Chapter 10
Layer Segmentation and Analysis
for Retina with Diseases
Fei Shi, Weifang Zhu and Xinjian Chen
Though segmentation of normal retina has been successful, segmentation and analysis of pathological retina are far more important. This chapter first presents an
automatic layer segmentation method for retinas with certain deformed layers, and
then introduces two layer disruption detection methods based on feature analysis of
segmented layers.
10.1 Introduction
It is with the development of optical coherence tomography (OCT) technique, an
in vivo and noninvasive scan of the retina that shows its cross-sectional profile, that
the layered structure of retina can be extensively studied. Recently introduced spectral
domain (SD) OCT produces high resolution real 3-D volumetric scan of the retina
that visualize most of the anatomical layers. Automated retinal layer segmentation
for normal eyes based on SD-OCT images have been successful [1–14]. However,
layer segmentation of retina with diseases is of more value to both pathological study
and clinical practice. Some of the methods proposed for normal retinas can also be
applied to retinas with certain types of diseases, such as glaucoma [9–11], multiple
sclerosis [12], dry age-related macular degeneration (AMD) [13], or other diseases
at an early stage, when no dramatic change in the layer structure happens. However,
layer segmentation for diseased retina still remains a challenging problem, especially
when additional structures exist, such as intraretinal cysts, subretinal or sub-RPE
F. Shi · W. Zhu · X. Chen
School of Electronics and Information Engineering, Soochow University, Suzhou, China
X. Chen (B)
State Key Laboratory of Radiation Medicine and Protection, Soochow University,
Suzhou, China
e-mail: xjchen@suda.edu.cn
© Science Press and Springer Nature Singapore Pte Ltd. 2019
X. Chen et al. (eds.), Retinal Optical Coherence Tomography Image Analysis,
Biological and Medical Physics, Biomedical Engineering,
https://doi.org/10.1007/978-981-13-1825-2_10
243
Layer Segmentation and Analysis
for Retina with Diseases
Fei Shi, Weifang Zhu and Xinjian Chen
Though segmentation of normal retina has been successful, segmentation and analysis of pathological retina are far more important. This chapter first presents an
automatic layer segmentation method for retinas with certain deformed layers, and
then introduces two layer disruption detection methods based on feature analysis of
segmented layers.
10.1 Introduction
It is with the development of optical coherence tomography (OCT) technique, an
in vivo and noninvasive scan of the retina that shows its cross-sectional profile, that
the layered structure of retina can be extensively studied. Recently introduced spectral
domain (SD) OCT produces high resolution real 3-D volumetric scan of the retina
that visualize most of the anatomical layers. Automated retinal layer segmentation
for normal eyes based on SD-OCT images have been successful [1–14]. However,
layer segmentation of retina with diseases is of more value to both pathological study
and clinical practice. Some of the methods proposed for normal retinas can also be
applied to retinas with certain types of diseases, such as glaucoma [9–11], multiple
sclerosis [12], dry age-related macular degeneration (AMD) [13], or other diseases
at an early stage, when no dramatic change in the layer structure happens. However,
layer segmentation for diseased retina still remains a challenging problem, especially
when additional structures exist, such as intraretinal cysts, subretinal or sub-RPE
F. Shi · W. Zhu · X. Chen
School of Electronics and Information Engineering, Soochow University, Suzhou, China
X. Chen (B)
State Key Laboratory of Radiation Medicine and Protection, Soochow University,
Suzhou, China
e-mail: xjchen@suda.edu.cn
© Science Press and Springer Nature Singapore Pte Ltd. 2019
X. Chen et al. (eds.), Retinal Optical Coherence Tomography Image Analysis,
Biological and Medical Physics, Biomedical Engineering,
https://doi.org/10.1007/978-981-13-1825-2_10
243