|
|
Semantic Segmentation of Pathologies in Retinal Images
Čabala, Roman ; Orság, Filip (referee) ; Kavetskyi, Andrii (advisor)
The thesis aimed to segment pathology visible in the retina images, such as exudates, hemorrhages, and microaneurysms. For that, two well known deep neural networks, named U-Net and SegFormer, were trained. To test the performance of the models, one publicly available dataset was used, named IDRiD. Obtained results were reported after analyzing different factors which affected the performance of the models U-Net and Segformer.
|
|
|
Detection and Recognition of ARMD Disease Impacts to the Human Eye Retina
Stančíková, Ivana ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
This thesis aims to create a software able to detect symptoms of age-related macular degeneration in images of human eye retina. This condition is considered one of the leading causes of vision loss in older adults. Lesions of the macular area called drusen are the first and also the most distinctive sign of developing ARMD. The approach presented in this thesis utilizes methods of image processing and computer vision to recognize retinal structures, in particular the optical disk and blood vessels, and distinguish between these structures and actual symptoms of the disease. The evaluation of the program's success rate was performed on 692 images originating from four databases. The resulting solution has the potential to assist medical professionals with earlier diagnosis of the disease and thus contribute to prevention of severe vision loss.
|
|
|
Semantic Segmentation of Pathologies in Retinal Images
Čabala, Roman ; Orság, Filip (referee) ; Kavetskyi, Andrii (advisor)
The thesis aimed to segment pathology visible in the retina images, such as exudates, hemorrhages, and microaneurysms. For that, two well known deep neural networks, named U-Net and SegFormer, were trained. To test the performance of the models, one publicly available dataset was used, named IDRiD. Obtained results were reported after analyzing different factors which affected the performance of the models U-Net and Segformer.
|
|
|
Detection and Recognition of ARMD Disease Impacts to the Human Eye Retina
Stančíková, Ivana ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
This thesis aims to create a software able to detect symptoms of age-related macular degeneration in images of human eye retina. This condition is considered one of the leading causes of vision loss in older adults. Lesions of the macular area called drusen are the first and also the most distinctive sign of developing ARMD. The approach presented in this thesis utilizes methods of image processing and computer vision to recognize retinal structures, in particular the optical disk and blood vessels, and distinguish between these structures and actual symptoms of the disease. The evaluation of the program's success rate was performed on 692 images originating from four databases. The resulting solution has the potential to assist medical professionals with earlier diagnosis of the disease and thus contribute to prevention of severe vision loss.
|
guest ::
