ABSTRACT
This paper describes automated lesion detection in retinal images. Physicians and ophthalmologists assess retinal images for several kinds of lesions, including hemorrhages, exudates, and arteriolar narrowing. Hemorrhage is a major sign of diabetic retinopathy, which is the second most common cause of vision loss. Arteriolar narrowing is a major sign of hypertensive retinopathy. The aim of this study was to measure arteriolar-to-venular diameter ratio for the detection of arteriolar narrowing and to develop a hemorrhage detection method. Blood vessels and hemorrhages were extracted using a double-ring filter. This filter device calculates the difference between the average pixel values of the inside and outside regions. Arteriolar narrowing is determined based on major arteriolar-to-venular diameter ratios. Thus, the major blood vessels were extracted and the arteriolar-to-venular diameter ratio was automatically calculated based on the artery and vein diameter measurements. Finally, the hemorrhage candidates remained after the blood vessels were "erased" from the image and hemorrhages were detected by machine learning methods using 64 texture features. We tested 20 retinal images from the DRIVE database to evaluate our proposed arteriolar-to-venular diameter ratio measurement method. Both the average error and the standard deviation of the arteriolar-to-venular diameter ratio measurements were 0.07 ± 0.06. We evaluated the proposed method for hemorrhage detection by testing 71 retinal images, including 53 images with hemorrhages and 18 normal ones. The sensitivity and specificity for the detection of abnormal cases were 83% and 67%, respectively.
- Hatanaka, Y., Nakagawa, T., Hayashi, Y., Aoyama, Zhou, X., Hara, T., Fujita, H., Mizukusa, Y., Fujita, A., and Kakogawa, M. 2005. Automated detection algorithm for arteriolar narrowing on fundus images. In Proceedings of the 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Conference. (September 2005), 291. DOI=http://dx.doi.org/10.1109/IEMBS.2005.1616400.Google Scholar
- Takahashi, R., Hatanaka, Y., Nakagawa, T., Hayashi, Y., Aoyama, A., Mizukusa, Y., Fujita, A., Kakogawa, M., Hara, T., and Fujita, H. 2006. Automated analysis of blood vessel intersections retinal images for diagnosis of hypertension. In Medical Imaging Technology. 24, 4 (September 2006), 270--276.Google Scholar
- Nakagawa, T., Hayashi, Y., Hatanaka, Y., Aoyama, A., Mizukusa, Y., Fujita, A., Kakogawa, M., Hara, T., Fujita, H., and Yamamoto, T. 2006. Three-dimensional reconstruction using a single two-dimensional retinal image. In Medical Imaging and Information Sciences. 23, 2 (August 2006), 85--90.Google Scholar
- Nakagawa, T., Hayashi, Y., Hatanaka, Y., Aoyama, A., Mizukusa, Y., Fujita, A., Kakogawa, M., Hara, T., Fujita, H., and Yamamoto, T. 2006. Recognition of optic nerve head using blood-vessel-erased image and its application to production of simulated stereogram in computer-aided diagnosis system for retinal images. IEICE Trans. Inf. Syst. (Japanese edition). E93-D, 9 (September 2006), 2397--2406.Google Scholar
- Muramatsu, C., Hatanaka, Y., Iwase, T., and Fujita, H. 2010. Automated detection and classification of major retinal vessels for determination of diameter ratio of arteries and veins. In Proceedings of SPIE, 7624 (February 2010), 76240J. DOI=http://dx.doi.org/10.1117/12.843898.Google Scholar
- Hatanaka, Y., Nakagawa, T., Hayashi, Y., Fujita, A., Kakogawa, M., Kawase, K., Hara, T., and Fujita, H. 2007. CAD scheme to detect hemorrhages and exudates in ocular fundus images. In Proceedings of SPIE. 6514 (February 2007), 65142M. DOI=http://dx.doi.org/10.1117/12.708367.Google Scholar
- Hatanaka, Y., Nakagawa, T., Hayashi, Y., Hara, T., and Fujita, H. 2008. Improvement of automated detection method of hemorrhages in fundus images. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. (August 2008), 5429--5432. DOI=http://dx.doi.org/10.1109/IEMBS.2008.4650442.Google ScholarCross Ref
- Niemeijer, M., van Ginneken, B., Cree, M. J., Mizutani, A., Quellec, G., Sanchez, C. I., Zhang, B., Hornero, R., Lamard, M., Muramatsu, C., Wu, X., Cazuguel, G., You, J., Mayo, A. Li, Q., Hatanaka, Y., Cochener, B., Roux, C., Karray, F., Garcia, M., Fujita, H., and Abramoff, M. D. 2010. Retinopathy online challenge: Automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans. Med. Imaging. 29, 1 (January 2010), 185--195. DOI=http://dx.doi.org/10.1109/TMI.2009.2033909.Google ScholarCross Ref
- Muramatsu, C., Hayashi, Y., Sawada, A., Hatanaka, Y., Hara, T., Yamamoto, T., and Fujita, H. 2010. Detection of retinal nerve fiber layer defects on retinal fundus images for early diagnosis of glaucoma. J. Biomed. Opt. 15, 1 (January 2010), 016021. DOI=http://dx.doi.org/10.1117/12.863325.Google ScholarCross Ref
- Muramatsu, C., Nakagawa, T., Sawada, A., Hatanaka, Y., Hara, T., Yamamoto, T., and Fujita, H. 2011. Automated segmentation of optic disc region on retinal fundus photographs: Comparison of contour modeling and pixel classification methods. Comput. Methods Programs Biomed. 101, 1 (January 2011), 23--32. DOI=http://dx.doi.org/10.1016/j.cmpb.2010.04.006. Google ScholarDigital Library
- Hatanaka, Y., Noudo, A., Muramatsu, C., Sawada, A., Hara, T., Yamamoto, T., and Fujita, H. 2010. Automatic measurement of vertical cup-to-disc ratio on retinal fundus images. Medical Biometrics, LNCS, 6165 (June 2010), 54--72. DOI=http://dx.doi.org/10.1007/978-3-642-13923-9_7. Google ScholarDigital Library
- Nakagawa, T., Suzuki, T., Hayashi, Y., Mizukusa, Y., Hatanaka, Y., Ishida, K., Hara, T., Fujita, H., and Yamamoto, T. 2008. Quantitative depth analysis of optic nerve head using stereo retinal fundus image pair. J. Biomed. Opt. 13, 6 (November 2008), 064026. DOI=http://dx.doi.org/10.1117/12.823869.Google ScholarCross Ref
- Muramatsu, C., Nakagawa, T., Sawada, A., Hatanaka, Y., Hara, T., Yamamoto, T., and Fujita, H. 2009. Determination of cup and disc ratio of optical nerve head for diagnosis of glaucoma on stereo retinal fundus image pairs. In Proceedings of SPIE, 7260 (February 2009), 72603L. DOI=http://dx.doi.org/10.1117/12.811461.Google Scholar
- Doyle, W. 1962. Operation useful for similarity-invariant pattern recognition. J. Assoc. Comput. Mach. 9, 2 (April 1962), 259--267. DOI=http://dx.doi.org/10.1145/321119.321123. Google ScholarDigital Library
- Mitchell, O. R., Myers, C. R., Boyne, W. 1977. A max-min measure for image texture analysis. IEEE Trans. Comput. C-2, 4 (April 1977), 408--414. DOI=http://dx.doi.org/10.1109/TC.1977.1674850. Google ScholarDigital Library
- Haralick, R. M. 1979. Statistical and structural approaches to texture. In Proceedings of IEEE. 67, 5 (May 1979), 786--804. DOI=http://dx.doi.org/10.1109/PROC.1979.11328.Google ScholarCross Ref
- Weszka, J. S., Dyer, C. R., and Rosenfeld, A. 1976. A comparative study of texture measures for terrain classification. IEEE Trans. Syst. Man Cybern. SMC-6, 4 (April 1976), 269--285. DOI=http://dx.doi.org/10.1109/TSMC.1976.5408777.Google ScholarCross Ref
- Galloway, M. M. 1975. Texture analysis using gray level run lengths. Comput. Graphics Image Process. 4 (June 1975), 172--179. DOI=http://dx.doi.org/10.1016/S0146-664X(75)80008-6.Google Scholar
- Iwamura, M., Omachi, S., and Aso, H. 1998. Character recognition with Mahalanobis distance based on between-cluster information. IEICE Technical Report. 98, 490 (December 1998), 49--54, 1998.Google Scholar
- Cristianini, N., and Shawe-Talor, J. 2000. An Introduction to Support Vector Machines. Cambridge University Press, Cambridge, UK. Google ScholarDigital Library
- Staal, J. J., Abramoff, M. D., Niemeijer, M., Viergever, M. A., and van Ginneken, B. 2004. Ridge based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging. 23, 4 (April 2004), 501--509. DOI=http://dx.doi.org/10.1109/TMI.2004.825627Google ScholarCross Ref
Index Terms
- Automated lesion detection in retinal images
Recommendations
Exudates and optic disk detection in retinal images of diabetic patients
Diabetic retinopathy is the progressive pathological alterations in the retinal microvasculature that very often causes blindness. Because of its clinical significance, it will be helpful to have regular cost-effective eye screening for diabetic ...
Automated Identification of Diabetic Retinopathy Stages Using Digital Fundus Images
Diabetic retinopathy (DR) is caused by damage to the small blood vessels of the retina in the posterior part of the eye of the diabetic patient. The main stages of diabetic retinopathy are non-proliferate diabetes retinopathy (NPDR) and proliferate ...
Identification of different stages of diabetic retinopathy using retinal optical images
Diabetes is a disease which occurs when the pancreas does not secrete enough insulin or the body is unable to process it properly. This disease affects slowly the circulatory system including that of the retina. As diabetes progresses, the vision of a ...
Comments