Thesis Details
Detekce projevů onemocnění na sítnici lidského oka
The most common cause of blindness in humans, between 20 and 64 years, is diabetic retinopathy. This disease is due to unclear reasons, but the cause is clear. Diabetes mellitus. The prognosis of the number of sick people in the future is very bad. For this reason, early diagnosis of diabetic retinopathy is highly needed, as untreated patients may lose sight very quickly. Therefore, the aim of this work is to design and implement an algorithm, that can automatically search for certain symptoms of the disease. The algorithm works on a way of adaptive Gaussian thresholding. A very important part of the algorithm is also pre-processing and subsequent classification of suspicious areas. The detection success was evaluated on 70 images from various databases, where the algorithm achieves very good results. Deploying this algorithm in diagnostics could greatly help to automate the whole process. Ultimately, this would mean earlier treatment for patients where the start time of treatment is critical.
Eye, retina, diabetic retinopathy, image processing, openCV, python
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
@bachelorsthesis{FITBT22993, author = "Gabriel Ko\v{s}tialik", type = "Bachelor's thesis", title = "Detekce projev\r{u} onemocn\v{e}n\'{i} na s\'{i}tnici lidsk\'{e}ho oka", school = "Brno University of Technology, Faculty of Information Technology", year = 2020, location = "Brno, CZ", language = "slovak", url = "https://www.fit.vut.cz/study/thesis/22993/" }