Medical artificial intelligence (AI) solution development company VUNO Inc. announced that it ranked first in the Retinal Fundus Glaucoma Challenge Edition (REFUGE2).
REFUGE2 was organized in conjunction with the 8th workshop of MICCAI(the Medical Image Computing and Computer Assisted Intervention Society) – one of the world's most prestigious associations for medical image processing – for three months from July 2020. A total of 134 teams across all over the world joined the REFUGE2 to claim the title of owning the best-performing deep learning algorithm to automatically detect glaucoma based on fundus image data.
VUNO proudly became the final winner of the REFUGE2 this year by outperforming all other competitors in its three research challenges: Classification of Clinical Glaucoma; Segmentation of Optic Disc and Cup; and Localization of Fovea (macular center). VUNO proved its world-class level of technological prowess in AI-based glaucoma detection, one of the most fiercely competitive fields where world-famous businesses scramble to make their technology available on the market.
The winning of the REFUGE2 is only the latest in a long line of the remarkable achievements that VUNO has so far made in various international competitions. VUNO boasted its outstanding technological competence in the Automatic Detection Challenge on Age-related Macular degeneration (ADAM) and the DeepDR Diabetic Retinopathy Image Dataset (DeepDRiD), two of which were part of the International Symposium on Biomedical Imaging (ISBI) 2020. Back in 2018, the South Korean AI-based solution developer also garnered the honor of topping the Diabetic Retinopathy – Segmentation and Grading Challenge in the ISBI 2018 and the REFUGE in the MICCAI 2018.
"It is my great pleasure to see that VUNO earned praise for its outstanding technological excellence in AI-based fundus image analysis and glaucoma detection in this year's REFUGE,” said Jaemin Son, leader of eye imaging research team of VUNO. "I seek to make a continued effort to lead research and development so that not only the domestic market but also the rest of the globe can highly acclaim VUNO Med®-Fundus AI™, the innovator's fundus screening solution which perfectly embodies its technological expertise,” he added.
VUNO Med®-Fundus AI™, VUNO’s AI based screening solution for the fundus, analyzes retinal fundus images to validate and detect more than 12 lesions and provides diagnosis within one second. The 12 findings detected by the device: ▲hemorrhage, ▲hard exudate, ▲cotton wool patch, ▲drusen, ▲membrane, ▲macular hole, ▲myelinated nerve fiber, ▲chorioretinal atrophy or scar, ▲vascular abnormality, ▲retinal nerve fiber layer defect, ▲glaucomatous disc change, and ▲non-glaucomatous disc change, encompass all findings that are essential in diagnosing all retinal diseases including diabetic retinopathy, macular degeneration, and glaucoma.