Paper Info
Title
Min-Cut Segmentation of Retinal OCT Images.
Abstract
Optical Coherence Tomography (OCT) is one of the most vital tools for diagnosing and tracking progress of medication of various retinal disorders. Many methods have been proposed to aid with the analysis of retinal images due to the intricacy of retinal structures, the tediousness of manual segmentation and variation from different specialists. However image artifacts, in addition to inhomogeneity in pathological structures, remain a challenge, with negative influence on the performance of segmentation algorithms. In this paper we present an automatic retinal layer segmentation method, which comprises of fuzzy histogram hyperbolization and graph cut methods. We impose hard constraints to limit search region to sequentially segment 8 boundaries and 7 layers of the retina on 150 OCT B-Sans images, 50 each from the temporal, nasal and center of foveal regions. Our method shows positive results, with additional tolerance and adaptability to contour variance and pathological inconsistence of the retinal structures in all regions.
Year
DOI
Venue
2018
10.1007/978-3-030-29196-9_5
BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, BIOSTEC 2018
Keywords
Field
DocType
Retinal layer segmentation,Optical Coherence Tomography,Graph-cut,Image analysis
Cut,Computer vision,Data mining,Histogram,Optical coherence tomography,Retinal Disorder,Retina,Segmentation,Computer science,Foveal,Artificial intelligence,Retinal
Conference
Volume
ISSN
Citations 
1024
1865-0929
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Bashir Isa Dodo100.34
Yongmin Li2595.19
Khalid Eltayef300.34
Xiaohui Liu45042269.99