Design of an Optimal Convolutional Neural Network Architecture for MRI Brain Tumor Classification by Exploiting...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computational Neuroscience

Background:

• Accurate brain tumor classification from MRI scans is crucial for diagnosis and treatment planning.
• Traditional Convolutional Neural Networks (CNNs) struggle with the complex variations in tumor characteristics like shape, size, and texture.
• Manual CNN architecture design is inefficient and prone to errors.

Purpose of the Study:

• To develop an automated approach for designing a CNN architecture tailored for MRI-based brain tumor classification.
• To enhance the accuracy and efficiency of brain tumor classification using optimized CNN models.

Main Methods:

• Employed Particle Swarm Optimization (PSO) to automatically search for optimal CNN architectural parameters.
• Optimized parameters included layer types/numbers, filter sizes/quantities, and fully connected layer neuron counts.
• Evaluated the PSO-optimized CNN's performance on MRI-based brain tumor classification tasks.

Main Results:

• The PSO-optimized CNN achieved a highly accurate classification rate of 99.19%.
• Demonstrated superior performance compared to traditional or manually designed CNN models.
• Validated the effectiveness of automated architecture search for medical imaging applications.

Conclusions:

• Automated CNN architecture design using PSO significantly improves brain tumor classification accuracy from MRI data.
• This approach offers a powerful tool for enhancing diagnostic precision in complex medical imaging.
• Highlights the potential of AI-driven methods in advancing healthcare technology.