Prediction of keratoconus progression using deep learning of anterior segment optical coherence tomography maps.
Prediction of keratoconus progression using deep learning of anterior segment optical coherence tomography maps.
复制标题
DOI：
10.21037/atm-21-1772
复制
发表时间：
2021-08
影响因子：
--
通讯作者：
Miyata K
中科院分区：
文献类型：
--
作者：
Kamiya K;Ayatsuka Y;Kato Y;Shoji N;Miyai T;Ishii H;Mori Y;Miyata K
目的：利用扫描源眼前段光学相干断层扫描(AS-OCT)设备测量的彩色编码图的深度学习来预测圆锥角膜的进展。我们招募了218只有和没有疾病进展的圆锥角膜患者。通过对AS-OCT(CASIA，Tomey)获得的6个彩色编码图(前高度、前曲率、后高度、后曲率、总屈光度和角膜厚度图)的深度学习，我们评估了预测圆锥角膜进展的准确性、敏感性和特异性。对6个颜色编码地图的深度学习显示，在区分圆锥角膜是否进展的准确率为0.794。对于单幅图分析，在区分进行性圆锥角膜和非进展性圆锥角膜时，后高度图(0.798)的准确率最高，其次是前曲率图(0.775)、角膜后曲率图(0.757)、前高度图(0.752)、总屈光度图(0.729)和角膜厚度图(0.720)。按年龄分组使用调整后的算法的准确率提高到0.849。通过对AS-OCT彩色编码图的深入学习，利用调整后的AGE算法有效地区分进展性圆锥角膜和非进行性圆锥角膜，准确率约为85%，这表明它将成为预测疾病进展的辅助手段，这对于临床上决定角膜交联术(CXL)的手术适应症是有益的。
To predict keratoconus progression using deep learning of the color-coded maps measured with a swept-source anterior segment optical coherence tomography (As-OCT) device. We enrolled 218 keratoconic eyes with and without disease progression. Using deep learning of the 6 color-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power, and pachymetry map) obtained by the As-OCT (CASIA, Tomey), we assessed the accuracy, sensitivity, and specificity of prediction of keratoconus progression in such eyes. Deep learning of the 6 color-coded maps exhibited an accuracy of 0.794 in discriminating keratoconus with and without progression. For a single map analysis, posterior elevation map (0.798) showed the highest accuracy, followed by anterior curvature map (0.775), posterior corneal curvature map (0.757), anterior elevation map (0.752), total refractive power map (0.729), and pachymetry map (0.720), in distinguishing between progressive and non-progressive keratoconus. The use of the adjusted algorithm by age subgroups improved to an accuracy of 0.849. Deep learning of the As-OCT color-coded maps effectively discriminates progressive keratoconus from non-progressive keratoconus with an accuracy of approximately 85% using the adjusted age algorithm, indicating that it will become an aid for predicting the progression of the disease, which is clinically beneficial for decision-making of the surgical indication of corneal cross-linking (CXL).
登录
查看更多内容
影响因子：
3.9
作者：
Kato N;Masumoto H;Tanabe M;Sakai C;Negishi K;Torii H;Tabuchi H;Tsubota K
通讯作者：
Tsubota K
影响因子：
4.6
作者：
Berchuck, Samuel I.;Mukherjee, Sayan;Medeiros, Felipe A.
通讯作者：
Medeiros, Felipe A.
影响因子：
4.4
作者：
Russakoff, Daniel B.;Lamin, Ali;Sivaprasad, Sobha
通讯作者：
Sivaprasad, Sobha
影响因子：
2.9
作者：
Kamiya, Kazutaka;Ayatsuka, Yuji;Miyata, Kazunori
通讯作者：
Miyata, Kazunori
影响因子：
4.2
作者：
Godefrooij, Daniel A.;De Wit, G. Ardine;Wisse, Robert P. L.
通讯作者：
Wisse, Robert P. L.