Lightweight G-YOLOv11: Advancing Efficient Fracture Detection in Pediatric Wrist X-rays

TL;DR

This paper introduces G-YOLOv11, a lightweight and efficient fracture detection system for pediatric wrist X-rays that reduces computational resources while maintaining high accuracy, suitable for clinical use.

Contribution

The paper presents a novel lightweight YOLOv11-based detector using ghost convolution, achieving state-of-the-art efficiency and accuracy in fracture detection.

Findings

Achieved mAP@0.5 of 0.535 on GRAZPEDWRI-DX dataset.

Reduced model size by 68.7% compared to YOLOv11l.

Inference time of 2.4 ms on NVIDIA A10 GPU.

Abstract

Computer-aided diagnosis (CAD) systems have greatly improved the interpretation of medical images by radiologists and surgeons. However, current CAD systems for fracture detection in X-ray images primarily rely on large, resource-intensive detectors, which limits their practicality in clinical settings. To address this limitation, we propose a novel lightweight CAD system based on the YOLO detector for fracture detection. This system, named ghost convolution-based YOLOv11 (G-YOLOv11), builds on the latest version of the YOLO detector family and incorporates the ghost convolution operation for feature extraction. The ghost convolution operation generates the same number of feature maps as traditional convolution but requires fewer linear operations, thereby reducing the detector's computational resource requirements. We evaluated the performance of the proposed G-YOLOv11 detector on the GRAZPEDWRI-DX dataset, achieving an mAP@0.5 of 0.535 with an inference time of 2.4 ms on an NVIDIA A10 GPU. Compared to the standard YOLOv11l, G-YOLOv11l achieved reductions of 13.6% in mAP@0.5 and 68.7% in size. These results establish a new state-of-the-art benchmark in terms of efficiency, outperforming existing detectors. Code and models are available at https://github.com/AbdesselamFerdi/G-YOLOv11.