4 Reconstruction of Retinal OCT Images with Sparse Representation
99
Table 4.3 Mean of the PSNR (left) and FSIM (right) for 16 foveal images from 16 different
subjects reconstructed by JPEG 2000, MPEG-4, SPIHT [60], K-SVD [30], SRC-DIF, 2D-ASRC,
3D-ASRC-WA, and 3D-ASRC under different compression ratios
Method
Compression ratio
10
15
20
25
30
35
40
JPEG
2000
19.67/0.65 20.33/0.67 20.70/0.69 21.34/0.70 21.92/0.70 22.41/0.71 22.78/0.71
MPEG-4 20.42/0.72 22.44/0.78 22.63/0.79 22.71/0.79 22.76/0.79 23.21/0.78 23.22/0.79
SPIHT
25.56/0.80 26.17/0.82 26.50/0.82 26.68/0.82 26.79/0.82 26.86/0.82 26.89/0.82
K-SVD
20.74/0.68 22.51/0.70 22.51/0.72 23.06/0.74 23.56/0.75 23.94/0.75 24.28/0.76
SRC-Dif 26.98/0.85 27.26/0.86 27.45/0.87 27.54/0.87 27.56/0.87 27.58/0.86 27.55/0.86
2D-ASRC 26.14/0.81 26.51/0.82 26.73/0.82 26.85/0.83 26.89/0.83 26.91/0.83 26.99/0.83
ASRCWA
26.31/0.82 26.70/0.83 26.97/0.84 27.11/0.85 27.23/0.85 27.29/0.85 27.33/0.85
3D-ASRC 27.60/0.88 27.65/0.87 27.68/0.87 27.71/0.87 27.75/0.87 27.75/0.87 27.74/0.87
The best results in this table are labeled in bold
4.4 Conclusions
In this chapter, we presented three adaptive sparse representation methods for the
denoising, interpolation, and compression of OCT images. Specifically, for the
denoising problem, we proposed a multiscale sparsity based method called MSBTD,
which can well represent the multiscale information of the pathology structures and
learn high quality dictionaries from the nearby high SNR B-scan. For the interpolation
problem, we proposed an efficient sparsity based image reconstruction framework
called SBSDI that achieve a simultaneous interpolation and denoising of the clinical
SDOCT images via a pair of semi-coupled dictionaries. For the compression problem, we introduced a 3D adaptive sparse compression called 3D-ASRC, which can
simultaneously represent the nearby slices of the SDOCT images via a 3D adaptive
sparse representation algorithm. Such a 3D adaptive algorithm exploits similarities
among nearby slices, yet is sensitive in preserving their differences. Experiments on
real acquired clinical OCT images demonstrate the superiority of the proposed three
sparsity based reconstruction methods over several state-of-the-art reconstruction
methods.
99
Table 4.3 Mean of the PSNR (left) and FSIM (right) for 16 foveal images from 16 different
subjects reconstructed by JPEG 2000, MPEG-4, SPIHT [60], K-SVD [30], SRC-DIF, 2D-ASRC,
3D-ASRC-WA, and 3D-ASRC under different compression ratios
Method
Compression ratio
10
15
20
25
30
35
40
JPEG
2000
19.67/0.65 20.33/0.67 20.70/0.69 21.34/0.70 21.92/0.70 22.41/0.71 22.78/0.71
MPEG-4 20.42/0.72 22.44/0.78 22.63/0.79 22.71/0.79 22.76/0.79 23.21/0.78 23.22/0.79
SPIHT
25.56/0.80 26.17/0.82 26.50/0.82 26.68/0.82 26.79/0.82 26.86/0.82 26.89/0.82
K-SVD
20.74/0.68 22.51/0.70 22.51/0.72 23.06/0.74 23.56/0.75 23.94/0.75 24.28/0.76
SRC-Dif 26.98/0.85 27.26/0.86 27.45/0.87 27.54/0.87 27.56/0.87 27.58/0.86 27.55/0.86
2D-ASRC 26.14/0.81 26.51/0.82 26.73/0.82 26.85/0.83 26.89/0.83 26.91/0.83 26.99/0.83
ASRCWA
26.31/0.82 26.70/0.83 26.97/0.84 27.11/0.85 27.23/0.85 27.29/0.85 27.33/0.85
3D-ASRC 27.60/0.88 27.65/0.87 27.68/0.87 27.71/0.87 27.75/0.87 27.75/0.87 27.74/0.87
The best results in this table are labeled in bold
4.4 Conclusions
In this chapter, we presented three adaptive sparse representation methods for the
denoising, interpolation, and compression of OCT images. Specifically, for the
denoising problem, we proposed a multiscale sparsity based method called MSBTD,
which can well represent the multiscale information of the pathology structures and
learn high quality dictionaries from the nearby high SNR B-scan. For the interpolation
problem, we proposed an efficient sparsity based image reconstruction framework
called SBSDI that achieve a simultaneous interpolation and denoising of the clinical
SDOCT images via a pair of semi-coupled dictionaries. For the compression problem, we introduced a 3D adaptive sparse compression called 3D-ASRC, which can
simultaneously represent the nearby slices of the SDOCT images via a 3D adaptive
sparse representation algorithm. Such a 3D adaptive algorithm exploits similarities
among nearby slices, yet is sensitive in preserving their differences. Experiments on
real acquired clinical OCT images demonstrate the superiority of the proposed three
sparsity based reconstruction methods over several state-of-the-art reconstruction
methods.