MEDnet, a neural network for automated detection of avascular area in OCT angiography

Guo, Yukun; Camino, Acner; Wang, Jie; Huang, David; Hwang, Thomas S.; Jia, Yali

doi:10.1364/boe.9.005147

Cited by 75 publications

(52 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FA and ICGA have some limitations such as intravenous dye administration, time consuming (up to 20 minutes), absence of topographic 3-dimensional (3D) images, low image resolution, and difficulty in the quantification of findings [10]. e introduction of OCT angiography (OCT-A) has solved these issues and provides rapid, noninvasive, high-resolution 3D images, and reliable quantitative data from the retinal and choroidal vasculature and structures [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Foveal and Parafoveal Microvascular Density and Retinal Vessel Caliber Alteration in Inactive Graves’ Ophthalmopathy

Akpolat

Kurt

Yılmaz

et al. 2020

Journal of Ophthalmology

View full text Add to dashboard Cite

Purpose. We aimed to evaluate foveal and parafoveal density using optical coherence tomography angiography and the alteration on the retinal vessel diameter in patients with inactive Graves’ ophthalmopathy compared to age-matched normal population. Materials and Methods. Patients with inactive Graves’ ophthalmopathy (study group) and healthy individuals (control group) were enrolled in the cross sectionally designed study. The optical coherence tomography angiography parameters and retinal vessel diameter measurements were assessed between the study and control groups. Foveal and parafoveal microvascular density in the retina was measured using optical coherence tomography angiography. Retinal artery and vein diameter and artery/vein ratio were assessed for retinal vessel caliber changes. Results. Patients with inactive Graves’ ophthalmopathy had higher values of intraocular pressure, proptosis, and axial length (P=0.001, P=0.002, and P=0.008, respectively). Temporal parafoveal vessel density was 48.93 ± 3.21 and 47.62 ± 2.59 in the study and control groups, respectively (P=0.017). Nasal parafoveal vessel density was 47.55 ± 3.01 and 46.46 ± 2.57 in the study and control groups, respectively (P=0.035). Foveal, superior, and inferior parafoveal vessel density values were similar in the study and control groups (P=0.268, P=0.107, and P=0.055, respectively). Patients in the study group had narrower retinal artery and vein diameters (P≤0.001 and P=0.033). Artery/vein ratio was significantly higher in the control group (P≤0.001). Conclusion. Optical coherence tomography angiography could be a novel and promising noninvasive diagnostic technique in patients with inactive Graves’ ophthalmopathy to detect foveal and parafoveal vessel density changes compared to healthy subjects. The decrease of retinal vessel diameter might be observed in patients with inactive graves ophthalmopathy.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of Foveal and Parafoveal Microvascular Density and Retinal Vessel Caliber Alteration in Inactive Graves’ Ophthalmopathy

Akpolat

Kurt

Yılmaz

et al. 2020

Journal of Ophthalmology

View full text Add to dashboard Cite

show abstract

“…The maximum SBP and within-patient SD of SBP were negatively correlated with SVP vessel density, while positively correlated with SVP flow void area. Both vessel density and flow void area could be biomarkers for retinal vascular injury 8,15,16,31 . More severe vascular injury tends to present a larger flow void area and a lower vessel density.…”

Section: Discussionmentioning

confidence: 99%

Impact of blood pressure control on retinal microvasculature in patients with chronic kidney disease

Peng

Lee

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Chronic kidney disease (CKD) is an emerging disease worldwide. We investigated the relationship between blood pressure (Bp) control and parafoveal retinal microvascular changes in patients with CKD. This case-control study enrolled 256 patients with CKD (stage 3-5) and 70 age-matched healthy controls. Optical coherence tomography angiography showed lower superficial vascular plexus (SVP) vessel density, lower deep vascular plexus (DVP) vessel density, and larger SVP flow void area in the CKD group. The BP parameters at enrollment and during the year before enrollment were collected in patients with CKD. Partial correlation was used to determine the relationship between BP parameters and microvascular parameters after controlling for age, sex, diabetes mellitus, axial length, and intraocular pressure. The maximum systolic blood pressure (SBP) (p = 0.003) and within-patient standard deviation (SD) of SBP (p = 0.006) in 1 year were negatively correlated with SVP vessel density. The average SBP (p = 0.040), maximum SBP (p = 0.001), within-patient SD of SBP (p < 0.001) and proportion of high BP measurement (p = 0.011) in 1 year were positively correlated with the SVP flow void area. We concluded that long-term SBP was correlated with SVP microvascular injury in patients with CKD. Superficial retinal microvascular changes may be a potential biomarker for prior long-term BP control in these patients. Chronic kidney disease (CKD) is an emerging disease worldwide that is highly prevalent in elderly individuals and in patients with hypertension or diabetes mellitus (DM) 1. Approximately 10-15% of the world's population have CKD 2 , and the prevalence could be as high as 40% among diabetic patients 3. CKD is associated with many systemic vascular complications such as atherosclerosis, cerebrovascular disease, and cardiovascular disease 1. End-stage kidney disease may increase the risk of cardiovascular mortality by 10-30 folds 1. Retinal vasculature, which can be directly visualized using non-invasive tools, has been considered a potential window for systemic vascular complications 4-6. Fundus photography provided a convenient tool for correlating the risk of systemic vascular diseases and retinal vasculature [e.g. the central retinal arteriolar equivalent (CRAE) and the central retinal venular equivalent (CRVE)] 5. However, recent publications showed that systemic diseases may cause retinal capillary alterations preceding any visible pathology in fundus 7-9. Optical coherence tomography angiography (OCTA) technology provides a rapid non-invasive method to quantify microvasculature at the capillary level in the different retinal layers. It could detect early subtle retinal microvascular changes from systemic diseases 8-11. Using OCTA, we had demonstrated decreased parafoveal microvascular vessel densities in both superficial vascular plexus (SVP) and deep vascular plexus (DVP) in patients with CKD 12. eGFR was an independent

show abstract

“…3(c)) that may be visible but cannot be reliably annotated due to the inherent difficulty in inferring their shape and connectivity, especially in the 8 mm by 8 mm scans. Finally, we believe that works that address the task foveal avascular zone (FAZ) quantification in OCT-A [29] are complimentary to our vessel segmentation method and potentially there exists a synergy between the two tasks due to their common spatial and functional support.…”

Section: State-of-the-art Retinal Vessel Segmentationmentioning

confidence: 99%

Deep iterative vessel segmentation in OCT angiography

Pissas¹,

Bloch²,

Cardoso³

et al. 2020

Biomed. Opt. Express

View full text Add to dashboard Cite

This paper addresses retinal vessel segmentation on optical coherence tomography angiography (OCT-A) images of the human retina. Our approach is motivated by the need for high precision image-guided delivery of regenerative therapies in vitreo-retinal surgery. OCT-A visualizes macular vasculature, the main landmark of the surgically targeted area, at a level of detail and spatial extent unattainable by other imaging modalities. Thus, automatic extraction of detailed vessel maps can ultimately inform surgical planning. We address the task of delineation of the Superficial Vascular Plexus in 2D Maximum Intensity Projections (MIP) of OCT-A using convolutional neural networks that iteratively refine the quality of the produced vessel segmentations. We demonstrate that the proposed approach compares favourably to alternative network baselines and graph-based methodologies through extensive experimental analysis, using data collected from 50 subjects, including both individuals that underwent surgery for structural macular abnormalities and healthy subjects. Additionally, we demonstrate generalization to 3D segmentation and narrower field-of-view OCT-A. In the future, the extracted vessel maps will be leveraged for surgical planning and semi-automated intraoperative navigation in vitreo-retinal surgery.

show abstract

MEDnet, a neural network for automated detection of avascular area in OCT angiography

Cited by 75 publications

References 33 publications

Analysis of Foveal and Parafoveal Microvascular Density and Retinal Vessel Caliber Alteration in Inactive Graves’ Ophthalmopathy

Analysis of Foveal and Parafoveal Microvascular Density and Retinal Vessel Caliber Alteration in Inactive Graves’ Ophthalmopathy

Impact of blood pressure control on retinal microvasculature in patients with chronic kidney disease

Deep iterative vessel segmentation in OCT angiography

Contact Info

Product

Resources

About