Related Experiment Video
Updated: Jul 17, 2025
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.7K
Meningioma brain tumor detection and classification using hybrid CNN method and RIDGELET transform
B V Prakash1, A Rajiv Kannan2, N Santhiyakumari3
1Faculty of Information Technology, Government College of Engineering, Erode, Tamil Nadu, India.
Scientific Reports
|September 4, 2023
Summary
This study introduces a hybrid Convolutional Neural Network (HCNN) for automated meningioma brain tumor detection. The HCNN system achieves high accuracy in distinguishing tumors from non-tumors in medical images.
Area of Science:
- Medical Imaging Analysis
- Artificial Intelligence in Healthcare
- Computational Neuroscience
Background:
- Meningioma detection is challenging due to low pixel intensity.
- Automated systems are essential for modern medical platforms.
- Accurate detection of brain tumors like meningiomas is critical.
Purpose of the Study:
- To propose a novel hybrid Convolutional Neural Network (HCNN) for automated meningioma detection.
- To develop an efficient HCNN classifier to differentiate meningioma from non-meningioma brain images.
- To improve the accuracy and reliability of brain tumor detection systems.
Main Methods:
- A hybrid Convolutional Neural Network (HCNN) classifier was developed.
- The HCNN incorporates Ridgelet transform for pixel stability and feature extraction.
- A segmentation algorithm was employed for precise tumor pixel identification.
Main Results:
- The HCNN system demonstrated high performance on multiple datasets (BRATS 2019, Nanfang, BRATS 2022).
- Achieved up to 99.81% classification accuracy and 99.8% segmentation accuracy.
- Outperformed state-of-the-art meningioma detection algorithms in experimental comparisons.
Conclusions:
- The proposed HCNN-based system offers a highly efficient and accurate solution for meningioma detection.
- The integration of Ridgelet transform enhances feature stability and classification performance.
- This automated approach holds significant potential for clinical application in neuro-oncology.
