Brain tumour classification using MRI images based on lenet with golden teacher learning optimization.
Srilakshmi Aluri1, Sagar S Imambi2
1Research Scholar, Computer Science & Engineering, K L Educational foundation, deemed to be University, Vaddeswaram, India.
Network (Bristol, England)
|November 10, 2023
Summary
This study introduces an optimized LeNet model for brain tumour classification (BTC) using MRI images. The GTLO-LeNet model achieved high accuracy in identifying gliomas, meningiomas, and pituitary tumours.
Area of Science:
- Neurology
- Medical Imaging
- Artificial Intelligence
Background:
- Brain tumours (BT) are a significant neurological disorder with a rising mortality rate.
- Early detection of brain tumours is critical for effective patient treatment and improved survival rates.
- Magnetic Resonance Imaging (MRI) is a key modality for diagnosing brain tumours.
Purpose of the Study:
- To develop and evaluate an automated brain tumour classification (BTC) system using MRI images.
- To enhance the accuracy and efficiency of brain tumour diagnosis through advanced image processing and machine learning techniques.
Main Methods:
- MRI images were pre-processed using a non-local means (NLM) filter for noise reduction.
- Tumour segmentation was performed using the SegNet model.
- Brain tumour classification was achieved using the LeNet model, optimized with the Golden Teacher Learning Optimization Algorithm (GTLO).
Main Results:
- The GTLO-LeNet model demonstrated high performance in classifying brain tumours.
- Achieved an accuracy of 0.896.
- Key performance metrics included NPV of 0.907, PPV of 0.821, TNR of 0.880, and TPR of 0.888.
Conclusions:
- The proposed GTLO-LeNet model offers a promising approach for accurate and efficient brain tumour classification from MRI data.
- This method has the potential to aid clinicians in early diagnosis, leading to better patient outcomes.
