Implementation of Deep Learning Neural Network for Retinal Images

Implementation of Deep Learning Neural Network for Retinal Images

R. Murugan (National Institute of Technology Silchar, India)
DOI: 10.4018/978-1-5225-9902-9.ch005


The retinal parts segmentation has been recognized as a key component in both ophthalmological and cardiovascular sickness analysis. The parts of retinal pictures, vessels, optic disc, and macula segmentations, will add to the indicative outcome. In any case, the manual segmentation of retinal parts is tedious and dreary work, and it additionally requires proficient aptitudes. This chapter proposes a supervised method to segment blood vessel utilizing deep learning methods. All the more explicitly, the proposed part has connected the completely convolutional network, which is normally used to perform semantic segmentation undertaking with exchange learning. The convolutional neural system has turned out to be an amazing asset for a few computer vision assignments. As of late, restorative picture investigation bunches over the world are rapidly entering this field and applying convolutional neural systems and other deep learning philosophies to a wide assortment of uses, and uncommon outcomes are rising constantly.
Chapter Preview


The eye is an important organ that allows human to observe, react and adapt to surrounding environments. It also enables to interpret shapes, colours and dimensions of objects visualized. Eye contains three major layers, an outer layer sclera in continuation with cornea, a vascular layer choroid and the neurosensory component retina. The visible parts of the eye also include the colour (blue, green, brown or a mixture of these) iris, and an opening in the iris, the normally black pupil. A ray of light, after passing through the cornea, which partially focuses the image, passes through the anterior chamber, the pupil, lens, vitreous and is then focused on the retina. The retina is supported by pigment epithelium, which is normally opaque (Livingstone & Hubel, 1988). The Anatomy of human eye is shown in Figure 1.

Figure 1.

Anatomy of human eye (Source: Livingstone & Hubel 1988)


The neurosensory retina, usually called retina, is the largest part of the fundus which is the interior surface of the eye. The retina is a multi-layered sensory tissue that lines the back of the eye. The fundus includes the retina, the optic disc, and the macula. The retina is located in the eyeball as shown in Figure 2. The retina contains millions of photo-receptors that capture light rays and converts them into electrical impulses. These impulses travel along the optic nerve to the brain. The brain then “interprets” the electrical message sent to it, resulting in vision (Foracchia et al. 2004)

Figure 2.

Location and appearance of the retina (Source: Foracchia et al. 2004)


There are two types of photo-receptors in the retina: rods and cones, named after their shape. The retina contains approximately 6 to 7 million cones and about 125 million rods. Rods are the photo-receptors that are more responsive to light than the cones. Whether the cones or rods are used, depends on the amount of incoming light. In daylight the cones are the most active, under dark circumstances the rods are the most active and at dusk a combination of the two are used. In the human eye there are three distinct types of cones, and each type of cone responds to a different part of the colour spectrum. When the three different types of cones are located in a small area of the retina, the responses are combined. This enables us to see colors from the color spectrum. The rods, on the other hand, are not sensitive to color (Youssif et al. 2008).

When light enters the pupil, it is focused by the cornea and lens, and is projected onto the retina. The retina converts light into electrical impulses by use of the rods and cones, but the cells that transmit the neural signal to the brain are the ganglion cells. The axons of these ganglion cells make up the optic nerve, the single route by which information leaves the eye. When examining the back of the eye a portion of the optic nerve called the optic disc can be seen. At the optic disc the retina contains no photo-receptors. The result of having no photo-receptors at the optic disc is that light cannot be converted to neural signals and this creates a hole in our vision. That is why the optic disc is often called the blind spot (Hoover at al.2003).

Key Terms in this Chapter

Diabetic retinopathy: Diabetic retinopathy is the most common cause of vision loss among people with diabetes and a leading cause of blindness among working-age adults. DME is a consequence of diabetic retinopathy that causes swelling in the area of the retina called the macula.

Convolutional Neural Network: In deep learning, a convolutional neural network is a class of deep neural networks, most commonly applied to analyzing visual imagery. CNNs use a variation of multilayer perceptrons designed to require minimal preprocessing.

Deep Learning: Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised.

Blood Vessels: A retinal vessel occlusion is a blockage in the blood vessel of your eye that can result in sight loss. There are two types of retinal blood vessels, arteries and veins.

Glaucoma: Glaucoma is a group of related eye disorders that cause damage to the optic nerve that carries information from the eye to the brain. The increased pressure, called intraocular pressure, can damage the optic nerve, which transmits images to your brain. If the damage continues, glaucoma can lead to permanent vision loss. Without treatment, glaucoma can cause total permanent blindness within a few years.

Machine Learning: Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves.

Retina: The retina is a thin layer of tissue that lines the back of the eye on the inside. It is located near the optic nerve. The purpose of the retina is to receive light that the lens has focused, convert the light into neural signals, and send these signals on to the brain for visual recognition.

Complete Chapter List

Search this Book: