| Title (english) | DogEyeSeg4: Dog Eye Segmentation 4-Class Ophthalmic Disease Dataset |
| Author | Matija Burić Faculty of Informatics and Digital Technologies, University of Rijeka; Hrvatska Elektroprivreda d.d. |
| Author | Marina Ivašić-Kos Faculty of Informatics and Digital Technologies, University of Rijeka; Centre for Artificial Intelligence, University of Rijeka |
| Collaborator | Siniša Grozdanić (Other) Animal Eye Consultants of Iowa, North Liberty, Iowa, United States |
| Scientific / art field, discipline and subdiscipline | TECHNICAL SCIENCES Computing Data Processing |
| Abstract (english) | 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. |
| Keywords (english) | |
| Language | english |
| URN:NBN | urn:nbn:hr:195:405214 |
| Publication | 2024-08-22 |
| Geolocation | Croatia |
| Publisher | Fakultet informatike i digitalnih tehnologija Faculty of Informatics and Digital Technologies |
| Access conditions | Open access |
| Terms of use |  |
| Public note (english) | Experiment details are available in the "Diagnosis of ophthalmologic diseases in canines based on images using neural networks for image segmentation" paper |
| Created on | 2024-08-22 11:31:04 |
