Deep Learning Can be Used to Classify the Disease Status of the Canine Middle Ear From Computed Tomographic Images

TL;DR

This study shows that deep learning can accurately classify canine middle ear disease from CT scans, achieving over 80% accuracy with a relatively small dataset.

Contribution

The novel contribution is applying deep learning with transfer learning and data augmentation to diagnose canine middle ear disease using CT images.

Findings

A deep learning model achieved 84.7% accuracy in classifying canine middle ear disease from CT images.

Transfer learning and data augmentation improved performance with a limited dataset of 535 images.

The model can distinguish between normal and diseased middle ears in dogs with over 80% accuracy.

Abstract

Middle ear disease occurs frequently in dogs. CT has proven to be an excellent diagnostic tool for detecting middle ear structures, helping to achieve rapid and accurate diagnoses. Deep learning techniques are now widely used in CT scan‐based human medical image analysis, providing decision support and diagnostics. However, such techniques are currently underutilized in veterinary radiology. The focus of this study was to develop a deep learning model capable of diagnosing middle ear disease in dogs using CT images. To achieve this with a relatively small dataset, transfer learning and data augmentation techniques were applied. During the experimental phase of the study, we tested 10 binary classification models based on the ResNet architecture, combined with data augmentation and transfer learning, on a dataset consisting of a total of 535 canine CT images. We achieved a classification accuracy of up to 84.7%. The developed classifier, trained on relatively few CT images, can detect normal middle ears and middle ear disease in dogs with over 80% accuracy.

Figures