ScholarDeck

Animal / preclinicalScientific reports · 2026

A deep learning-based framework for fundus image classification of inherited retinal degeneration in dogs.

David A Smith, Valerie L Dufour, Hippolyte G J Beltran-Grémaud … William A Beltran

Read paper

OphthalmologyAnimal / preclinical

Deep learning model detected inherited retinal degeneration in dogs from fundus photos accurately.

A deep learning-based framework for fundus image classification of inherited retinal degeneration in dogs.

David A Smith … William A Beltran

Scientific reports · 2026

Background

Inherited retinal degenerations (inherited retinal degenerations) are a frequent cause of vision impairment in numerous breeds of dogs.

Methods

In this study, we evaluated three deep learning architectures using fundus images to detect degenerative retinal disease in dogs.

Results

correctly identified affected vs healthy dogs 87.5% of the time

Accuracy

87.5%

Sensitivity

87.5%

Specificity

87.5%

More results

An EfficientNetV2-based convolutional neural network with a custom classification head was selected for final evaluation.

Dog-level calibration analysis yielded a Brier score of 0.093.

More results

Under constrained single-image evaluation conditions, the model showed higher dog-level classification performance than the majority-vote classification of three experienced veterinary ophthalmologists, primarily by reducing false-positive classification of normal dogs as affected.

“

Conclusion

These results support the potential of deep learning as an objective decision-support tool for canine fundus image interpretation, although broader multi-center and prospective validation is needed before clinical deployment.

Post

A deep learning-based framework for fundus image classification of inherited retinal degeneration in dogs.

Deep learning model detected inherited retinal degeneration in dogs from fundus photos accurately.

Related papers