Age-related macular degeneration (AMD) is a common ophthalmic disease, mainly occurring in the elderly. After the occurrence of pigment epithelial detachment (PED), neuroepithelial detachment and subretinal fluid (SRF) are further caused, and patients need follow-up treatment. Quantitative analysis of these two symptoms is very important for clinical diagnosis. Therefore, we propose a new joint segmentation network to accurately segment PED and SRF in this paper. Our main contributions are: (1) a new multi-scale information selection module is proposed. (2) based on the U-shape network, a novel decoder branch is proposed to obtain boundary information, which is critical to segmentation. The experimental results show that our method achieves 72.97% for the average dice (DSC), 79.92% for the average recall, and 67.11% for the average intersection over union (IOU).
Optical coherence tomography (OCT) is now a popular high resolution optical imaging technology capable of providing three-dimension images of internal microstructures within biological tissues. To date, the most successful application of OCT has been in ophthalmology, where the technology has become an indispensable diagnostic tool. It has proven able to image the structural changes due to various eye diseases. Besides, those structural changes may also be associated with certain physiological conditions, for instance, vessel density changes resulting from intraocular pressure change. Intraocular pressure (IOP) can also serve as an important physiological marker for the diagnosis of ophthalmic diseases. Therefore, in this study, we aim to develop ophthalmic OCT combined with a novel flexible pressure sensor for retina imaging and intraocular pressure measurement. A swept source OCT (SS-OCT) system is designed, and its axial resolution is about 5 μm. The OCT system is specially designed to allow for both anterior and posterior eye segment imaging. The anterior eye segment imaging is dedicated to measure the contact area between the pressure sensor and the cornea, which is needed by the pressure sensor to calculate the intraocular pressure. This system will be a versatile ophthalmic imaging platform: (1) conventional anterior and posterior eye imaging; (2) intraocular pressure measurement. Further, it will serve as a useful tool aiding in eye disease diagnostics in clinics.
Intraocular pressure (IOP) is the pressure exerted by the eye contents on the eyeball wall and is used to maintain the shape of the eyeball. It may cause glaucoma when the dynamic balance of the generation and excretion of aqueous humor in the eyeball is broken. The Goldmann applanation tonometer (GAT) based on the Imbert-Fick principle is considered to be the reference standard for glaucoma diagnosis in clinics. OCT is widely used for eye screening by imaging structural changes caused by various eye diseases. In this paper, we have developed an OCT-assisted transparent flexible force sensing system (O-FPSS) for IOP measurements. In general, the hybrid O-FPSS consists of a droplet-based flexible transparent force sensor placed over an optical coherence tomography imaging lens, in which the IOP measured once the apex of the cornea is flatted by the sensor. According to the Imbert-Fick law, when cornea is flattened, the pressure applied by the sensor equals to the IOP. Specially, the droplet-based capacitive flexible force sensor is consisted by two flexible conductive membranes, and an ionic is sandwiched in between, in which the force applied on the cornea can be monitored by the output. The sensing membrane deforms uniformly upon contacting the cornea, leading to the expansion of the droplet and an increase of the overall capacitance. On the other hand, to get the flatten area between the sensor and the cornea, a swept-source OCT (SS-OCT) is used to record the interfacial with a resolution of 5μm.
Intraocular pressure (IOP) is considered as a critical sign for glaucoma diagnosis. Tonometry, such as Goldmann applanation tonometry, Tono-Pen and noncontact tonometry, are widely used in clinical practices for IOP evaluations. However, limitations of the tonometry, such as high cost, operating complexity, and lack of feasibility are major concerns in a busy clinic. In this paper, we propose a facile method for IOP monitoring by utilizing a simple constructed force/displacement-hybrid sensor. The device is constructed by a capacitive force sensor mounted on handheld linear stage, which is able to record the force and travel distance simultaneously. A numerical study based on the finite element method (FEM) is used to evaluate the performance of the sensor for the IOP detections. In particular, a numerical corneal-sensor model is built by the FEM, in which the sensor is placed on the apex of the corneal structure. As the sensor presses against the cornea, the physical parameters, such as the contact pressure, the contact area between the sensor and the cornea, the travel displacement of the sensor are recorded. Importantly, to improve the modeling accuracy, we use a dynamic Young’s modulus in the cornea model, considering the multi-layered structure of the human cornea whose Young’s modulus varies as the IOP changes. Our sensor exhibits a highly linear relationship between the contact pressure and the travel displacement in the progress of cornea applanation, from which the IOP can be simply derived. A minimal pressure of 1mmHg can be sensitively detected by our sensor, which is highly desired in clinical trials.
The recent introduction of next generation spectral optical coherence tomography (OCT) has become increasingly important in the detection and investigation of retinal related diseases. However, unstable eye position of patient makes tracking disease progression over short period difficult. This paper proposed a method to remove the eye position difference for longitudinal retinal OCT data. In the proposed method, pre-processing is first applied to get the projection image. Then, a vessel enhancement filter is applied to detect vessel shadows. Third, SURF algorithm is used to extract the feature points and RANSAC algorithm is used to remove outliers. Finally, transform parameter is estimated and the longitudinal OCT data are registered. Simulation results show that our proposed method is accurate.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.