Brain Tumor Detection Based on Hybrid Convolutional Adaptive Neuro Fuzzy Inference System Using MRI Image

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computational Neuroscience

Background:

• Brain tumors are life-threatening, and their early detection is crucial.
• Current magnetic resonance imaging (MRI) detection methods face challenges with noise, segmentation accuracy, and generalization.
• Limitations in existing techniques necessitate advanced approaches for reliable brain tumor identification.

Purpose of the Study:

• To develop and evaluate a novel Convolutional-Adaptive Neuro-Fuzzy Inference System (Conv-ANFIS) for enhanced brain tumor detection from MRI images.
• To address the limitations of existing brain tumor detection methods, including noise handling and segmentation accuracy.
• To improve the overall accuracy and reliability of brain tumor identification using a hybrid AI model.

Main Methods:

• A Convolutional Neural Network (CNN) is integrated with an Adaptive Neuro-Fuzzy Inference System (ANFIS) to create the Conv-ANFIS model.
• Pre-processing steps include Non-Local Means (NLM) filtering for de-noising and skull removal.
• Segmentation is performed using the Structure Correcting Adversarial Network (SCAN), followed by feature extraction and tumor identification via Conv-ANFIS.

Main Results:

• The Conv-ANFIS approach achieved a recall of 92.31%, precision of 90.13%, and an F1-score of 91.21%.
• The proposed method demonstrated superior performance compared to existing brain tumor detection techniques.
• Effective de-noising, skull removal, and segmentation were achieved, leading to improved detection accuracy.

Conclusions:

• The Conv-ANFIS model offers a robust and accurate solution for brain tumor detection in MRI images.
• This hybrid AI approach effectively overcomes the limitations of traditional detection methods.
• The study highlights the potential of integrating deep learning and fuzzy inference systems for advanced medical image analysis.