YOLOv9 for Fracture Detection in Pediatric Wrist Trauma X-ray Images

TL;DR

This paper applies the YOLOv9 object detection model to pediatric wrist fracture detection in X-ray images, demonstrating improved accuracy over previous models and providing a publicly available implementation.

Contribution

First application of YOLOv9 for fracture detection in pediatric wrist X-rays, with data augmentation enhancing model performance.

Findings

YOLOv9 achieved a 43.73% mAP 50-95, outperforming previous models.

Data augmentation improved detection accuracy.

Model implementation is publicly available.

Abstract

The introduction of YOLOv9, the latest version of the You Only Look Once (YOLO) series, has led to its widespread adoption across various scenarios. This paper is the first to apply the YOLOv9 algorithm model to the fracture detection task as computer-assisted diagnosis (CAD) to help radiologists and surgeons to interpret X-ray images. Specifically, this paper trained the model on the GRAZPEDWRI-DX dataset and extended the training set using data augmentation techniques to improve the model performance. Experimental results demonstrate that compared to the mAP 50-95 of the current state-of-the-art (SOTA) model, the YOLOv9 model increased the value from 42.16% to 43.73%, with an improvement of 3.7%. The implementation code is publicly available at https://github.com/RuiyangJu/YOLOv9-Fracture-Detection.