Yan Liu

Deep learning-enabled volumetric cone photoreceptor segmentation in adaptive optics optical coherence tomography images of normal and diseased eyes

, , , , , , ,

Deep learning-enabled volumetric cone photoreceptor segmentation in adaptive optics optical coherence tomography images of normal and diseased eyes Objective quantification of photoreceptor cell morphology, such as cell diameter and outer segment length, is crucial for early, accurate, and sensitive diagnosis and prognosis of retinal neurodegenerative diseases. Adaptive optics optical coherence tomography (AO-OCT) provides three-dimensional (3-D) visualization of photoreceptor cells in the living human eye. The current gold standard for extracting cell morphology from AO-OCT images involves the tedious process of 2-D manual marking. To automate this process and extend to 3-D analysis of the volumetric data, we propose a comprehensive deep learning framework to segment individual cone cells in AO-OCT scans. Our automated method achieved human-level performance in assessing cone photoreceptors of healthy and diseased participants captured with three different AO-OCT systems representing two different types of point scanning OCT: spectral domain and swept source.

Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images

, , , , , , ,

Due to its noninvasive character, optical coherence tomography (OCT) has become a popular diagnostic method in clinical settings. However, the low-coherence interferometric imaging procedure is inevitably contaminated by heavy speckle noise, which impairs both visual quality and diagnosis of various ocular diseases. Although deep learning has been applied for image denoising and achieved promising results, the lack of well-registered clean and noisy image pairs makes it impractical for supervised learning-based approaches to achieve satisfactory OCT image denoising results. In this paper, we propose an unsupervised OCT image speckle reduction algorithm that does not rely on well-registered image pairs. Specifically, by employing the ideas of disentangled representation and generative adversarial network, the proposed method first disentangles the noisy image into content and noise spaces by corresponding encoders. Then, the generator is used to predict the denoised OCT image with th...

Relationships of Rheumatoid Factor with Thickness of Retina and Choroid in Subjects without Ocular Symptoms Using Swept-Source Optical Coherence Tomography

, , , , , , , , , ,

Purpose . Researches have confirmed that the retinal and choroidal thickness in patients with autoimmune disease-associated uveitis displays significant changes. However, the relationships between rheumatoid factor (RF) and thickness of the retina and choroid in individuals without ocular manifestations remain unclear. The aim of this study is to assess the associations of RF with retinal and choroidal thickness. Methods . The individuals enrolled in the cross-sectional research received full ocular examinations. The participants were classified as the RF (+) group ( IU/ml) and the RF (−) group ( IU/ml) according to the serum RF titers. The thickness of the retina and choroid was measured by swept-source optical coherence tomography (SS-OCT). Results . The study covered 65 right eyes of 65 individuals that are RF-positive and 130 right eyes of 130 age- and sex-matched individuals that are RF-negative. The RF (+) group showed decreased choroidal thickness that ach...

Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images

, , , , , , ,

Due to its noninvasive character, optical coherence tomography (OCT) has become a popular diagnostic method in clinical settings. However, the low coherence interferometric imaging procedure is inevitably contaminated by heavy speckle noise, which impairs both visual quality and diagnosis of various ocular diseases. Although deep learning has been applied for image denoising and achieved promising results, the lack of well-registered clean and noisy image pairs makes it impractical for supervised learning-based approaches to achieve satisfactory OCT image denoising results. In this paper, we propose an unsupervised OCT image speckle reduction algorithm that does not rely on well-registered image pairs. Specifically, by employing the ideas of disentangled representation and generative adversarial network, the proposed method first disentangles the noisy image into content and noise spaces by corresponding encoders. Then, the generator is used to predict the denoised OCT image with th...

Comparison of choroidal thickness in high myopic eyes after FS-LASIK versus implantable collamer lens implantation with swept-source optical coherence tomography

, , ,

AIM : To investigate the changes in choroidal thickness (CT) in high myopic eyes after femtosecond laser-assisted in situ keratomileusis (FS-LASIK) surgery or central hole implantable collamer lens (ICL V4c) implantation using swept-source optical coherence tomography (SS-OCT). METHODS : We examined the right eyes of 116 patients with high myopia who were candidates for FS-LASIK surgery and ICL implantation. Sixty eyes underwent ICL V4c implantation and 56 eyes were subjected to FS-LASIK surgery. The CT was measured with SS-OCT. All data were recorded preoperatively and 2h, 1wk, 1 and 3mo postoperatively. Other demographic information was collected, including age, sex, uncorrected visual acuity (UCVA), best corrected visual acuity (BCVA), spherical equivalent (SE), intraocular pressure (IOP) and axial length (AL). RESULTS : The UCVA improved in both groups and showed no significant differences between groups. There also were no significant differences between the two groups in posto...

Quantitative evaluation of scattering in optical coherence tomography skin images using the extended Huygens–Fresnel theorem

, , , , , ,

An optical properties extraction algorithm is developed based on enhanced Huygens–Fresnel light propagation theorem, to extract the scattering coefficient of a specific region in an optical coherence tomography (OCT) image. The aim is to quantitatively analyze the OCT images. The algorithm is evaluated using a set of phantoms with different concentrations of scatterers, designed based on Mie theory. The algorithm is then used to analyze basal cell carcinoma and healthy eyelid tissues, demonstrating distinguishable differences in the scattering coefficient between these tissues. In this study, we have taken advantage of the simplification introduced by the utilization of a dynamic focus OCT system. This eliminates the need to deconvolve the reflectivity profile with the confocal gate profile, as the sensitivity of the OCT system is constant throughout the axial range ( Read Full Article )

Categories

Organizations in the News

OCT Companies in the News

Picture Gallery