Related Experiment Video
Updated: Aug 29, 2025
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
Published on: June 21, 2024
Image Recognition of Pediatric Pneumonia Based on Fusion of Texture Features and Depth Features
Hao-Nan Wang1, Li-Xin Zheng1, Shu-Wan Pan1
1College of Engineering, Huaqiao University, Quanzhou 362021, China.
Insights
This study introduces FC-VGG, a novel feature fusion model for diagnosing childhood pneumonia using chest X-rays. The model enhances diagnostic accuracy by combining texture and deep features, outperforming existing methods.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Vision
Background:
- Pneumonia poses a significant threat to child health, particularly in China, where it is a leading cause of mortality in children under five.
- Chest X-rays are the primary diagnostic tool, but interpretation errors can occur due to human factors like fatigue and inexperience.
- Developing automated diagnostic tools is crucial to improve accuracy and efficiency in pediatric pneumonia detection.
Purpose of the Study:
- To develop and evaluate a novel feature fusion model (FC-VGG) for improved detection of childhood pneumonia from chest X-ray images.
- To enhance the diagnostic performance by integrating texture features (LBP, HOG) with deep features within a convolutional neural network architecture.
- To address the limitations of manual interpretation and existing automated methods in pediatric pneumonia diagnosis.
Main Methods:
- A modified VGG16 convolutional neural network (C-VGG) was employed as the base architecture.
- Texture features, including Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG), were extracted and fused with deep features.
- An Additive fusion method was utilized to combine texture and deep features, creating the FC-VGG model.
Main Results:
- The FC-VGG model achieved high performance metrics: 92.19% accuracy, 93.44% average precision, 92.19% average recall, and 92.81% average F1-score.
- Experimental results demonstrated that the FC-VGG model surpasses the performance of existing deep learning models and traditional feature recognition algorithms.
- The integration of detailed texture information improved the model's ability to recognize pneumonia patterns in pediatric chest X-rays.
Conclusions:
- The proposed FC-VGG model effectively integrates texture and deep features for accurate childhood pneumonia detection.
- FC-VGG offers a promising advancement in AI-assisted medical imaging for pediatric respiratory diseases.
- The model's enhanced performance suggests its potential for clinical application in improving pneumonia diagnosis in children.
Abstract:
Pneumonia is one of the diseases that seriously endangers human health, and it is also the leading cause of death of children under the age of five in China. The most commonly used imaging examination method for radiologists is mainly based on chest X-ray images. Still, imaging errors often result during imaging examinations due to objective factors such as visual fatigue and lack of experience. Therefore, this paper proposes a feature fusion model, FC-VGG, based on the fusion of texture features (local binary pattern LBP and directional gradient histogram HOG) and depth features. The model improves model performance by adding detailed information in texture features to the convolutional neural network while making the model more suitable for clinical use. We input the X-ray image with texture features into the modified VGG16 model, C-VGG, and then add the Add fusion method to C-VGG for feature fusion so that FC-VGG is obtained, so FC-VGG has texture features detailed information and abstract information of deep features. Through experiments, our model has achieved 92.19% accuracy in recognizing children's pneumonia images, 93.44% average precision, 92.19% average recall, and 92.81% average F1 coefficient, and the model performance exceeds existing deep learning models and traditional feature recognition algorithms.
More Related Videos
Related Concept Videos
01:30Pneumonia III: Complications and Assessment
01:29Assessment of Ventilation II: Respiratory Depth and Rhythm
Respiratory depth measures the volume of air inhaled or exhaled during a breath. It can vary from shallow to deep and typically remains consistent when a person is at rest or asleep. Occasionally, individuals will automatically inhale deeply, known as sighing, which inflates the lungs with more air than normal breathing.
To assess respiratory depth, observe the degree of chest excursion or movement: