• Shubhankar Shirish Joshi
• Atul Dusane

A brain tumour is a collection, or mass, of abnormal cells inside the brain. The skull encloses the brain, and is very strong. Any growth inside such a space can create problems. Brain tumours can be of two types i.e. cancerous (malignant) or non cancerous (benign). Brain cancer is a life-threatening disease and it affects all the diagnosed people severely. Precise brain tumour classification helps to diagnose brain cancer early, which increases the survival rate of brain cancer patients, but it is quite hard to detect early. It is difficult to evaluate the magnetic resonance imaging images manually. Therefore there is a need for optimised and fast digital methods for tumour diagnosis with better accuracy. This paper also details the different machine learning techniques used to classify cancer into malignant and normal category. We have used two activations functions and compare the accuracy. We get the highest accuracy on relu which is 91.23% on 100 epo

Convolutional Neural Network, Deep Learning, Image processing

"Brain Tumour Detection by Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 10, page no.d70-d73, October-2022, Available :http://www.jetir.org/papers/JETIR2210320.pdf

"Brain Tumour Detection by Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 10, page no. ppd70-d73, October-2022, Available at : http://www.jetir.org/papers/JETIR2210320.pdf