正常角膜和圆锥角膜的特征提取

余锦华; 季春红; 李添捷; 田磊; 黄一飞; 汪源源; 郑永平

doi:10.3788/OPE.20152310.2919

您当前的位置：

首页 >

文章列表页 >

正常角膜和圆锥角膜的特征提取

信息科学 | 更新时间：2020-08-13

- 正常角膜和圆锥角膜的特征提取
- Extracting features from normal corneas and keratoconus based on wavelet analysis
- 光学精密工程 2015年23卷第10期页码：2919-2926
- 作者机构：
  
  1. 复旦大学电子工程系上海,200433
  2. 医学影像计算及计算机协助介入重点实验室上海,200433
  3. 香港理工大学跨学科生物医学工程部门,香港
  4. 首都医科大学附属北京同仁医院北京市眼科研究所北京,100005
  5. 中国人民解放军总医院眼科系北京,100853
- 作者简介：
- 基金信息：
  
  国家973重点基础研究发展计划资助项目(No. 2015CB755500)();国家自然科学基金资助项目(No. 61471125,No.81271052)();香港理
- DOI：10.3788/OPE.20152310.2919
  中图分类号： R722.21;TP391
- 收稿日期：2015-05-21，
  
  修回日期：2015-07-20，
  
  纸质出版日期：2015-10-25
- 稿件说明：
移动端阅览
余锦华, 季春红, 李添捷等. 正常角膜和圆锥角膜的特征提取[J]. 光学精密工程, 2015,23(10): 2919-2926

YU Jin-hua, JI Chun-hong, LI Tian-jie etc. Extracting features from normal corneas and keratoconus based on wavelet analysis[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10): 2919-2926
余锦华, 季春红, 李添捷等. 正常角膜和圆锥角膜的特征提取[J]. 光学精密工程, 2015,23(10): 2919-2926 DOI： 10.3788/OPE.20152310.2919.

YU Jin-hua, JI Chun-hong, LI Tian-jie etc. Extracting features from normal corneas and keratoconus based on wavelet analysis[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10): 2919-2926 DOI： 10.3788/OPE.20152310.2919.

摘要

基于角膜测量仪器Corvis ST采集的图像视频

提出提取新特征参数以便准确区分正常角膜和圆锥角膜。首先对图像进行滤波、分割等预处理

检测角膜上下边界

并计算前角膜曲率值;用小波变换分析角膜曲率变化

获取与角膜运动趋势相关的特征

包括角膜运动的整体趋势和角膜振动的范数和标准差。然后

基于均方误差最小化法

提取特征参数

构建最优参数。最后

用支持向量机(SVM)对正常角膜和圆锥角膜进行分类。从频率的角度实施的实验显示角膜在基本运动趋势上存在着振动过程。此外

提出的参数优于形变幅度(DA)、峰值距离(PD)等传统参数

使准确度、灵敏度和特异性分别提高了10.2%

5.7%和6.9%。受试者工作特征曲线 (ROC)下面积为0.948

接近于1。结果显示本文方法自动提取的特征参数可提高正常角膜和圆锥角膜区分的准确性

对临床诊断有辅助作用。

Abstract

On the basis of video image captured by the cornea measuring instrument Corvis ST

this paper proposes an idea to improve the accuracy of distinguishing normal corneas from keratoconic corneas by extracting new feature parameters

Firstly

the original images were preprocessed by filtering and segmenting to detect the upper and lower boundaries of the cornea and calculate the curvature of anterior cornea. Then

the change of corneal curvature was analyzed by wavelet transformation method to obtain features related to the trend of corneal movement

including the trend of the whole corneal motion as well the norm and the standard deviation of corneal vibration. Furthermore

the feature parameters were extracted in succession and the optimal parameter was obtained by the minimum mean square error algorithm. The Support Vector Machine (SVM) was finally applied to distinction of normal corneas from keratoconic corneas. The experiment results on the frequency indicate that there are corneal vibrations along with the basic movement process. Besides

the proposed parameters are better than traditional parameters such as Deformation Amplitude (DA)

Peak Distance(PD) at the highest concavity

which improves the accuracy

sensitivity and specificity by 10.2%

5.7% and 6.9%

respectively. Moreover

the area under the receiver operating characteristic curve (ROC) is 0.948

close to unity. The automatic extracted feature parameters in this paper are able to improve the accuracy of classification between normal and keratoconic corneas and contribute to the clinical diagnoses.

关键词

Keywords

references

DUDAKOVA L, LISKOVA P, JIRSOVA K. Is copper imbalance an environmental factor influencing keratoconus development? [J]. Medical Hypotheses, 2015, 84(5): 518-524.

KRACHMER J H, FEDER R S, BELIN M W. Keratoconus and related non-inflammatory corneal thinning disorders [J]. Surv Opthalmol, 1994, 28: 293-322.

SULL A C, VUONG L N, PRICE L L, et al.. Comparison of spectral/Fourier domain optical coherence tomography instruments for assessment of normal macular thickness [J]. Retina-The Journal of Retinal and Vitreous Diseases, 2010, 30(2): 235-245.

王立科,张佳莹,田磊,等. 基于光学相干层析气冲印压技术研究角膜生物力学特性 [J]. 光学精密工程, 2015, 23(2): 325-333. WANG L K, ZHANG J Y, TIAN L, et al.. OCT based air jet indentation for corneal biomechanical assessment[J]. Opt. Precision Eng., 2015,23(2): 325-333. (in Chinese)

ANAYOL M A, GULER E, YAGCI R, et al.. Comparison of central corneal thickness, thinnest corneal thickness, anterior chamber depth, and simulated keratometry using galilei, pentacam, and sirius devices [J]. Cornea, 2014, 33(6): 582-586.

AMBROSIO R, CAIADO A L C, GUERRA F P, et al.. Novel pachymetric parameters based on corneal tomography for diagnosing keratoconus [J]. Journal of Refractive Surgery, 2011, 27(10): 753-758.

LUCE D A. Determining in vivo biomechanical properties of the cornea with an ocular response analyzer [J]. Journal of Cataract & Refractive Surgery, 2005, 31(1): 156-162.

LUCE D, TAYLOR D. Reichert ocular response analyzer measures corneal biomechanical properties and IOP [J]. Reichert Ophthalmic Instruments, 2006.

AMBROSIO R, RAMOS I, LUZ A, et al.. Dynamic ultra high speed Scheimpflug imaging for assessing corneal biomechanical properties [J]. Revista Brasileira de Oftalmologia, 2013, 72(2): 99-102.

HONG J X, XU J J, WEI A J, et al.. A new tonometer-the Corvis ST tonometer: clinical comparison with noncontact and Goldmann applanation tonometers [J]. Investigative Ophthalmology & Visual Science, 2013, 54(1): 659-665.

AMBRÓSIO JR R, NOGUEIRA L P, CALDAS D L, et al.. Evaluation of corneal shape and biomechanics before LASIK [J]. International Ophthalmology Clinics, 2011, 51(2): 11-38.

TIAN L, HUANG Y F, WANG L Q, et al.. Corneal biomechanical assessment using corneal visualization scheimpflug technology in keratoconic and normal eyes [J]. Journal of Ophthalmology, 2014, 2014:147516.

AMBROSIO JR R, CALDAS D, RAMOS I, et al.. Corneal biomechanical assessment using dynamic ultra high-speed Scheimpflug technology non-contact tonometry (UHS-ST NCT): preliminary results [C]. American Society of Cataract and Refractive Surgery-American Society of Ophthalmic Administrators (ASCRS-ASOA) Symposium and Congress, San Diego, CA, 2011.

ROBERTS C. Biomechanical customization: the next generation of laser refractive surgery [J]. Journal of Cataract & Refractive Surgery, 2005, 31(1): 2-5.

TANG M L, LI Y, AVILA M, et al.. Measuring total corneal power before and after laser in situ keratomileusis with high-speed optical coherence tomography [J]. Journal of Cataract & Refractive Surgery, 2006, 32(11): 1843-1850.

LANZA M, CENNAMO M, LACCARINO S, et al.. Evaluation of corneal deformation analyzed with scheimpflug based device in healthy eyes and diseased ones [J]. BioMed Research International, 2014, 2014:748671.

HON Y, LAM A K C. Corneal deformation measurement using Scheimpflug noncontact tonometry [J]. Optometry & Vision Science, 2013, 90(1):e1-e8.

张浩, 袁怡宝, 张峰. 巴特沃思小波在表面形貌信号分离中的应用 [J]. 光学精密工程,2010, 18(7): 1661-1667. ZHANG H, YUAN Y B, ZHANG F. Application of Butterworth wavelet to surface topography signal separation [J]. Opt. Precision Eng., 2010, 18(7):1661-1667. (in Chinese)

高恒振,万建伟,粘永健,等. 组合核函数支持向量机高光谱图像融合分类 [J]. 光学精密工程,2011, 19(4): 878-883. GAO H ZH, WAN J W, NIAN Y J, et al.. Fusion classification of hyperspectral image by composite kernels support vector machine[J]. Opt. Precision Eng., 2011, 19(4): 878-883. (in Chinese)

MELGANI F, BRUZZONE L. Classification of hyperspectral remote sensing images with support vector machines [J]. IEEE Trans. Geosci. Remote Sens., 2004, 42(8):1778-1790.

谭熊,余旭初,张鹏强,等. 基于多核支持向量机的高光谱影像非线性混合像元分解 [J]. 光学精密工程,2014, 22(7): 1912-1920. TAN X, YU X CH, ZHANG P Q, et al.. Nonlinear mixed pixel decomposition of hyperspectral imagery based on multiple kernel SVM[J]. Opt. Precision Eng., 2014, 22(7): 1912-1920. (in Chinese)

JI C H, YU J H, WANG Y Y, et al.. Automatic phase-based edge detection of corneal Sheimpflug images [C]. 2014 IEEE Workshop on Electronics, Computer and Applications, 2014: 840-843.

JI CH H, YU J H, LI T J, et al.. Dynamic curvature topography for evaluating the anterior corneal surface change with Corvis ST [J]. Biomedical Engineering Online,2015,14,Doi:10.1186/s 12938-015-0036-2. (Accepted)

KOVESI P. Symmetry and asymmetry from local phase [C]. Tenth Australian Joint Conference on Artificial Intelligence, 1997, 190.

THOMAS S M, CHAN Y T. A simple approach for the estimation of circular arc center and its radius [J]. Computer Vision, Graphics, and Image Processing, 1989, 45(3): 362-370.

MALLAT S G. A theory for multiresolution signal decomposition: the wavelet representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674-693.

MISITI M, MISITI Y, Oppenheim G, et al.. Wavelet toolbox [J]. The MathWorks Inc., Natick, MA, 1996.

THAYAPARAN T, ABROL S, RISEBOROUGH E, et al.. Analysis of radar micro-Doppler signatures from experimental helicopter and human data [J]. IET Radar, Sonar & Navigation, 2007, 1(4): 289-299.

HAN Z L, TAO C, ZHOU D, et al.. Air puff induced corneal vibrations: theoretical simulations and clinical observations [J]. Journal of Refractive Surgery, 2014, 30(3): 208-213.

CHEN K. A connectionist method for pattern classification with diverse features [J]. Pattern Recognition Letters, 1998, 19(7): 545-558.

陈显毅. 图像配准技术及其MATLAB编程实现 [M]. 北京:电子工业出版社,2009. CHEN X Y. Image Registration Technique and MATLAB Programming[M]. Beijing: Electronic Industry Press, 2009. (in Chinese)

刘欣悦,黄廉卿. 利用多分辨率直方图特征分类数字X光乳腺图像 [J]. 光学精密工程,2006, 14(2):327-332. LIU X Y, HUANG L Q. Using multi-resolution histogram feature to classify digital X-ray mammography [J]. Opt. Precision Eng., 2006, 14(2):327-332. (in Chinese)

浏览量

251

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

跨层注意力交互下的多特征交叉无人机图像检测

小波DehazeFormer网络的道路交通图像去雾

基于分数阶微分的高光谱图像特征提取与分类

面向高光谱影像场景分类的轻量化深度全局-局部知识蒸馏网络

多分支无锚框网络密集行人检测算法