# Wavelet Transform and Hierarchical Hybrid Matching for Enhancing End-to-End Pediatric Wrist Fracture Detection

## TL;DR

This paper introduces a new AI model for detecting wrist fractures in children using advanced image processing techniques.

## Contribution

The novel WH-DETR model combines wavelet transforms and hierarchical hybrid matching for improved pediatric wrist fracture detection.

## Key findings

- The WH-DETR model achieves state-of-the-art performance with 68.8% mAP50 score.
- The model improves mAP50 by 1.78%, mAP50-90 by 1.69%, and F1 score by 1.75% over the next best model.
- The model maintains high inference efficiency with only 43 million parameters.

## Abstract

With the increasing frequency of daily physical activities among children and adolescents, the incidence of wrist fractures has been rising annually. Without precise and prompt diagnosis, these fractures may remain undetected, potentially leading to complications. Recent advancements in computer-aided diagnosis (CAD) technologies have facilitated the development of sophisticated diagnostic tools, which significantly improve the accuracy of fracture detection. To enhance the capability of detecting pediatric wrist fractures, this study presents the WH-DETR model, specifically designed for pediatric wrist fracture detection. WH-DETR is configured as a DEtection TRansformer framework, an end-to-end object detection algorithm that obviates the need for non-maximum suppression post-processing. To further enhance its performance, this study first introduces a wavelet transform projection module to capture different frequency features from the feature maps extracted by the backbone. This module allows the network to effectively capture multi-scale and multi-frequency information, improving the detection of subtle and complex features in medical images. Secondly, this study designs a hierarchical hybrid matching framework that decouples the prediction tasks of different decoder layers during training, thereby improving the final predictive capabilities of the model. The framework improves prediction robustness while maintaining inference efficiency. Extensive experiments on the GRAZPEDWRI-DX dataset demonstrate that our WH-DETR model achieves state-of-the-art performance with only 43 M parameters, attaining an \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$ \text {mAP}_{50} $$\end{document}mAP50 score of 68.8%, an \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$ \text {mAP}_{50-90} $$\end{document}mAP50-90 score of 48.3%, and an F1 score of 64.1%. These results represent improvements of 1.78% in \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$ \text {mAP}_{50} $$\end{document}mAP50, 1.69% in \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$ \text {mAP}_{50-90} $$\end{document}mAP50-90, and 1.75% in F1 score, respectively, over the next best-performing model, highlighting its superior efficiency and robustness in pediatric wrist fracture detection.