Vessel segmentation in images of optical coherence tomography using shadow information and thickening of Retinal Nerve Fiber Layer

Kafieh, Raheleh; Danesh, Hajar; Rabbani, Hossein; Abràmoff, Michael D.; Sonka, Milan

doi:10.1109/icassp.2013.6637815

Cited by 10 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anatomically, the medium-caliber vessels from the central artery of the retina are located in the GCL and IPL [ 36 ]. The image of medium-caliber vessels has been described as hyperintense in the GCL with a prominent posterior shadow that presents higher contrast in the inner retina [ 37 ]. The hyper-reflective lesions reported in the abovementioned study could be included within this description, as they are located more frequently in the papillomacular area, where the horizontal arrangement of the vessels causes longitudinal cross-sections of the vessels, as they present the same orientation as the horizontal B-scan.…”

Section: Discussionmentioning

confidence: 99%

Retinal Microvascular Impairment in COVID-19 Bilateral Pneumonia Assessed by Optical Coherence Tomography Angiography

et al. 2021

View full text Add to dashboard Cite

The purpose of this study was to evaluate the presence of retinal and microvascular alterations in COVID-19 patients with bilateral pneumonia due to SARS-COV-2 that required hospital admission and compare this with a cohort of age- and sex-matched controls. COVID-19 bilateral pneumonia patients underwent retinal imaging 14 days after hospital discharge with structural optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) measurements. Vessel density (VD) and foveal avascular zone (FAZ) area were evaluated in the superficial, deep capillary plexus (SCP, DCP), and choriocapillaris (CC). After exclusion criteria, only one eye per patient was selected, and 50 eyes (25 patients and 25 controls) were included in the analysis. COVID-19 patients presented significantly thinner ganglion cell layer (GCL) (p = 0.003) and thicker retinal nerve fiber layer (RNFL) compared to controls (p = 0.048), and this RNFL thickening was greater in COVID-19 cases with cotton wool spots (CWS), when compared with patients without CWS (p = 0.032). In both SCP and DCP, COVID-19 patients presented lower VD in the foveal region (p < 0.001) and a greater FAZ area than controls (p = 0.007). These findings suggest that thrombotic and inflammatory phenomena could be happening in the retina of COVID-19 patients. Further research is warranted to analyze the longitudinal evolution of these changes over time as well as their correlation with disease severity.

show abstract

Section: Discussionmentioning

confidence: 99%

Retinal Microvascular Impairment in COVID-19 Bilateral Pneumonia Assessed by Optical Coherence Tomography Angiography

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The local brightness of the x z y location hosting the vessel is considered and each new vessel profile is normalized to match the host region [34]. The vessel intensity profiles are then placed in locations calculated using the shadow-based method [50].…”

Section: Synthetic Layer Content In 3dmentioning

confidence: 99%

Synthetic OCT data in challenging conditions: three-dimensional OCT and presence of abnormalities

Danesh

Maghooli

Dehghani

et al. 2021

Med Biol Eng Comput

Self Cite

View full text Add to dashboard Cite

Nowadays, retinal optical coherence tomography (OCT) plays an important role in ophthalmology and automatic analysis of the OCT is of real importance: image denoising facilitates a better diagnosis and image segmentation and classification are undeniably critical in treatment evaluation. Synthetic OCT was recently considered to provide a benchmark for quantitative comparison of automatic algorithms and to be utilized in the training stage of novel solutions based on deep learning. Due to complicated data structure in retinal OCTs, a limited number of delineated OCT datasets are already available in presence of abnormalities; furthermore, the intrinsic three-dimensional (3D) structure of OCT is ignored in many public 2D datasets. We propose a new synthetic method, applicable to 3D data and feasible in presence of abnormalities like diabetic macular edema (DME). In this method, a limited number of OCT data is used during the training step and the Active Shape Model is used to produce synthetic OCTs plus delineation of retinal boundaries and location of abnormalities. Statistical comparison of thickness maps showed that synthetic dataset can be used as a statistically acceptable representative of the original dataset (p > 0.05). Visual inspection of the synthesized vessels was also promising. Regarding the texture features of the synthesized datasets, Q-Q plots were used, and even in cases that the points have slightly digressed from the straight line, the p-values of the Kolmogorov–Smirnov test rejected the null hypothesis and showed the same distribution in texture features of the real and the synthetic data. The proposed algorithm provides a unique benchmark for comparison of OCT enhancement methods and a tailored augmentation method to overcome the limited number of OCTs in deep learning algorithms. Graphical abstract

show abstract

“…To produce images with highest similarity to the reference image, blood vessels are also added to the image. Since the presence of shadows in the outer layers of the retina is the main factor determining the vessel location [28], after finding the reference image (section 2.3) the brightness profile of the pixels between the boundaries (OPL) and (BM) are computed. A moving average filter is applied to each intensity profile to estimate the drift line to be eliminated.…”

Section: Inserting Blood Vesselsmentioning

confidence: 99%

Automatic Production of Synthetic Labeled OCT Images Using Active Shape Model

Danesh

Maghooli

Kafieh

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The challenge of limited labeled data in the field of medical imaging and the need for large number of labeled data for training machine learning algorithms, and to measure the performance of image processing algorithms increases the demand to use synthetic images. The purpose of this paper is to construct synthetic and labeled Optical Coherence Tomography (OCT) data to solve the problems like having access to the accurate labeled data and evaluating the processing algorithms. In this study, a modified active shape model is used which considers the anatomical features of available images such as number and thickness of the layers and their associated brightness, the retinal blood vessels, and shadow information with wise consideration of speckle noise. The algorithm is also able to provide different datasets with varying noise level. The validity of our method for synthesis of retinal images is measured by two methods (qualitative assessment and quantitative analysis).

show abstract

Vessel segmentation in images of optical coherence tomography using shadow information and thickening of Retinal Nerve Fiber Layer

Cited by 10 publications

References 14 publications

Retinal Microvascular Impairment in COVID-19 Bilateral Pneumonia Assessed by Optical Coherence Tomography Angiography

Retinal Microvascular Impairment in COVID-19 Bilateral Pneumonia Assessed by Optical Coherence Tomography Angiography

Synthetic OCT data in challenging conditions: three-dimensional OCT and presence of abnormalities

Automatic Production of Synthetic Labeled OCT Images Using Active Shape Model

Contact Info

Product

Resources

About