Qualit ätskontrolle in der Hornhautbank mit KI: Vergleich des neuen Deep-Learning-basierten Ansatzes mit der konventionellen Endothelzelldichtenbestimmung durch das Rhine-Tec System

This study aims to compare this new method with the conventional Rhine-Tec system. 9,375 archived phase-contrast microscopic images of consecutive grafts from the Lions Eye Bank were evaluated with the deep learning method and compared with the corresponding archived analyses of the Rhine-Tec system. Specifically, comparisons of means, Bland-Altman and correlation analyses were performed. Comparable results were obtained for both methods. The mean difference between the Rhine-Tec system and the deep learning method was only -23 cells/mm2 (95% confidence interval -29 to -17). There was a statistically significant positive correlation between the two methods with a correlation coefficient of 0.748. Noticeable in the Bland-Altman analysis were clustered deviations in the cell density range between 2000 and 2500 cells/mm2 with higher values in the Rhine-Tec system. The comparable results regarding cell density measurement values underline the validity of the "deep learning" based method. The deviations around the formal threshold for graft release of 2000 cells/mm2 are most likely explained by the higher objectivity of the deep learning method and the fact that measurement frames and manual corrections were specifically selected to reach the formal threshold of 2000 cells/mm2 when the full area endothelial quality was good. This full area assessment of the graft endothelium cannot currently be replaced by deep learning methods and remains the most important basis for graft releas...
Source: Klinische Monatsblatter fur Augenheilkunde - Category: Opthalmology Authors: Source Type: research