Enhancing Wrist Fracture Detection with YOLO

TL;DR

This study evaluates state-of-the-art YOLO single-stage deep learning models for wrist fracture detection, demonstrating their superior performance over traditional two-stage methods and highlighting their potential in improving pediatric wrist diagnosis.

Contribution

It introduces the application of YOLOv5, YOLOv6, YOLOv7, and YOLOv8 models for wrist fracture detection, showing their effectiveness and outperforming Faster R-CNN in this domain.

Findings

YOLO models outperform Faster R-CNN in fracture detection.

YOLOv8m achieves a sensitivity of 0.92 and mAP of 0.95.

YOLOv8x achieves the highest mAP of 0.77 on pediatric wrist dataset.

Abstract

Diagnosing and treating abnormalities in the wrist, specifically distal radius, and ulna fractures, is a crucial concern among children, adolescents, and young adults, with a higher incidence rate during puberty. However, the scarcity of radiologists and the lack of specialized training among medical professionals pose a significant risk to patient care. This problem is further exacerbated by the rising number of imaging studies and limited access to specialist reporting in certain regions. This highlights the need for innovative solutions to improve the diagnosis and treatment of wrist abnormalities. Automated wrist fracture detection using object detection has shown potential, but current studies mainly use two-stage detection methods with limited evidence for single-stage effectiveness. This study employs state-of-the-art single-stage deep neural network-based detection models YOLOv5, YOLOv6, YOLOv7, and YOLOv8 to detect wrist abnormalities. Through extensive experimentation, we found that these YOLO models outperform the commonly used two-stage detection algorithm, Faster R-CNN, in fracture detection. Additionally, compound-scaled variants of each YOLO model were compared, with YOLOv8m demonstrating a highest fracture detection sensitivity of 0.92 and mean average precision (mAP) of 0.95. On the other hand, YOLOv6m achieved the highest sensitivity across all classes at 0.83. Meanwhile, YOLOv8x recorded the highest mAP of 0.77 for all classes on the GRAZPEDWRI-DX pediatric wrist dataset, highlighting the potential of single-stage models for enhancing pediatric wrist imaging.