Related Experiment Video
Updated: Oct 2, 2025
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
Multi-Channel Based Image Processing Scheme for Pneumonia Identification
Grace Ugochi Nneji1, Jingye Cai1, Jianhua Deng1
1School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
Abstract:
Pneumonia is a prevalent severe respiratory infection that affects the distal and alveoli airways. Across the globe, it is a serious public health issue that has caused high mortality rate of children below five years old and the aged citizens who must have had previous chronic-related ailment. Pneumonia can be caused by a wide range of microorganisms, including virus, fungus, bacteria, which varies greatly across the globe. The spread of the ailment has gained computer-aided diagnosis (CAD) attention. This paper presents a multi-channel-based image processing scheme to automatically extract features and identify pneumonia from chest X-ray images. The proposed approach intends to address the problem of low quality and identify pneumonia in CXR images. Three channels of CXR images, namely, the Local Binary Pattern (LBP), Contrast Enhanced Canny Edge Detection (CECED), and Contrast Limited Adaptive Histogram Equalization (CLAHE) CXR images are processed by deep neural networks. CXR-related features of LBP images are extracted using shallow CNN, features of the CLAHE CXR images are extracted by pre-trained inception-V3, whereas the features of CECED CXR images are extracted using pre-trained MobileNet-V3. The final feature weights of the three channels are concatenated and softmax classification is utilized to determine the final identification result. The proposed network can accurately classify pneumonia according to the experimental result. The proposed method tested on publicly available dataset reports accuracy of 98.3%, sensitivity of 98.9%, and specificity of 99.2%. Compared with the single models and the state-of-the-art models, our proposed network achieves comparable performance.
Insights
This study introduces a novel computer-aided diagnosis (CAD) system for identifying pneumonia from chest X-rays. The multi-channel deep learning approach achieves high accuracy, aiding in early detection of this severe respiratory infection.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Pulmonology
Background:
- Pneumonia is a significant global health concern, causing high mortality rates, particularly in young children and the elderly.
- Accurate and timely diagnosis of pneumonia is crucial for effective treatment and public health management.
- Existing diagnostic methods can be limited by factors such as image quality and the need for expert interpretation.
Purpose of the Study:
- To develop and evaluate a multi-channel image processing scheme for automated pneumonia detection from chest X-ray (CXR) images.
- To address challenges related to low image quality and improve the accuracy of pneumonia identification in CXR.
- To present a deep learning model that integrates features from different image processing techniques for enhanced pneumonia classification.
Main Methods:
- A novel multi-channel approach was employed, utilizing Local Binary Pattern (LBP), Contrast Enhanced Canny Edge Detection (CECED), and Contrast Limited Adaptive Histogram Equalization (CLAHE) processed CXR images.
- Deep neural networks, including shallow CNN, pre-trained Inception-V3, and pre-trained MobileNet-V3, were used to extract features from the three distinct image channels.
- Features from each channel were concatenated, and a softmax classifier was used for the final pneumonia identification.
Main Results:
- The proposed deep learning network demonstrated high accuracy in classifying pneumonia from CXR images.
- Experimental results on a public dataset reported an accuracy of 98.3%, sensitivity of 98.9%, and specificity of 99.2%.
- The multi-channel approach achieved comparable performance to single-model and state-of-the-art methods.
Conclusions:
- The developed multi-channel computer-aided diagnosis (CAD) system effectively identifies pneumonia from chest X-rays.
- The proposed method shows significant potential for improving the accuracy and efficiency of pneumonia diagnosis.
- This approach offers a promising tool for assisting clinicians in the early detection and management of pneumonia.
More Related Videos
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
10:06Efficient Method for Imaging Murine Lungs that Preserves Spatial Dynamics of Fungal Spores in the Airways
Published on: December 13, 2024
