Corpus ID: 236171000

A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image

  title={A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image},
  author={Yufei Wang and Yiqing Shen and Meng Yuan and Jing Xu and Bin Yang and Chi Liu and Wenjia Cai and Weijing Cheng and Wei Wang},
  • Yufei Wang, Yiqing Shen, +6 authors Wei Wang
  • Published 2021
  • Computer Science, Engineering
  • ArXiv
Optical Coherence Tomography Angiography (OCTA) is a non-invasive and non-contacting imaging technique providing visualization of microvasculature of retina and optic nerve head in human eyes in vivo. The adequate image quality of OCTA is the prerequisite for the subsequent quantification of retinal microvasculature. Traditionally, the image quality score based on signal strength is used for discriminating low quality. However, it is insufficient for identifying artefacts such as motion and off… Expand


Automated OCT angiography image quality assessment using a deep learning algorithm
Deep learning (DL) appears to be a potential approach to automatically distinguish between sufficient and insufficient OCTA image quality. Expand
Foveal avascular zone segmentation in optical coherence tomography angiography images using a deep learning approach
The DL model showed an excellent accuracy in detection of FAZ border in en face optical coherence tomography angiography images of both diabetic patients and healthy subjects and outperformed the automated measurements of the built-in software. Expand
A Novel Deep Learning Based OCTA De-striping Method
This paper proposes a revised U-net framework for removing the stripe noise from OCTA images, leaving a clean image, and evaluates the effectiveness of the proposed method using the peak-signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM), achieving excellent results. Expand
Development and validation of a deep learning algorithm for distinguishing the nonperfusion area from signal reduction artifacts on OCT angiography.
A convolutional neural network is developed, MEDnet-V2, to distinguish NPA from signal reduction artifacts in 6×6 mm2 OCTA and achieves strong specificity and sensitivity for NPA detection across a wide range of DR severity and scan quality. Expand
MEDnet, a neural network for automated detection of avascular area in OCT angiography.
A first deep learning solution to segment the avascular area in OCTA of DR, which was effectively detected in DR subjects of various disease stages as well as in the foveal avascular zone of healthy subjects. Expand
Optical coherence tomography angiography of the retina and choroid; current applications and future directions
The ability of OCTA to identify and quantify vascular changes in different ocular diseases including retinal vascular occlusive disorders, neovascular age related macular degeneration (AMD) and other related conditions, uveitic disorders and optic neuropathies has been described. Expand
Automated Measurement of the Foveal Avascular Zone in Swept-Source Optical Coherence Tomography Angiography Images
Automated determination of the FAZ area is feasible and yields results comparable to those obtained by manual measurement, and could potentially contribute to the understanding of the pathophysiology of various retinal diseases, particularly underlying vascular diseases. Expand
Anatomy-guided Multimodal Registration by Learning Segmentation without Ground Truth: Application to Intraprocedural CBCT/MR Liver Segmentation and Registration
The experimental results on in-house TACE patient data demonstrated that the APA2Seg-Net can generate robust CBCT and MR liver segmentation, and the anatomy-guided registration framework with these segmenters can provide high-quality multimodal registrations. Expand
Automated quantification of superficial retinal capillaries and large vessels for diabetic retinopathy on optical coherence tomographic angiography.
A fully automatic algorithm for the quantitative measurement of microcirculatory changes in sight-threatening diabetic retinopathy is presented, which shows that the diabetic group showed a significantly larger large vessel density, but a significantly smaller capillary density. Expand
Retinal vascular layers imaged by fluorescein angiography and optical coherence tomography angiography.
In none of the 12 eyes could the radial peripapillary capillary network be visualized completely around the nerve head by fluorescein angiography, whereas the network was readily visualized in the SSADA scans. Expand