• Current Optics and Photonics
• /
• v.8 no.2
• /
• pp.183-191
• /
• 2024

High-resolution retinal imaging based on adaptive optics (AO) is important for early diagnosis related to retinal diseases. However, in practical applications, closed-loop AO correction takes a relatively long time, and traditional open-loop correction methods have low accuracy in correction, leading to unsatisfactory imaging results. In this paper, a SH-U-net-based open-loop AO wavefront correction method is presented for a retinal AO imaging system. The SH-U-net builds a mathematical model of the entire AO system through data training, and the Root mean square (RMS) of the distorted wavefront is 0.08λ after correction in the simulation. Furthermore, it has been validated in experiments. The method improves the accuracy of wavefront correction and shortens the correction time.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.321-325
• /
• 2004

Retinopathy of Prematurity (ROP) is a common retinal neovascular disorder of premature infants. It can be characterized by inappropriate and disorganized vessel. This paper present a method for blood vessel detection on infant retinal images. The algorithm is designed to detect the retinal vessels. The proposed method applies a Lapalacian of Gaussian as a step-edge detector based on the second-order directional derivative to identify locations of the edge of vessels with zero crossings. The procedure allows parameters computation in a fixed number of operations independent of kernel size. This method is composed of four steps : grayscale conversion, edge detection based on LOG, noise removal by adaptive Wiener filter & median filter, and Otsu's global thresholding. The algorithm has been tested on twenty infant retinal images. In cooperation with the Digital Imaging Research Centre, Kingston University, London and Department of Opthalmology, Imperial College London who supplied all the images used in this project. The algorithm has done well to detect small thin vessels, which are of interest in clinical practice.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.614-616
• /
• 2021

The world faces difficulties in terms of eye care, including treatment, quality of prevention, vision rehabilitation services, and scarcity of trained eye care experts. However, it is difficult to develop a method for classifying various ocular diseases because the existing dataset for retinal image disclosure does not consist of various diseases found in clinical practice. We propose a method for classifying ocular diseases using the Retinal Fundus Multi-disease Image Dataset (RFMiD), a dataset published in the ISBI-2021 challenge. Our goal is to develop a robust and generalizable model for screening retinal images into normal and abnormal categories. The performance of the proposed model shows a value of 0.9782 for the test dataset as an area under the curve (AUC) score.

• Journal of the Optical Society of Korea
• /
• v.18 no.2
• /
• pp.151-155
• /
• 2014

Although various ophthalmic imaging methods, including fundus photography and optical coherence tomography, have been applied for effective diagnosis of ocular diseases with high spatial resolution, most of them are limited by shallow imaging penetration depth and a narrow field of view. Also, many of those imaging modalities are optimized to provide microscopic anatomical information, while functional or cellular information is lacking. Compared to other ocular imaging modalities, photoacoustic imaging can achieve relatively deep penetration depth and provide more detailed functional and cellular data based on photoacoustic signal generation from endogenous contrast agents such as hemoglobin and melanin. In this paper, array-based ultrasound and photoacoustic imaging was demonstrated to visualize pigmentation in the eye as well as overall ocular structure. Fresh porcine eyes were visualized using a real-time ultrasound micro-imaging system and an imaging probe supporting laser pulse delivery. In addition, limited photoacoustic imaging field of view was improved by an imaging probe tilting method, enabling visualization of most regions of the retina covered in the ultrasound imaging.

• Journal of The Korean Ophthalmological Society
• /
• v.59 no.12
• /
• pp.1160-1165
• /
• 2018

Purpose: To evaluate the availability of ultra-wide field fundus photography based on eye steering technique to diagnose retinal breaks in patients with symptomatic posterior vitreous detachment (PVD). Methods: The medical records of patients with symptomatic PVD were reviewed. Retinal breaks were independently identified using four eye steering capture images of ultra-wide field fundus photographs. The sensitivity and specificity of eye steering capture imaging for diagnosing retinal breaks were calculated. Results: A total of 94 eyes of 94 patients were included. Using fundus examination after pupil dilatation, retinal breaks were diagnosed in 42 (45%) eyes. The sensitivity of the eye steering capture imaging was 98% (95% confidence interval [CI]: 88-100%), and the specificity was 98% (95% CI: 90-100%). Of the 58 retinal tears, 28 (97%) involving the superior quadrant, 10 (100%) involving the inferior quadrant, 6 (100%) involving the nasal quadrant, and 13 (100%) involving the temporal quadrant were identified using eye steering capture images. Conclusions: Ultra-wide field fundus photography based on eye steering technique was useful for diagnosing retinal breaks in patients with symptomatic PVD. However, eye steering photography could not adequately replace the fundus examination after pupil dilatation in all cases.

• Proceedings of the Optical Society of Korea Conference
• /
• 2007.02a
• /
• pp.44-45
• /
• 2007

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.1
• /
• pp.88-96
• /
• 2012

According to development of technology for media, observers try to watch the realities from images, as follows, 3D imaging has been extremely developed. 3D image gives depth in the image, observers feel in nature. Different image perception from left and right eyes make the 3D image. Anaglyph which is one of the ways to make an image of three dimensions is for obtaining an image of three dimensions by using color filter glasses. Anaglyph has a little amount of calculation and is easy to make, and it has a good point that anaglyph can be used in more wide field because it can create an image of three dimensions to the output of print like printed matter. However, the phenomenon of retinal rivalry can cause a feeling of fatigue because a difference of brightness of the left image and the right image happen. The way to reduce this problem is made by cutting down a difference of brightness. In the result, retinal rivalry can be reduced. We reduced a difference of the brightness of the left and the right image by utilizing the brightness and average of the original image to reduce retinal rivalry and we made better colors of anaglyph by using the way that we keep the hue caused by a change of brightness and supplement saturation about color distortion which is created at that time.

• Journal of the Optical Society of Korea
• /
• v.15 no.3
• /
• pp.293-299
• /
• 2011

In this study, we demonstrated Fourier-domain/swept-source optical coherence tomography (FD/SS-OCT) at a center wavelength of 800 nm for in vivo human retinal imaging. A wavelength-swept source was constructed with a semiconductor optical amplifier, a fiber Fabry-Perot tunable filter, isolators, and a fiber coupler in a ring cavity. Our swept source produced a laser output with a tuning range of 42 nm (779 to 821 nm) and an average power of 3.9 mW. The wavelength-swept speed in this configuration with bidirectionality is 2,000 axial scans per second. In addition, we suggested a modified zero-crossing method to achieve equal sample spacing in the wavenumber (k) domain and to increase the image depth range. FD/SS-OCT has a sensitivity of ~89.7 dB and an axial resolution of 10.4 ${\mu}m$ in air. When a retinal image with 2,000 A-lines/frame is obtained, an acquisition speed of 2.0 fps is achieved.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.541-543
• /
• 2022

In recent years, retinal disorders have become a serious health concern. Retinal disorders develop slowly and without obvious signs. To avoid vision deterioration, early detection and treatment are critical. Optical coherence tomography (OCT) is a non-invasive and non-contact medical imaging technique used to acquire informative and high-resolution image of retinal area and underlying layers. Disease signs are difficult to detect because OCT images have many areas which are not related to any disease. In this paper, we present a deep learning-based method to perform multi-label classification on a long-tailed OCT dataset. Our method first extracts the region of interest and then performs the classification task. We achieve 98% accuracy, 92% sensitivity, and 99% specificity on our private OCT dataset. Using the heatmap generated from trained convolutional neural network, our method is more robust and explainable than previous approaches because it focuses on areas that contain disease signs.

• Current Optics and Photonics
• /
• v.6 no.2
• /
• pp.151-160
• /
• 2022

Fundus images can reflect ocular diseases and systemic diseases such as glaucoma, diabetes mellitus, and hypertension. Thus, research on fundus-detection equipment is of great importance. The fundus camera has been widely used as a kind of noninvasive detection equipment. Most existing devices can only obtain two-dimensional (2D) retinal-image information, yet the fundus of the human eye also has spectral characteristics. The fundus has many pigments, and their different distributions in the eye lead to dissimilar tissue penetration for light waves, which can reflect the corresponding fundus structure. To obtain more abundant information and improve the detection level of equipment, a snapshot nonmydriatic fundus imaging spectral system, including fundus-imaging spectrometer and illumination system, is studied in this paper. The system uses a microlens array to realize snapshot technology; information can be obtained from only a single exposure. The system does not need to dilate the pupil. Hence, the operation is simple, which reduces its influence on the detected object. The system works in the visible and near-infrared bands (550-800 nm), with a volume less than 400 mm × 120 mm × 75 mm and a spectral resolution better than 6 nm.