Related Experiment Video
Updated: May 4, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
43.7K
An intelligent framework for medical image retrieval using MDCT and multi SVM
J A Alex Rajju Balan1, S Edward Rajan2
1Vins Christian College of Engineering, Nagercoil, Tamil Nadu, India.
Summary
This study introduces an advanced medical image retrieval system using texture features and multi-Support Vector Machines (SVM) for accurate diagnosis in healthcare management systems. The developed method achieved an impressive 98% retrieval accuracy.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Healthcare Informatics
Background:
- The exponential growth of medical images presents significant management challenges.
- Effective retrieval of medical images is crucial for accurate diagnosis and healthcare management.
Purpose of the Study:
- To develop and analyze an innovative medical image retrieval system.
- To enhance diagnostic accuracy within healthcare management systems through improved image retrieval.
Main Methods:
- Extraction of texture features from medical images using Modified Discrete Cosine Transform (MDCT).
- Implementation of a multi-Support Vector Machine (SVM) classification technique.
- Validation through theoretical analysis and simulation on a database of 100 trademark medical images.
Main Results:
- Successful data extraction and high-performance image retrieval were achieved.
- An integrated texture feature representation using MDCT and multi-SVM yielded 98% retrieval accuracy.
- The multiclassification SVM technique demonstrated high suitability for medical image analysis.
Conclusions:
- The proposed multiclassification SVM approach is effective for medical image retrieval.
- The system achieved retrieval accuracies of 98% and 99% for different medical image sets.
- This method significantly improves the efficiency and accuracy of medical image management in healthcare.