• P Navya
• A Dakshayani
• P Asish Kumar
• M Krishna Akhilesh

Brain tumours are serious health problems affecting the growth of the brain or surrounding tissues and divine cells, and are classified as primary tumours derived from brain and secondary (metastatic) tumours that diffuse from other organs. The most frequently diagnosed types include neuroma, meningitis, and pituitary adenoma. Each demonstrates unique problems in diagnosis and treatment with early detection and accurate classification to optimize treatment strategies and improve patient survival. This study evaluates the effects of neural chain architectures based on deep training for classification of brain tumours using MRI images, and focuses on the accuracy of classification and computational efficiency that identifies balance, and resource use. By comparing different models, including folding networks (CNN), multi-layer procedure (MLP), and CNN user architecture, experimental results show that CNN has a large classification accuracy of approximately 95%, surpassing other architectures. This examines the complex spatial features of MRI images and highlights techniques that are highly effective in classifying tumours. The results also show that CNNs defined by the architecture user provide faster start times than MLP. This becomes a practical option for real-time diagnostic applications and is ultimately improved due to automated diagnostic methods for neuronal condensation.

Brain tumours, MRI images, Deep Learning, Convolutional Neural Networks,Classification Accuracy.

"Brain Tumour Diagnosis Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.e59-e66, March-2025, Available :http://www.jetir.org/papers/JETIR2503421.pdf

"Brain Tumour Diagnosis Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppe59-e66, March-2025, Available at : http://www.jetir.org/papers/JETIR2503421.pdf