| Title |
Investigation of eye fundus blood vessel segmentation using autoencoders |
| Translation of Title |
Autoenkoderių taikymas akies dugno kraujagyslėms atpažinti. |
| Authors |
Shirvinskii, Aleksandr |
| Full Text |
|
| Pages |
47 |
| Keywords [eng] |
Eye Fundus Blood Vessels, Segmentation, Autoencoders, Unet |
| Abstract [eng] |
Progress of compact high definition digital retinal cameras allowed us to reveal structural and functional information about the human retina in a harmless and non-invasive way. Eye diseases cause noticeable pathological changes, so segmentation of vessels in fundus images is of great importance. In this research work I developed a new retinal vessel segmentation method that achieves state-of-the-art performance in several metrics and with threshold optimization the model showed comparable results to well researched methods on cross datasets experiments on the segmentation task. |
| Dissertation Institution |
Vilniaus universitetas. |
| Type |
Master thesis |
| Language |
English |
| Publication date |
2022 |
