Detection Of Topographic Images Of Keratoconus Disease Using Machine Vision

Year 2020, Volume: 4 Issue: 4, 145 - 150, 28.12.2020

Ehsan Amiri , Zahra Roozbakhsh Saeed Amiri Mohammad Hasan Asadi

Abstract

The human eye is one of the most important and first senses (vision) of the five senses. Each eye disease creates its own problems for the patient, and measures are needed to diagnose and treat these diseases. One of these diseases is keratoconus, which is the basis of this article. In this article, first, explanations about this progressive disease are presented, then the important and basic factors used in the programming of this project are briefly and usefully expressed and using 33 topographic images (both healthy eyes and eyes with keratoconus). Four prominent features of this disease were studied and diagnosed with the help of MATLAB software. Proper images of keratoconus are not available, so images were collected. These images were taken in a medical center in Shiraz under the supervision of a corneal specialist and with a size of 1024 * 1024. Any eye that has one of four characteristics is known as a keratoconus. In the end, all the results are compared with the results provided by the expert and the accuracy of the obtained result is measured.

Keywords

Corneal diagnosis, image processing, measurement criteria, topographic image characteristics

References

• [1] Klein, S. R., Epstein, R. J., Randleman, J. B., & Stulting, R. D. (2006). Corneal ectasia after laser in situ keratomileusis in patients without apparent preoperative risk factors. Cornea, 25(4), 388-403.
• [2] Randleman, J. B., Trattler, W. B., & Stulting, R. D. (2008). Validation of the Ectasia Risk Score System for preoperative laser in situ keratomileusis screening. American journal of ophthalmology, 145(5), 813-818.
• [3] Caporossi, A., Mazzotta, C., Baiocchi, S., & Caporossi, T. (2010). Long-term results of riboflavin ultraviolet a corneal collagen cross-linking for keratoconus in Italy: The Siena eye cross study. American journal of ophthalmology, 149(4), 585-593.
• [4] Klyce, S. D. (2009). Chasing the suspect: keratoconus.
• [5] Martínez-Abad, A., & Pinero, D. P. (2017). New perspectives on the detection and progression of keratoconus. Journal of Cataract & Refractive Surgery, 43(9), 1213-1227.
• [6] Shi, C., Wang, M., Zhu, T., Zhang, Y., Ye, Y., Jiang, J., ... & Shen, M. (2020). Machine learning helps improve diagnostic ability of subclinical keratoconus using Scheimpflug and OCT imaging modalities. Eye and Vision, 7(1), 1-12.
• [7] Zhang, X., Munir, S. Z., Karim, S. A. S., & Munir, W. M. (2020). A review of imaging modalities for detecting early keratoconus. Eye, 1-15.
• [8] Lavric, A., & Valentin, P. (2019). KeratoDetect: keratoconus detection algorithm using convolutional neural networks. Computational intelligence and neuroscience, 2019.
• [9] Lin, S. R., Ladas, J. G., Bahadur, G. G., Al-Hashimi, S., & Pineda, R. (2019, May). A review of machine learning techniques for keratoconus detection and refractive surgery screening. In Seminars in Ophthalmology (Vol. 34, No. 4, pp. 317-326). Taylor & Francis.
• [10] Sharifi Borojerdi, S., Karimi, M., & Amiri, E. (2020). Investigation of Warrior Robots Behavior by Using Evolutionary Algorithms. arXiv e-prints, arXiv-2011.
• [11] Auffarth, G. U., Wang, L., & Völcker, H. E. (2000). Keratoconus evaluation using the Orbscan topography system. Journal of Cataract & Refractive Surgery, 26(2), 222-228.
• [12] Arbelaez, M. C., Versaci, F., Vestri, G., Barboni, P., & Savini, G. (2012). Use of a support vector machine for keratoconus and subclinical keratoconus detection by topographic and tomographic data. Ophthalmology, 119(11), 2231-2238.
• [13] Holladay, J. T. (2009). Keratoconus detection using corneal topography. Journal of Refractive Surgery, 25(10), S958-S962.
• [14] Issarti, I., Consejo, A., Jiménez-García, M., Hershko, S., Koppen, C., & Rozema, J. J. (2019). Computer aided diagnosis for suspect keratoconus detection. Computers in biology and medicine, 109, 33-42.