CVD vs. NonCVD Retinal Images of Cattle

This dataset contains a collection of RGB retinal images captured using the Optomed Smartscope digital fundus camera. The dataset consists of a total of 1,118 images taken from the right and left eyes of 100 cattle, with a resolution of 1536×1152 pixels in JPG format. The dataset is designed to aid in the development of AI-driven models for the diagnosis of cardiovascular diseases (CVD) in cattle based on retinal imaging.

Dataset Details:

• Total Images: 1,118 retinal images
• Resolution: 1536×1152 pixels (JPG format)
• Cattle Included: 100 cattle (52 diagnosed with CVD, 48 non-CVD)
• CVD Labeling:
  • 0: Non-CVD (527 images)
  • 1: CVD (591 images)

This dataset includes both cardiovascular disease (CVD) and non-CVD retinal images, which can be used for training machine learning and deep learning models for disease classification.

Key Features:

• AI-Aided Disease Diagnosis
• Retinal Image Classification
• CVD Detection in Cattle
• Suitable for Machine Learning & Deep Learning Models
• High-Resolution Fundus Images
• Use for Biometric and Agricultural Research

Research Paper:

To cite this dataset, please reference the following publication:
Pınar Cihan, Ahmet Saygılı, Celal Şahin Ermutlu, Uğur Aydın, Özgür Aksoy, “AI-aided cardiovascular disease diagnosis in cattle from retinal images: Machine learning vs. deep learning models,” Computers and Electronics in Agriculture, 226 (2024):109391