Related Experiment Video
Updated: Oct 14, 2025
09:03
Nasal Brushing Sampling and Processing Using Digital High Speed Ciliary Videomicroscopy – Adaptation for the COVID-19 Pandemic
Published on: November 7, 2020
5.1K
A Study on Weak Edge Detection of COVID-19's CT Images Based on Histogram Equalization and Improved Canny Algorithm
Shou-Ming Hou1, Chao-Lan Jia1, Ming-Jie Hou2
1School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454000, China.
Computational and Mathematical Methods in Medicine
|November 8, 2021
Summary
This study introduces an improved edge detection method for COVID-19 lesions in CT scans, enhancing diagnostic accuracy. The new algorithm effectively identifies weak lesion edges, aiding in the clinical diagnosis of coronavirus disease 2019.
Area of Science:
- Medical Imaging
- Computer Vision
- Artificial Intelligence
Background:
- Coronavirus disease 2019 (COVID-19) poses a significant global health threat.
- Computed tomography (CT) scans are crucial for COVID-19 diagnosis, but lesion edge detection is challenging due to image noise and grayscale variations.
- Accurate detection of weak lesion edges in CT images is vital for effective COVID-19 diagnosis.
Purpose of the Study:
- To develop and evaluate an enhanced edge detection method for identifying COVID-19 lesions in CT images.
- To address the limitations of existing methods in detecting weak and complex lesion edges.
- To improve the accuracy and reliability of CT-based COVID-19 diagnosis.
Main Methods:
- A novel edge detection method combining histogram equalization and an improved Canny algorithm was proposed.
- Histogram equalization was used to enhance image contrast.
- The improved Canny algorithm incorporated a median filter for noise reduction, K-means for segmentation, mathematical morphology, and the Otsu method for edge detection.
Main Results:
- The proposed method demonstrated superior performance in detecting weak lesion edges compared to three other methods.
- Quantitative evaluation using MSE, MAE, and SNR showed favorable results, with average values of 1.7322, 7.9010, and 57.1241, respectively.
- The algorithm achieved an average running time of 5.4887, indicating efficiency.
Conclusions:
- The developed edge detection algorithm effectively enhances the visibility of weak lesion edges in COVID-19 CT scans.
- This method offers a valuable tool to assist clinicians in the accurate diagnosis of COVID-19.
- The findings support the integration of advanced image processing techniques in medical diagnostics.
