当前圆锥角膜检测方法与神经网络方法的比较

Current keratoconus detection methods compared with a neural network approach.

作者信息

Smolek M K, Klyce S D

机构信息

LSU Eye Center, Louisiana State University Medical Center, New Orleans 70112, USA.

出版信息

Invest Ophthalmol Vis Sci. 1997 Oct;38(11):2290-9.

PMID:9344352

Abstract

PURPOSE

Four videokeratographic methods for keratoconus detection were compared with a neural network approach.

METHODS

A classification neural network for keratoconus screening was designed to detect the presence of keratoconus (KC) or keratoconus suspects (KCS); a separate cone severity network graded the severity of conelike topography patterns consistent with KC or KCS. Three hundred TMS-1 examinations (Tomey) were randomly divided into training and test sets. Ten topographic indexes were network inputs. Nine categories were used: normal, astigmatism, KC, KCS, contact lens-induced warpage, pellucid marginal degeneration, photorefractive keratectomy, radial keratotomy, and penetrating keratoplasty. KC was subdivided into KC1 (mild), KC2 (moderate), and KC3 (advanced). There were three outputs for the classification network (KC, KCS, and OTHER); target output values of 0 = OTHER, 0.25 = KCS, 0.5 = KC1, 0.75 = KC2, and 1.0 = KC3 were used for the severity network.

RESULTS

The best-trained classification network had 100% accuracy, specificity, and sensitivity for the test set. The severity network had mean outputs (+/-standard deviation) of OTHER = 0.02+/-0.02, KCS = 0.21+/-0.05, KC1 = 0.52+/-0.17, KC2 = 0.74+/-0.12, and KC3 = 0.91+/-0.15. The severity network output for all categories was well correlated to the keratoconus prediction index (R = 0.892, P < 0.0001). The classification network had an overall accuracy and specificity significantly better (P < or = 0.005) than the Klyce/Maeda keratoconus index (KCI) test, the Rabinowitz test (K & I-S), and simulated keratometry (average Sim K). However, there were no significant differences in keratoconus sensitivity between the classification network, KCI, and K & I-S. The sensitivity and specificity of average Sim K were significantly worse than those of the other tests. The classification network had significantly better sensitivity (P < 0.001) and specificity (P = 0.025) for KCS detection than the K & I-S.

CONCLUSIONS

The neural networks completely distinguished KC from KCS and from topographies that resembled KC. The network approach equaled the sensitivity of currently used tests for keratoconus detection and outperformed them in terms of accuracy and specificity.

摘要

目的

将四种用于圆锥角膜检测的角膜地形图测量方法与一种神经网络方法进行比较。

方法

设计了一个用于圆锥角膜筛查的分类神经网络，以检测圆锥角膜（KC）或圆锥角膜疑似病例（KCS）的存在；一个单独的圆锥严重程度网络对与KC或KCS一致的圆锥状地形图模式的严重程度进行分级。300次TMS - 1检查（托米公司）被随机分为训练集和测试集。十个地形学指标作为网络输入。使用九种类别：正常、散光、KC、KCS、隐形眼镜引起的角膜变形、透明边缘变性、准分子激光原位角膜磨镶术、放射状角膜切开术和穿透性角膜移植术。KC被细分为KC1（轻度）、KC2（中度）和KC3（重度）。分类网络有三个输出（KC、KCS和其他）；严重程度网络使用的目标输出值为0 = 其他，0.25 = KCS，0.5 = KC1，0.75 = KC2，1.0 = KC3。

结果

训练最佳的分类网络对测试集的准确率、特异性和敏感性均为100%。严重程度网络的平均输出（±标准差）为：其他 = 0.02±0.02，KCS = 0.21±0.05，KC1 = 0.52±0.17，KC2 = 0.74±0.12，KC3 = 0.91±0.15。所有类别的严重程度网络输出与圆锥角膜预测指数高度相关（R = 0.892，P < 0.0001）。分类网络的总体准确率和特异性显著优于（P≤0.005）Klyce/Maeda圆锥角膜指数（KCI）测试、Rabinowitz测试（K & I - S）和模拟角膜曲率测量（平均模拟K）。然而，分类网络、KCI和K & I - S在圆锥角膜敏感性方面无显著差异。平均模拟K的敏感性和特异性显著低于其他测试。分类网络在检测KCS方面的敏感性（P < 0.001）和特异性（P = 0.025）显著优于K & I - S。