Auto-Detection of Tibial Plateau Angle in Canine Radiographs Using a Deep Learning Approach

TL;DR

This paper presents a deep learning method using YOLO to automatically detect and measure the Tibial Plateau Angle in canine radiographs, aiding quicker diagnosis of joint issues.

Contribution

It introduces a novel application of YOLO-based object detection for TPA measurement in veterinary radiology, achieving high accuracy in identifying the angle.

Findings

Successfully predicts TPA within normal range for 80% of images

Demonstrates feasibility of deep learning for veterinary diagnostic measurements

Provides a foundation for automated diagnosis in veterinary practice

Abstract

Stifle joint issues are a major cause of lameness in dogs and it can be a significant marker for various forms of diseases or injuries. A known Tibial Plateau Angle (TPA) helps in the reduction of the diagnosis time of the cause. With the state of the art object detection algorithm YOLO, and its variants, this paper delves into identifying joints, their centroids and other regions of interest to draw multiple line axes and finally calculating the TPA. The methods investigated predicts successfully the TPA within the normal range for 80 percent of the images.