Automatic Glaucoma Detection Method Applying a Statistical Approach to Fundus Images
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Objectives: Glaucoma is an incurable eye disease and the second leading cause of blindness in the world. Until 2020, thenumber of patients of this disease is estimated to increase. This paper proposes a glaucoma detection method using statisticalfeatures and the k-nearest neighbor algorithm as the classifier. Methods: We propose three statistical features, namely,the mean, smoothness and 3rd moment, which are extracted from images of the optic nerve head. These three features areobtained through feature extraction followed by feature selection using the correlation feature selection method. To classifythose features, we apply the k-nearest neighbor algorithm as a classifier to perform glaucoma detection on fundus images. Results: To evaluate the performance of the proposed method, 84 fundus images were used as experimental data consistingof 41 glaucoma image and 43 normal images. The performance of our proposed method was measured in terms of accuracy,and the overall result achieved in this work was 95.24%, respectively. Conclusions: This research showed that the proposedmethod using three statistics features achieves good performance for glaucoma detection
Abstract
Objectives: Glaucoma is an incurable eye disease and the second leading cause of blindness in the world. Until 2020, thenumber of patients of this disease is estimated to increase. This paper proposes a glaucoma detection method using statisticalfeatures and the k-nearest neighbor algorithm as the classifier. Methods: We propose three statistical features, namely,the mean, smoothness and 3rd moment, which are extracted from images of the optic nerve head. These three features areobtained through feature extraction followed by feature selection using the correlation feature selection method. To classifythose features, we apply the k-nearest neighbor algorithm as a classifier to perform glaucoma detection on fundus images. Results: To evaluate the performance of the proposed method, 84 fundus images were used as experimental data consistingof 41 glaucoma image and 43 normal images. The performance of our proposed method was measured in terms of accuracy,and the overall result achieved in this work was 95.24%, respectively. Conclusions: This research showed that the proposedmethod using three statistics features achieves good performance for glaucoma detection
참고문헌 (32)
- Quigley HA, "Number of people with glaucoma worldwide", Br J Ophthalmol, 80(5), pp.389~393 (1996)[DOI]
- Quigley HA, "The number of people with glaucoma worldwide in 2010 and 2020", Br J Ophthalmol, 90(3), pp.262~267 (2006)[DOI]
- Gamero GE, "Atlas of glaucoma" (2007), CRC Press
- Septiarini A, "Automatic glaucoma detection based on the type of features used : a review", J Theor Appl Inf Technol, 72(3), pp.366~375 (2015)
- Salam AA, "Automated detection of glaucoma using structural and non structural features", Springerplus, 5(1), pp.1519~ (2016)[DOI]
- Issac A, "An adaptive threshold based image processing technique for improved glaucoma detection and classification", Comput Methods Programs Biomed, 122(2), pp.229~244 (2015)[DOI]
- Marin D, "Obtaining optic disc center and pixel region by automatic thresholding methods on morphologically processed fundus images", Comput Methods Programs Biomed, 118(2), pp.173~185 (2015)[DOI]
- Septiarini A, "Optic disc and cup segmentation by automatic thresholding with morphological operation for glaucoma evaluation", Signal Image Video Process, 11(5), pp.945~952 (2017)[DOI]
- Muramatsu C, "Automated segmentation of optic disc region on retinal fundus photographs: comparison of contour modeling and pixel classification methods", Comput Methods Programs Biomed, 101(1), pp.23~32 (2011)[DOI]
- Mary MC, "An empirical study on optic disc segmentation using an active contour model", Biomed Signal Process Control, 18, pp.19~29 (2015)[DOI]
- Cheng J, "Superpixel classification based optic disc and optic cup segmentation for glaucoma screening", IEEE Trans Med Imaging, 32(6), pp.1019~1032 (2013)[DOI]
- Khalid NE, "Fuzzy c-means (FCM) for optic cup and disc segmentation with morphological operation", Procedia Comput Sci, 42, pp.255~262 (2014)[DOI]
- Welfer D, "A morphologic two-stage approach for automated optic disk detection in color eye fundus images", Pattern Recognit Lett, 34(5), pp.476~485 (2013)[DOI]
- Mookiah MR, "Data mining technique for automated diagnosis of glaucoma using higher order spectra and wavelet energy features", Knowl Based Syst, 33, pp.73~82 (2012)[DOI]
- Annu N, "Classification of glaucoma images using wavelet based energy features and PCA", Int J Sci Eng Res, 4(5), pp.1369~1374 (2013)
- Dey A, "Automated glaucoma detection using support vector machine classification method", Br J Med Med Res, 11(12), pp.1~12 (2016)
- Singh A, "Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image", Comput Methods Programs Biomed, 124, pp.108~120 (2016)[DOI]
- Noronha KP, "Automated classification of glaucoma stages using higher order cumulant features", Biomed Signal Process Control, 10(1), pp.174~183 (2014)[DOI]
- Karthikeyan S, "Performance analysis of gray level cooccurrence matrix texture features for glaucoma diagnosis", Am J Appl Sci, 11(2), pp.248~257 (2014)[DOI]
- Ali MA, "Glaucoma detection based on local binary patterns in fundus photographs", Proceedings of SPIE Medical Imaging 2014: Image Processing (2014)
- Aruchamy S, "Automated glaucoma screening in retinal fundus images", Int J Multimed Ubiquitous Eng, 10(9), pp.129~136 (2015)
- Murthi A, "Medical decision support system to identify glaucoma using cup to disc ratio", J Theor Appl Inf Technol, 68(2), pp.406~413 (2014)
- Septiarini A, "The contour extraction of cup in fundus images for glaucoma detection", Int J Electr Comput Eng, 6(6), pp.2797~2804 (2016)
- Sheshadri HS, "Breast tissue classification using statistical feature extraction of mammograms", Med Imaging Inf Sci, 23(3), pp.105~107 (2006)
- 김태연, "The Recent Progress in Quantitative Medical Image Analysis for Computer Aided Diagnosis Systems", Healthcare Informatics Research, 17(3), pp.143~149 (2011), 대한의료정보학회
- Wiharto Wiharto, "Interpretation of Clinical Data Based on C4.5 Algorithm for the Diagnosis of Coronary Heart Disease", Healthcare Informatics Research, 22(3), pp.186~195 (2016), 대한의료정보학회[DOI]
- Yousefi S, "Glaucoma progression detection using structural retinal nerve fiber layer measurements and functional visual field points", IEEE Trans Biomed Eng, 61(4), pp.1143~1154 (2014)[DOI]
- Ashraf M, "Neural Information Processing", pp.272~280 (2012), Springer
- Vanaja S, "Analysis of feature selection algorithms on classification : a survey", Int J Comput Appl, 96(17), pp.28~35 (2014)
- Saeys Y, "A review of feature selection techniques in bioinformatics", Bioinformatics, 23(19), pp.2507~2517 (2007)[DOI]
- Hall MA, "Feature selection for machine learning: comparing a correlation-based filter approach to the wrapper", Proceedings of the 12th International FLAIRS Conference, pp.235~239 (1999)
- Kotsiantis SB, "Supervised machine learning: a review of classification techniques", Informatica, 31, pp.249~268 (2007)