Papers › Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images

Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images

1 Oct 2024arXiv:2410.01031archive 2025-07-28

Rui-Yang Ju, Chun-Tse Chien, Enkaer Xieerke, Jen-Shiun Chiang

Children often suffer wrist trauma in daily life, while they usually need radiologists to analyze and interpret X-ray images before surgical treatment by surgeons. The development of deep learning has enabled neural networks to serve as computer-assisted diagnosis (CAD) tools to help doctors and experts in medical image diagnostics. Since YOLOv8 model has obtained the satisfactory success in object detection tasks, it has been applied to various fracture detection. This work introduces four variants of Feature Contexts Excitation-YOLOv8 (FCE-YOLOv8) model, each incorporating a different FCE module (i.e., modules of Squeeze-and-Excitation (SE), Global Context (GC), Gather-Excite (GE), and Gaussian Context Transformer (GCT)) to enhance the model performance. Experimental results on GRAZPEDWRI-DX dataset demonstrate that our proposed YOLOv8+GC-M3 model improves the mAP@50 value from 65.78% to 66.32%, outperforming the state-of-the-art (SOTA) model while reducing inference time. Furthermore, our proposed YOLOv8+SE-M3 model achieves the highest mAP@50 value of 67.07%, exceeding the SOTA performance. The implementation of this work is available at https://github.com/RuiyangJu/FCE-YOLOv8.

Paper PDF Code

Code

ruiyangju/fce-yolov8 officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

2D Object Detection Fracture detection Object Detection Retinal Vessel Segmentation medical image detection object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+SE	AP50	67.07	#1 of 19	Archive leaderboard	report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+SE	F1-score	0.66	#1 of 19	Archive leaderboard	report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+GC	AP50	66.32	#3 of 19	Archive leaderboard	report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+GC	F1-score	0.66	#3 of 19	Archive leaderboard	report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+GE	AP50	65.99	#4 of 19	Archive leaderboard	report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+GE	F1-score	0.64	#4 of 19	Archive leaderboard	report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+GCT	AP50	65.67	#7 of 19	Archive leaderboard	report
Fracture detection	GRAZPEDWRI-DX	YOLOv8+GCT	F1-score	0.64	#7 of 19	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer YOLOv8

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections