National Repository of Grey Literature 3 records found  Search took 0.01 seconds. 
Detection of Diabetic Retinopathy using Deep Learning and Transfer Learning Techniques with Oversampling to Address Imbalanced Dataset
RANĐELOVIĆ, Teodora
The study aims to develop a system for detecting diabetic retinopathy using deep learning. In this study I have explored transfer learning with four distinct models and addressed the issue of an unbalanced dataset with oversampling. The final experiment achieved a significant improvement in accuracy and quadratic kappa score. The study highlights the potential of deep learning and the importance of addressing dataset imbalances for accurate results.
Research of vitreous and vitreoretinal interface in microvascular retinal disorders focussed on eye complications of diabetes mellitus
Křížová, Libuše ; Zima, Tomáš (advisor) ; Průša, Richard (referee) ; Sosna, Tomáš (referee)
In this work I present conclusions of clinical-laboratory research focused on the patients with diabetic macular edema (DME). We performed biochemical and immunochemical analyses of vitreous samples that were collected during the pars plana vitrectomy. Moreover, at patients with non-proliferative diabetic retinopathy (NPDR) we assessed morphological characteristics of DME using optical coherence tomography (OCT). According to our findings, the vitreous and serum concentrations of uric acid and glucose were significantly higher in patients with diabetic retinopathy and DME compared to controls. Also total ratio (serum/ vitreous concentration) of uric acid and glucose was in diabetics significantly higher than in controls. The most important determinant of increasing concentration of both uric acid and glucose in the vitreous was the grade of diabetic retinopathy. Moreover, we demonstrated significant correlation between vitreous concentration of uric acid and concentration of the vascular endothelial growth factor (VEGF) in patients with DME and NPDR. We found further, that the volume of the macula (cube volume - CV) computed with the software of Cirrus HD-OCT correlates in diabetics significantly with the vitreous VEGF concentration, but not with uric acid. This OCT parameter could be used to...
Research of vitreous and vitreoretinal interface in microvascular retinal disorders focussed on eye complications of diabetes mellitus
Křížová, Libuše ; Zima, Tomáš (advisor) ; Průša, Richard (referee) ; Sosna, Tomáš (referee)
In this work I present conclusions of clinical-laboratory research focused on the patients with diabetic macular edema (DME). We performed biochemical and immunochemical analyses of vitreous samples that were collected during the pars plana vitrectomy. Moreover, at patients with non-proliferative diabetic retinopathy (NPDR) we assessed morphological characteristics of DME using optical coherence tomography (OCT). According to our findings, the vitreous and serum concentrations of uric acid and glucose were significantly higher in patients with diabetic retinopathy and DME compared to controls. Also total ratio (serum/ vitreous concentration) of uric acid and glucose was in diabetics significantly higher than in controls. The most important determinant of increasing concentration of both uric acid and glucose in the vitreous was the grade of diabetic retinopathy. Moreover, we demonstrated significant correlation between vitreous concentration of uric acid and concentration of the vascular endothelial growth factor (VEGF) in patients with DME and NPDR. We found further, that the volume of the macula (cube volume - CV) computed with the software of Cirrus HD-OCT correlates in diabetics significantly with the vitreous VEGF concentration, but not with uric acid. This OCT parameter could be used to...

Interested in being notified about new results for this query?
Subscribe to the RSS feed.