Burić, M. i Ivašić Kos, M. (2024). DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset [Skup podataka]. https://urn.nsk.hr/urn:nbn:hr:195:405214.
Burić, Matija i Marina Ivašić Kos. DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset. Fakultet informatike i digitalnih tehnologija, 2024. 25.12.2024. https://urn.nsk.hr/urn:nbn:hr:195:405214.
Burić, Matija, i Marina Ivašić Kos. 2024. DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset. Fakultet informatike i digitalnih tehnologija. https://urn.nsk.hr/urn:nbn:hr:195:405214.
Burić, M. i Ivašić Kos, M. 2024. DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset. Fakultet informatike i digitalnih tehnologija. [Online]. [Citirano 25.12.2024.]. Preuzeto s: https://urn.nsk.hr/urn:nbn:hr:195:405214.
Burić M, Ivašić Kos M. DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset. [Internet]. Fakultet informatike i digitalnih tehnologija: , HR; 2024, [pristupljeno 25.12.2024.] Dostupno na: https://urn.nsk.hr/urn:nbn:hr:195:405214.
M. Burić i M. Ivašić Kos, DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset, Fakultet informatike i digitalnih tehnologija, 2024. Citirano: 25.12.2024. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:195:405214.
Naslov (engleski)
DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset
Autor
Matija Burić Faculty of Informatics and Digital Technologies, University of Rijeka; Hrvatska Elektroprivreda d.d.
Autor
Marina Ivašić-Kos Faculty of Informatics and Digital Technologies, University of Rijeka; Centre for Artificial Intelligence, University of Rijeka
Suradnik
Siniša Grozdanić (Other) Animal Eye Consultants of Iowa, North Liberty, Iowa, United States
Znanstveno / umjetničko područje, polje i grana
TEHNIČKE ZNANOSTI Računarstvo Obradba informacija
Sažetak (engleski)
A dataset is used for training and evaluating a U-Net-based system designed to accurately segment dog eye images for the identification of four specific disease symptoms. The dataset is intended to assist veterinary professionals in the early diagnosis of ophthalmic conditions. The images were collected from two specialized veterinary clinics and a veterinary ophthalmologic atlas, with all images reviewed and verified by a veterinary specialist. These images were gathered as part of standard clinical evaluations, with strict anonymization protocols ensuring that no examination dates, client information, or animal identifiers are included. This dataset supports the development of automated segmentation tools that enhance the accuracy and efficiency of disease detection in canine ophthalmology, ultimately contributing to better clinical outcomes in veterinary practice.
Fakultet informatike i digitalnih tehnologija Faculty of Informatics and Digital Technologies
Prava pristupa
Otvoreni pristup
Uvjeti korištenja
Javna napomena (engleski)
Experiment details are available in the "Diagnosis of ophthalmologic diseases in canines based on images using neural networks for image segmentation" paper