• M.SARANYA
• Dr.U.V.Ratna kumari

For numerous applications in the field of medical analysis, the localization and segmentation of brain tumours from magnetic resonance imaging (MRI) are challenging and important tasks. Many recent approaches used the four modalities T1, T1c, T2, and FLAIR because each brain imaging modality provides distinct and important details related to each area of the tumour. In this project, to obtain a flexible and effective brain tumour segmentation system, first, we propose a preprocessing approach to work only on a small part of the image rather than the whole part of the image. In the second step, as we are dealing with a smaller part of brain images in each slice, a simple and efficient Convolutional Neural Network is proposed. Two network one is 3D CNN and other is U-Net is designed and ensembled.Finally to achieve good results Particle swarm optimization is designed to achieve the global best feature for segmentation of brain tumour. The matlab is used for performing experimental evaluation.

3D CNN,U-Net,Particle swarm optimization,matlab

"OPTIMIZED DEEP NEURAL NETWORKS FOR SEGMENTATION OF BRAIN TUMOUR FROM MR IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 10, page no.c67-c72, October-2022, Available :http://www.jetir.org/papers/JETIR2210207.pdf

"OPTIMIZED DEEP NEURAL NETWORKS FOR SEGMENTATION OF BRAIN TUMOUR FROM MR IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 10, page no. ppc67-c72, October-2022, Available at : http://www.jetir.org/papers/JETIR2210207.pdf