Abstract: Brain tumor segmentation from 3D images is one of the most important and challenging tasks in the field of medical imaging. Manual classification can lead to false predictions and diagnoses. Moreover, this is a difficult process when the supporting data is enormous.. Extracting brain tumour regions from MRI images becomes challenging due to the great variety of appearances of brain tumours and how similar they are to normal tissues. In this article, we designed a modified U-Net architecture under a deep learning framework for brain real images for medical imaging and computer-assisted interventions provided by the BRATS 2020 dataset. Test accuracy of 99.4% has been achieved. A comparative review with other papers shows our model using U-Net performs better than other deep learning-based models.
Keywords: Deep learning,brain tumor classification and segmentation,3d unet architecture.
|
DOI:
10.17148/IJARCCE.2023.12574
