Automated Segmentation of the Optic Disc from Stereo Color Photographs Using Physiologically Plausible Features

Abstract

The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.

Sliding Window and Regression Based Cup Detection in Digital Fundus Images for Glaucoma Diagnosis

“…In previous work, researchers have mainly focused on automated segmentation of the optic disc [5], using various techniques such as intensity gradient analysis, Hough transforms, template matching, pixel feature classification, vessel geometry analysis, deformable models and level sets [6] [7]. In this paper, we focus only on the challenging cup detection problem [8][9], using a large clinical dataset called ORIGA −light [10] in which the ground-truth of discs and cups is marked by a team of graders from a hospital.…”

Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Images for Diagnosing Retinal Diseases

“…We intend to differentiate between the retinal area and artefacts using textural, grayscale-gradient and regional based features. Textural and gradient based features are calculated from red and green channels on different Gaussian blurring scales; also known as smoothing scales [3]. In SLO images, the blue channel is set to zero therefore no feature was calculated for the blue channel.…”

“…In order to calculate these features, the response from Gaussian filter bank [3] is calculated. The Gaussian filter bank includes GLCM process using image I [13] Gaussian N (σ), its two first order derivatives N x (σ) and N y (σ) and three second order derivatives N xx (σ), N xy (σ) and N yy (σ) in horizontal(x) and vertical(y) directions.…”

Optic disc segmentation using the sliding band filter

“…There are several works on the automatic segmentation of OD in retinal images which can mainly be grouped into four categories, namely template-based methods [4,5,6,7], deformable model methods [8,9,10,11,12,13], morphological-based approaches [14,15,16], and pixel classification methods [17,18]. Within the first category, Aquino et al [4] follow a voting-type algorithm to locate a pixel within the OD as initial information to define a starting sub-image.…”

“…In the pixel-based classification category, Abràmoff et al [17] use feature selection and a knearest neighbor classifier. The final step is the classification of each pixel into rim, cup, or background.…”