Peer-reviewed veterinary case report
Deep learning to detect cataracts in dog eye ultrasounds
By Sanghyeon Park et al.·Published in Animals·2025·Helix Animal Medical Center, Seoul 06546, Republic of Korea, CH·View original on DOAJ →
PetCaseFinder translated the abstract of this peer-reviewed paper into plain English so pet owners can read it. We do not publish original research — every detail traces back to the citation above. How we work →
Original publication title: Deep Learning-Based Classification of Canine Cataracts from Ocular B-Mode Ultrasound Images
- Species:
- dog
Plain-English summary
A study found that deep learning technology can help veterinarians identify cataracts in dogs using ultrasound images of their eyes. Cataracts are a common cause of vision loss, and the technology was able to classify different types of cataracts with high accuracy. The best model achieved over 92% accuracy in identifying whether a dog had cataracts or not. This advancement could assist vets in making quicker and more accurate diagnoses, ultimately helping dogs receive the treatment they need for better vision.
People also search for: dog cataracts treatment · how to tell if my dog has cataracts · canine eye problems ultrasound
Abstract
Cataracts are a prevalent cause of vision loss in dogs, and timely diagnosis is essential for effective treatment. This study aimed to develop and evaluate deep learning models to automatically classify canine cataracts from ocular ultrasound images. A dataset of 3155 ultrasound images (comprising 1329 No cataract, 614 Cortical, 1033 Mature, and 179 Hypermature cases) was used to train and validate four widely used deep learning models (AlexNet, EfficientNetB3, ResNet50, and DenseNet161). Data augmentation and normalization techniques were applied to address category imbalance. DenseNet161 demonstrated the best performance, achieving a test accuracy of 92.03% and an F1-score of 0.8744. The confusion matrix revealed that the model attained the highest accuracy for the No cataract category (99.0%), followed by Cortical (90.3%) and Mature (86.5%) cataracts, while Hypermature cataracts were classified with lower accuracy (78.6%). Receiver Operating Characteristic (ROC) curve analysis confirmed strong discriminative ability, with an area under the curve (AUC) of 0.99. Visual interpretation using Gradient-weighted Class Activation Mapping indicated that the model effectively focused on clinically relevant regions. This deep learning-based classification framework shows significant potential for assisting veterinarians in diagnosing cataracts, thereby improving clinical decision-making in veterinary ophthalmology.
Find similar cases for your pet
PetCaseFinder finds other peer-reviewed reports of pets with the same symptoms, plus a plain-English summary of what was tried across them.
Search related cases →Original publication on DOAJ: https://doi.org/10.3390/ani15091327