Self-attention-based generative adversarial network optimized with color harmony algorithm for brain tumor...

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Oncology

Background:

• Brain tumors are a significant global health concern with high fatality rates.
• Accurate and efficient brain tumor classification is crucial for timely diagnosis and treatment.
• Existing deep learning methods often struggle with precision and computational efficiency.

Purpose of the Study:

• To propose a novel and efficient approach for brain tumor classification using magnetic resonance (MR) images.
• To enhance the accuracy and reduce the computational time of brain tumor identification.
• To compare the proposed method against existing deep learning models.

Main Methods:

• A novel approach, BTC-SAGAN-CHA-MRI, was developed for brain tumor classification.
• Input brain MR images from the BRATS dataset were pre-processed using Mean Curvature Flow.
• Radiomic features were extracted using Improved Non-Sub sampled Shearlet Transform (INSST) and fed into a SAGAN optimized with a Color Harmony Algorithm.

Main Results:

• The proposed BTC-SAGAN-CHA-MRI method achieved an accuracy of 99.29% for brain tumor identification.
• It demonstrated significant improvements in accuracy (18.29%, 14.09%, 7.34%) and reductions in computation time (67.92%, 54.04%, 59.08%) compared to existing models.
• The method effectively categorizes brain images into Glioma, Meningioma, and Pituitary tumor types.

Conclusions:

• The BTC-SAGAN-CHA-MRI technique offers a promising advancement in brain tumor classification.
• The method enhances precision and efficiency, potentially leading to improved diagnostic outcomes in medical imaging.
• This approach addresses the limitations of current deep learning models in terms of accuracy and computational cost.