and the risk of macular edema (ME).
Two prospective analyses were conducted on fundus images from diabetic patients. Automated detection of microaneurysms and exudates was applied to two small image databases on which these lesions were manually marked. A computer-assisted diagnostic system for the detection and grading of DR and the risk of ME was then developed and evaluated, using a large database containing both normal and pathological images, and compared with manual grading.
The algorithm for the automated detection of microaneurysms demonstrated a sensitivity of 88.5%, with an average number of 2.13 false positives per image. The pixel-based evaluation of the algorithm for automated detection of exudates had a sensitivity of 92.8% and a positive predictive value of 92.4%. Combined automated grading of DR and risk of ME was performed on 761 images from a large database. For DR detection, the sensitivity and specificity of the algorithm were 83.9% and 72.7%, respectively, and, for detection of the risk of ME, the sensitivity and specificity were 72.8% and 70.8%, respectively.
This study shows that previously published algorithms for computer-aided diagnosis is a reliable alternative to time-consuming manual analysis of fundus photographs when screening for DR. The use of this system would allow considerable timesavings for physicians and, therefore, alleviate the time spent on a mass-screening programme.
本研究旨在评估用于检测原发性病变的自动眼底照相分析算法和用于分级糖尿病视网膜病变（DR）和黄斑水肿（ME）风险的计算机辅助诊断系统。
对糖尿病患者的眼底图像进行了两项前瞻性分析。将微动脉瘤和渗出物的自动检测应用于两个小的图像数据库，这些病变在这些数据库中是手动标记的。然后，开发并评估了用于检测和分级 DR 以及 ME 风险的计算机辅助诊断系统，该系统使用包含正常和病理图像的大型数据库，并与手动分级进行了比较。
用于自动检测微动脉瘤的算法的灵敏度为 88.5%，平均每张图像有 2.13 个假阳性。基于像素的算法自动检测渗出物的评估具有 92.8%的灵敏度和 92.4%的阳性预测值。对来自大型数据库的 761 张图像进行了 DR 和 ME 风险的自动分级。对于 DR 检测，算法的灵敏度和特异性分别为 83.9%和 72.7%，而对于 ME 风险的检测，灵敏度和特异性分别为 72.8%和 70.8%。
这项研究表明，以前发表的计算机辅助诊断算法是一种可靠的替代方法，可以替代耗时的手动分析眼底照片，用于筛查 DR。该系统的使用将为医生节省大量时间，从而减轻大规模筛查计划所花费的时间。
