Brain tumor segmentation of the FLAIR MRI images using novel ResUnet

New technologies are growing faster and now play a key role in analysing new ways of looking at the morphology of the brain. It is difficult to diagnose a brain tumor. Accurate diagnosis and segmentation of the brain tumor used for early treatment planning. Different neuroimaging modalities are used to provide better tissue resolution and provide assistance to the radiologist. Manual segmentation of the brain tumor is a complicated task as it faces problems with noise, intensity inhomogeneity, merging of tissues, and overlapping of tissue intensity. This makes manual segmentation a time consuming approach. In recent CAD systems are developed using deep learning models. In this paper, we used residual models and form as a Unet to perform segmentation of the tissues. To perform segmentation, we used the Kaggle LGG dataset, which contains 110 patient datasets. We designed a novel residual model used as the backbone to design Unet from scratch and perform segmentation of multi spectral images. The Proposed model works well, and the performance of the model is analysed using the Dice coefficient, Jaccard index/ IoU. The model yields a dice coefficient of 0.9056 and a jaccard index/ IoU of 0.8293. This model gives better tissue segmentation using FLAIR modality compared to the existing frame work.