A5085001536- Retinal Imaging and Analysis
- Glaucoma and retinal disorders
- Retinal Diseases and Treatments
- Gaze Tracking and Assistive Technology
- Medical Image Segmentation Techniques
- Image and Object Detection Techniques
- Digital Imaging for Blood Diseases
- Optical Coherence Tomography Applications
Thammasat University
2017-2024
Chiba University
2021-2022
Understanding the changes in choroidal thickness and vasculature is important to monitor development progression of various ophthalmic diseases. Accurate segmentation choroid layer vessels critical better analyze understand changes. In this study, we develop a dense dilated U-Net model (ChoroidNET) for segmenting optical coherence tomography (OCT) images. The performance ChoroidNET evaluated using an OCT dataset that contains images with retinal pathologies. Overall Dice coefficient 95.1 ±...
Diabetic retinopathy’s signs, such as exudates (EXs) and aneurysms (ANs), initially develop from under the retinal surface detectable optical coherence tomography (OCT) images. Detecting these signs helps ophthalmologists diagnose DR sooner. segmenting (ANs) in medical images is challenging due to their small size, similarity other hyperreflective regions, noise presence, low background contrast. Furthermore, scarcity of public OCT featuring abnormalities has limited number studies related...
Accurate localization and segmentation of an optic disk (OD) is important problem in the analysis abnormality conditions such as shrinking/swelling, pale glucoma. Hence, this paper proposes automated fast accurate OD technique. In work, performed using extended feature projection method (EFP) based on retinal vessel orientation average intensity variance. Multiple candidate locations, obtained from technique (EFP), are used initialization points active contour model to detect boundaries....
The advanced development of mobile phone and lens technology has made retinal imaging more convenient than ever before. In the digital health era, fundus photography evolved into a low-cost alternative to standard ophthalmoscope. Existing image processing algorithms have problem with handling narrow field view poor quality images from phone. This paper enhances accuracy our previously proposed scheme, ADI-GVF snakes, improve segmentation optic disk (OD) cup (OC) for glaucoma pre-screening...
Optic disc edema (ODE) is an essential ocular manifestation in neuro-ophthalmic diseases. The presence of ODE recommended to detect at early stage avoid blindness and visual impairment. area was suggested as a reliable index evaluate the severity ODE. Retinal images with have different textures from typical optic (OD) abnormal characteristics such dimmer color than usual, blurring enlargement OD, obscuring veins. These unique make existing OD segmentation methods fail work. This work...