Volume 11 - Volume 11
MRI Brain Image Segmentation by Fully Convectional U-Net
Abstract
When there is rapid growth in the research, and it will lead to use off large amount of data to get
accurate results. When you are having large number of data then we require new techniques that will
gives better performance in processing. The segmentation of a brain tumour is critical for both
treatment and prevention. Various researchers proposed different neural network architectures to get
better performance in segmentation of the brain tumour. processing this huge data is challenging and
time taking process for computational and analysis. In this paper we are discussing about image
segmentation by using fully conventional network U-Net. In the first stage we are performing some
pre-processing on data sets by using adaptive filters. In the next step we are using U-Net architecture
to perform segmentation and prediction of MRI brain images. In the next step we are performing
Contrast Limited Adaptive Histogram Equalization (CLAHE) to equalize images. CLAHE takes care
of over-amplification of the contrast. CLAHE operates on tiles of the image, rather than entire image.
Paper Details
PaperID: 1877
Author's Name: Srinivasarao Gajula and V. Rajesh
Volume: Volume 11
Issues: Volume 11
Keywords: Medical Imaging, Deep Learning, MRI, Brain Tumor Segmentation, Contrast Limited Adaptive Histogram Equalization (CLAHE).
Year: 2021
Month: February
Pages: 6035-6042