Page 203 - Computational Retinal Image Analysis
P. 203

CHAPTER


                  Structure-preserving

                  guided retinal image                              11

                  filtering for optic disc

                  analysis




                             a
                                                    a
                                         b
                                                                                    d
                                                               c
                     Jun Cheng , Zhengguo Li , Zaiwang Gu , Huazhu Fu , Damon Wing Kee Wong ,
                                                                                    a
                                                                             Jiang Liu
                                   a Chinese Academy of Sciences, Cixi Institute of Biomedical Engineering,
                                                                    Ningbo, Zhejiang, China
                       b Agency for Science, Technology and Research, Institute for Infocomm Research, Singapore
                               c Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates
                                                     d Nanyang Technological University, Singapore
                  1  Introduction

                  Glaucoma is a chronic eye disease where the optic nerve is progressively damaged.
                  It is the second-leading cause of blindness predicted to affect around 80 million
                  people by 2020 [1]. It leads to loss of vision, which often occurs gradually over
                  a long period of time. As the symptoms of the disease only occur when it is quite
                  advanced, glaucoma is called the silent thief of sight. Glaucoma cannot be cured, but
                  its progression can be slowed down by treatment. Therefore, detecting glaucoma in
                  time is critical. However, more than 50–90% of people are unaware of the disease
                  until it has reached an advanced stage [2, 3]. Since glaucoma progresses silently,
                  screening of people at high risk for the disease is vital. Three types of methods
                  to detect glaucoma exist and are based on the following: (1) raised intraocular
                  pressure (IOP), (2) abnormal visual field, and (3) damaged optic nerve head. Since
                  glaucoma can be present with or without increased IOP, the IOP measurement is
                  not accurate enough to be an effective screening tool. A functional test for vision
                  loss  requires  special  equipments  only  present  in territory  hospitals  and  therefore
                  unsuitable for screening. Assessment of the damaged optic nerve head is superior to
                  IOP measurement or visual field testing for glaucoma screening. Optic nerve head
                  assessment can be done by a trained professional. However, manual assessment is
                  subjective, time consuming, and expensive. Therefore, automatic optic nerve head
                  assessment would be very beneficial.
                     The optic nerve head or the optic disc (in short, disc) is the location where ganglion
                  cell axons exit the eye to form the optic nerve, through which visual information of
                  the photo-receptors is transmitted to the brain. In 2D images, the disc can be divided

                  Computational Retinal Image Analysis. https://doi.org/10.1016/B978-0-08-102816-2.00011-3  199
                  © 2019 Elsevier Ltd. All rights reserved.
   198   199   200   201   202   203   204   205   206   207   208