AI u veterinarskoj oftalmologiji: segmentacija slika i veliki jezični modeli u dijagnostici očnih bolesti pasa
AI in Veterinary Ophthalmology: Image Segmentation and Large Language Models in the Diagnosis of Canine Eye Diseases

Summary/Abstract: This study presents the application of artificial intelligence methods in veterinary ophthalmology through the combination of image segmentation and language understanding models. A customized U-Net model was used for detecting and segmenting canine ocular symptoms, including ocular opacity, sclera redness, excessive tearing, and colored ocular protrusion. The obtained results were used as input for large language models (GPT-4o, Mistral 7B, Gemini2, Llama-3, and Claude 4) to interpret symptoms and provide preliminary diagnoses. The evaluation was performed using linguistic and semantic metrics (MPNet, MiniLM, BERTScore, CLIPScore, BLEU, METEOR, ROUGE, and SPICE). The results show that integrating U-Net segmentation with LLM analytical capabilities enables effective preliminary diagnosis of canine eye diseases. The ResNet34-based model achieved the highest accuracy in identifying sclera redness, while GPT-4o performed best in interpreting symptoms and suggesting diagnoses. This approach contributes to the development of intelligent systems that can improve the accuracy and efficiency of veterinary diagnostics.

• Details
• Contents