Chien Chun-Tse ; Ju Rui-Yang ; Chou Kuang-Yi ; Chiang Jen-Shiun

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 fracturedetection task as computer-assisted diagnosis (CAD) to help radiologists andsurgeons to interpret X-ray images. Specifically, this paper trained the modelon the GRAZPEDWRI-DX dataset and extended the training set using dataaugmentation techniques to improve the model performance. Experimental resultsdemonstrate 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%, withan improvement of 3.7%. The implementation code is publicly available athttps://github.com/RuiyangJu/YOLOv9-Fracture-Detection.