Automated Hole and Non-hole Screening in Retinal OCT Images Using Local Binary Patterns with Support Vector Machine
- PDF / 307,314 Bytes
- 3 Pages / 595.276 x 790.866 pts Page_size
- 81 Downloads / 191 Views
SHORT COMMUNICATION
Automated Hole and Non-hole Screening in Retinal OCT Images Using Local Binary Patterns with Support Vector Machine Piyush Mishra1
•
Charul Bhatnagar1
Received: 6 July 2017 / Revised: 20 January 2020 / Accepted: 21 January 2020 The National Academy of Sciences, India 2020
Abstract Macular hole (MH) formation in between the retinal layers causes distorted vision and decrease in the person’s visual acuity. MH is also the chronic stage of retinal disorder, significantly treated only by surgeries. This work addresses to the automated screening of the hole and non-hole images in the cross-sectional depiction of retinal optical coherence tomography (OCT) images. Screening between hole and non-hole comprises various pathological traces observed in the retinal OCT scans, aiming to automatically differentiating the retinal hole present in the macula and other macular pathologies. Machine learning utilizes local binary pattern with reduced dimension, as local descriptors, in which the texture information from the retinal OCT images is encoded. For the identification of the MH, support vector machine classifier is used. Dataset was prepared for 51 unseen OCT scans from 14 patients having orientation variabilities and used for extensive experimentation. Method effectiveness was verified through results, and the statement supported with the evaluations was performed across the dataset. Systems’ overall performance was validated stochastically where the system sensitivity is 92.3% and the specificity is 92%. Keywords Retinal image processing Computer-aided diagnosis Optical coherence tomography Macular hole
& Piyush Mishra [email protected] 1
GLA University, Chaumuhan, India
OCT is a contactless, noninvasive imaging modality, which depicts cross-sectional view. Its wide acceptance in identification of diseases and their progression has standardized it as first choice for Ophthalmological care [1]. Huge availability of OCT data justifies requirement of computeraided systems to support disease screening and diagnosis. Such requirements are necessity since under standard clinical conditions, there is no radiologist interpretation of OCT data available for decision making during disease diagnosis. Previous researches addressing different topics in retinal image (OCT) processing include segmenting retinal layers [2] and assessing localized quality [3]. Peculiarly in elderly persons, and in consideration to various public health issues, automated screening and diagnosing the presence of macular holes (MHs) in a given OCT scan are substantial. Complications and challenges in automated screening of macular hole in retinal OCT images are: First, for more than one pathological coexistence, this gets further complicated with rise in the number of pathologies present. Second, the optical properties possessed by the light reflecting tissues affect reflectivity [1], leading to the shadowing effect, for example, the presence of translucentmattered tissues or blood vessels absorbing light may produce such i
Data Loading...
