Application of Independent Component Analysis techniques in speckle noise reduction of retinal OCT images

Baghaie, Ahmadreza; D’Souza, Roshan; Yu, Zeyun

doi:10.1016/j.ijleo.2016.03.078

Cited by 24 publications

(9 citation statements)

References 30 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Retinal image processing is a very attractive branch of biomedical image processing [62][63][64]. As an example of such a technique, 3D reconstruction of the Optic Nerve Head (ONH) in the retina can be mentioned.…”

Section: Applications In Biomedical Image Processingmentioning

confidence: 99%

Dense Descriptors for Optical Flow Estimation: A Comparative Study

Baghaie

D’Souza

2017

J. Imaging

Self Cite

View full text Add to dashboard Cite

Estimating the displacements of intensity patterns between sequential frames is a very well-studied problem, which is usually referred to as optical flow estimation. The first assumption among many of the methods in the field is the brightness constancy during movements of pixels between frames. This assumption is proven to be not true in general, and therefore, the use of photometric invariant constraints has been studied in the past. One other solution can be sought by use of structural descriptors rather than pixels for estimating the optical flow. Unlike sparse feature detection/description techniques and since the problem of optical flow estimation tries to find a dense flow field, a dense structural representation of individual pixels and their neighbors is computed and then used for matching and optical flow estimation. Here, a comparative study is carried out by extending the framework of SIFT-flow to include more dense descriptors, and comprehensive comparisons are given. Overall, the work can be considered as a baseline for stimulating more interest in the use of dense descriptors for optical flow estimation.

show abstract

Section: Applications In Biomedical Image Processingmentioning

confidence: 99%

Dense Descriptors for Optical Flow Estimation: A Comparative Study

Baghaie

D’Souza

2017

J. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Существуют различные методы фильтрации шумов рассеяния в ОКТ-сигналах [22][23][24][25][26][27][28][29][30][31]. Среди них широкое распространение получили методы накопления сигналов, выделения полезной составляющей сигнала с помощью априорной оценки параметров и модели шума, цифровой фильтрации (медианной, винеровской, билатеральной и пороговой), а также вейвлетной фильтрации.…”

Section: Introductionunclassified

Экспериментально Обучаемый Метод Фильтрации Шумов Рассеяния В Сигналах Оптической Когерентной Томографии-=sup=-*-=/Sup=-

Долганова¹,

Черномырдин²,

Александрова³

et al. 2019

Журнал Технической Физики

View full text Add to dashboard Cite

A method for wavelet filtration procedure training for optical coherence tomography (OCT) images using the experimental measurements of test objects that were constructed by means of water solutions of monodisperse nanoparticles and several microscopic inclusions has been described in the present paper. The choice of test-object parameters (concentration of water solution, size of nanoparticles, and shape, dimensions, and mutual position of inclusions) has allowed the modeling of various working conditions of OCT and setting different criteria for estimation of filtration efficiency. In the present work, the optimal filter for the considered example of a test object has been selected among the combinations of various basic functions of five wavelet families, soft and hard threshold filtering methods, four decomposition levels, and threshold values in a range of 0.05–3.05. The mutual position of the micro-inclusions has been used as a criterion for evaluating the filtration efficiency. As a result, it has been shown that the determined wavelet filter leads to effective suppression of the scattering noise in OCT images and preserve information about the structure of the object under study.

show abstract

“…In this case, the averaging should include algorithms of image alignment. Making some assumptions about noise statistics and properties, such methods as independent component analysis, 42 robust principal component analysis, 43 and statistical-based approach 44 give appropriate results, but remain computationally complicated and timeconsuming.…”

Section: Introductionmentioning

confidence: 99%

Nanoparticle-enabled experimentally trained wavelet-domain denoising method for optical coherence tomography

et al. 2018

View full text Add to dashboard Cite

We present the nanoparticle-enabled experimentally trained wavelet-domain denoising method for optical coherence tomography (OCT). It employs an experimental training algorithm based on imaging of a test-object, made of the colloidal suspension of the monodisperse nanoparticles and contains the microscale inclusions. The geometry and the scattering properties of the test-object are known a priori allowing us to set the criteria for the training algorithm. Using a wide set of the wavelet kernels and the wavelet-domain filtration approaches, the appropriate filter is constructed based on the test-object imaging. We apply the proposed approach and chose an efficient wavelet denoising procedure by considering the combinations of the decomposition basis from five wavelet families with eight types of the filtration threshold. We demonstrate applicability of the wavelet-filtering for the in vitro OCT image of human brain meningioma. The observed results prove high efficiency of the proposed OCT image denoising technique.

show abstract

Application of Independent Component Analysis techniques in speckle noise reduction of retinal OCT images

Cited by 24 publications

References 30 publications

Dense Descriptors for Optical Flow Estimation: A Comparative Study

Dense Descriptors for Optical Flow Estimation: A Comparative Study

Экспериментально Обучаемый Метод Фильтрации Шумов Рассеяния В Сигналах Оптической Когерентной Томографии-=sup=-*-=/Sup=-

Nanoparticle-enabled experimentally trained wavelet-domain denoising method for optical coherence tomography

Contact Info

Product

Resources

About