Predicting Meningioma Using Inception and Efficient Net Algorithms

Predicting Meningioma Using Inception and Efficient Net Algorithms

Chokkalla Ankith Dept of ECE IARE

Dr. S China Venkateswarlu Professor Dept of ECE IARE

Dr. V Siva Nagaraju Professor Dept of ECE IARE

Abstract - Meningioma is the most common primary brain tumor, accounting for more than 30% of all brain tumors. Meningiomas originate in the meninges, the outer three layers of tissue that cover and protect the brain just under the skull. Women are diagnosed with meningiomas more often than men. About 85% of meningiomas are noncancerous, slow-growing tumors. Almost all meningiomas are considered benign, but some meningiomas can be persistent and come back after treatment. This LGG is treated with a combination of surgery and examination by monitoring the meningioma with brain MRI scans. The study of this project enabled us to build a fully automated system for segmentation of meningioma utilizing computer vision techniques, and developing models that would allow high-quality LGG identification in the brain MRI would potentially be automated to identify the genomic subtype of the meningioma by rapid and inexpensive imaging. The methods, techniques, advantages and their limitations and their future challenges are discussed in this project..

Key Words: LGG, MRI,Inception,Efficient Net,CNN