Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detection

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

TL;DR

This paper proposes YOLOv8-ResCBAM, which incorporates Convolutional Block Attention Module integrated with resblock (ResCBAM) into the original YOLOv8 network architecture, which achieves the state-of-the-art performance.

Abstract

Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first, and prepare for the surgery based on the analysis of the X-ray images. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection for Computer-Assisted Diagnosis, where the YOLOv8 model has obtained the satisfactory results. Applying the attention modules to neural networks is one of the effective methods to improve the model performance. This paper proposes YOLOv8-ResCBAM, which incorporates Convolutional Block Attention Module integrated with resblock (ResCBAM) into the original YOLOv8 network architecture. The experimental results on the GRAZPEDWRI-DX dataset demonstrate that the mean Average Precision calculated at Intersection over Union threshold of 0.5 (mAP 50) of the proposed model increased from 63.6% of the original YOLOv8 model to 65.8%, which achieves the state-of-the-art performance. The implementation code is available at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.

YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detection

TL;DR

This paper proposes YOLOv8-ResCBAM, which incorporates Convolutional Block Attention Module integrated with resblock (ResCBAM) into the original YOLOv8 network architecture, which achieves the state-of-the-art performance.

Abstract

Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first, and prepare for the surgery based on the analysis of the X-ray images. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection for Computer-Assisted Diagnosis, where the YOLOv8 model has obtained the satisfactory results. Applying the attention modules to neural networks is one of the effective methods to improve the model performance. This paper proposes YOLOv8-ResCBAM, which incorporates Convolutional Block Attention Module integrated with resblock (ResCBAM) into the original YOLOv8 network architecture. The experimental results on the GRAZPEDWRI-DX dataset demonstrate that the mean Average Precision calculated at Intersection over Union threshold of 0.5 (mAP 50) of the proposed model increased from 63.6% of the original YOLOv8 model to 65.8%, which achieves the state-of-the-art performance. The implementation code is available at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.
Paper Structure (16 sections, 10 equations, 4 figures, 2 tables)

This paper contains 16 sections, 10 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Fracture Detection
  4. Attention Module
  5. Methodology
  6. Baseline
  7. Proposed Method
  8. Experiment
  9. Dataset
  10. Preprocessing and Data Augmentation
  11. Evaluation Metric
  12. Experiment Setup
  13. Ablation Study
  14. Experimental Results
  15. Conclusion and Future Work
  16. ...and 1 more sections

Figures (4)

  • Figure 1: The network architecture of our proposed YOLOv8-ResCBAM model.
  • Figure 2: The network architecture of ResCBAM, which is Convolutional Block Attention Module (CBAM) integrated with resblock.
  • Figure 3: Examples of prediction results of our proposed model and YOLOv8 model for pediatric wrist fracture detection when the input image size is 1024.
  • Figure 4: Visualization of the accuracy of predicting each class using our proposed and YOLOv8 models on the GRAZPEDWRI-DX dataset with the input image size of 1024.