Related Experiment Video
Updated: Jun 16, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Medical image segmentation approach based on hybrid adaptive differential evolution and crayfish optimizer.
Reham R Mostafa1, Ahmed M Khedr2, Zaher Al Aghbari2
1Big Data Mining and Multimedia Research Group, Centre for Data Analytics and Cybersecurity (CDAC), Research Institute of Sciences and Engineering (RISE), University of Sharjah, Sharjah 27272, United Arab Emirates; Information Systems Department, Faculty of Computers and Information Sciences, Mansoura University, Mansoura 35516, Egypt.
A novel hybrid optimization algorithm, HADECO, enhances multi-threshold image segmentation for medical imaging. This method improves diagnostic accuracy by efficiently segmenting tumors and lesions in MRI and CT scans.
Area of Science:
- Medical Image Analysis
- Computational Intelligence
- Optimization Algorithms
Background:
- Medical image segmentation is crucial for diagnostics but challenged by multilevel thresholding's complexity.
- Traditional methods struggle with NP-hard optimization problems in threshold determination.
- Efficient strategies are needed to improve segmentation accuracy and analysis.
Purpose of the Study:
- To introduce an efficient multi-threshold image segmentation (MTIS) method using a hybrid optimization algorithm.
- To enhance the accuracy and efficiency of medical image analysis and diagnosis.
- To address the computational complexity of multilevel thresholding.
Main Methods:
- Developed HADECO, a hybrid algorithm combining Differential Evolution (DE) and Crayfish Optimization Algorithm (COA) with information exchange.
- Employed Latin Hypercube Sampling (LHS) for initial population generation.
- Introduced an improved DE (IDE) with adaptive parameters and an adaptive COA (ACOA) for balanced exploration and exploitation.
Main Results:
- HADECO demonstrated superior optimization capabilities, achieving the lowest average Friedman rank (1.08) against contemporary algorithms.
- The HADECO-based MTIS method showed improved quantitative results in segmenting brain intracranial hemorrhage (ICH) and knee MRI images.
- Achieved superior average Peak Signal-to-Noise Ratio (PSNR) and Feature Similarity Index (FSIM) in both brain (1.5, 1.7) and knee (1.3, 1.2) image segmentation tasks.
Conclusions:
- The proposed HADECO algorithm effectively addresses the challenges of multi-threshold image segmentation.
- The HADECO-based MTIS method significantly enhances segmentation accuracy and efficiency in medical imaging applications.
- This approach offers a promising solution for precise tumor and lesion isolation, improving diagnostic capabilities.
