Chapter 4
Reconstruction of Retinal OCT Images
with Sparse Representation
Leyuan Fang and Shutao Li
In addition to the speckle noise introduced in the acquisition process, clinical-used
OCT images often have high resolution and thus create a heavy burden for storage
and transmission. To alleviate these problems, this chapter introduces several sparse
representation based reconstruction methods for denoising, interpolation and compression, which enhance the quality of the OCT images and efficiently manage such
large of amounts of data.
4.1 Introduction
Optical coherence tomography (OCT) is a non-invasive, cross-sectional imaging
modality which has been widely applied for diverse medical applications, especially
for diagnostic ophthalmology [1]. In clinical diagnosis, the ophthalmologists often
require high resolution and high signal-to-noise-ratio (SNR) OCT images. However,
due to the highly controlled imaging environment (e.g., limited light intensities),
the acquired OCT images are seriously interfered by heavy noise [2–4]. In addition,
to accelerate the acquisition process, relatively low spatial sampling rates are often
used in capturing clinical OCT images [5]. Both the heavy noise and low spatial
sampling rates negatively affect the analysis of the OCT image, necessitating the
utilization of effective denoising and interpolation techniques. Furthermore, storage
and transmission of the high resolution and high SNR OCT images consumes a
vast amount of memory and communication bandwidth, which exceeds the limits
of current clinical data archiving systems, and creates a heavy burden for remote
consultation and diagnosis. Therefore, development of efficient image compression
technique is often required to process such large amounts of data.
L. Fang · S. Li (B)
College of Electrical and Information Engineering, Hunan University, Changsha, China
e-mail: shutao_li@hnu.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_4
73
Reconstruction of Retinal OCT Images
with Sparse Representation
Leyuan Fang and Shutao Li
In addition to the speckle noise introduced in the acquisition process, clinical-used
OCT images often have high resolution and thus create a heavy burden for storage
and transmission. To alleviate these problems, this chapter introduces several sparse
representation based reconstruction methods for denoising, interpolation and compression, which enhance the quality of the OCT images and efficiently manage such
large of amounts of data.
4.1 Introduction
Optical coherence tomography (OCT) is a non-invasive, cross-sectional imaging
modality which has been widely applied for diverse medical applications, especially
for diagnostic ophthalmology [1]. In clinical diagnosis, the ophthalmologists often
require high resolution and high signal-to-noise-ratio (SNR) OCT images. However,
due to the highly controlled imaging environment (e.g., limited light intensities),
the acquired OCT images are seriously interfered by heavy noise [2–4]. In addition,
to accelerate the acquisition process, relatively low spatial sampling rates are often
used in capturing clinical OCT images [5]. Both the heavy noise and low spatial
sampling rates negatively affect the analysis of the OCT image, necessitating the
utilization of effective denoising and interpolation techniques. Furthermore, storage
and transmission of the high resolution and high SNR OCT images consumes a
vast amount of memory and communication bandwidth, which exceeds the limits
of current clinical data archiving systems, and creates a heavy burden for remote
consultation and diagnosis. Therefore, development of efficient image compression
technique is often required to process such large amounts of data.
L. Fang · S. Li (B)
College of Electrical and Information Engineering, Hunan University, Changsha, China
e-mail: shutao_li@hnu.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_4
73