Four discriminant models for detecting keratoconus pattern using Zernike coefficients of corneal aberrations.
Four discriminant models for detecting keratoconus pattern using Zernike coefficients of corneal aberrations.
复制标题
使用角膜像差泽尼克系数检测圆锥角膜模式的四种判别模型。
DOI：
10.1007/s10384-013-0269-1
复制
发表时间：
2013
期刊：
影响因子：
2.4
通讯作者：
Nishida K
中科院分区：
文献类型：
--
作者：
SaikaM;Maeda N;Hirohara Y;Mihashi T;Fujikado T;Nishida K
目的利用角膜像差的Zernike系数，比较四种判别模型检测圆锥角膜（KC）的能力。方法对51只KC眼、46只疑似KC眼、50只原位角膜移植术眼和65只正常眼进行研究。利用基于placido的地形学家获得的角膜像差Zernike系数进行了四种统计判别分析——线性判别分析、k近邻算法、马氏距离法和神经网络法。检测方案使用随机选择的一半研究参与者的训练数据集构建，并通过另一半的验证集评估性能。结果当包含<12个解释变量时，4种模型的性能存在差异。使用二阶至四阶Zernike项的性能在模型之间没有显着差异；平均准确率为79%。结论在不同的判别式模型中，选择合适的判别式模型解释变量，可以得到相似的判别式模型结果，因此确定判别式模型中角膜地形Zernike膨胀系数的解释变量有助于提高KC检测的准确性。
PurposeWe compared the ability of four discriminant models to detect keratoconus (KC) using Zernike coefficients of corneal aberrations.MethodsWe studied 51 eyes with KC, 46 with KC suspect, 50 after laser in situ keratomileusis, and 65 normal eyes. Four statistical discriminant analyses—linear discriminant analysis,k-nearest neighbor algorithm, Mahalanobis distance method, and neural network method—were performed using Zernike coefficients of corneal aberrations obtained by a Placido-based topographer. The detection scheme was constructed using a training set of data from one half of the randomly selected study participants, and performance was evaluated by a validation set in the other half.ResultsPerformance of the four models was different when <12 explanatory variables were included. Performance using the 2nd- to 4th-order Zernike terms did not differ significantly among models; average accuracy was 79 %.ConclusionsDetermining explanatory variables of Zernike expansion coefficients of the corneal topography in discriminant models may contribute to improving accuracy of KC detection over the discriminant model, as appropriate selection of explanatory variables gave similar results despite different discriminant models.