A U-Net-Based CNN Model for Detection and Segmentation of Brain Tumor

Abstract

Human brain consists of millions of cells to control the overall structure of the human body. When these cells start behaving abnormally, then brain tumors occurred. Precise and initial stage brain tumor detection has always been an issue in the field of medicines for medical experts. To handle this issue, various deep learning techniques for brain tumor detection and segmentation techniques have been developed, which worked on different datasets to obtain fruitful results, but the problem still exists for the initial stage of detection of brain tumors to save human lives. For this purpose, we proposed a novel U-Net-based Convolutional Neural Network (CNN) technique to detect and segmentizes the brain tumor for Magnetic Resonance Imaging (MRI). Moreover, a 2-dimensional publicly available Multimodal Brain Tumor Image Segmentation (BRATS2020) dataset with 1840 MRI images of brain tumors has been used having an image size of 240 × 240 pixels. After initial dataset preprocessing the proposed model is trained by dividing the dataset into three parts i.e., testing, training, and validation process. Our model attained an accuracy value of 0.98 % on the BRATS2020 dataset, which is the highest one as compared to the already existing techniques.

Comparative Study on Architecture of Deep Neural Networks for Segmentation of Brain Tumor using Magnetic Resonance Images

“…An improved U-Net architecture called InR-ResCBAM-U-net [117] was used for simplified training of DNN to achieve segmentation with higher accuracy. A CNN with U-Net based model was proposed in [118] to rectify the problem of tumor segmentation and the brain tumor was classified as non-enhancing tumor, necrosis, enhancing tumor and edema. The performance of the developed models based on U-Net for segmentation of abnormalities in brain using MRI images was compared by different learning parameters [119].…”

Deep Learning-Enhanced Brain Tumor Prediction via Entropy-Coded BPSO in CIELAB Color Space

“…Key-K-mean-SSO-RBNN and new hybrid segmentation were applied to the given data and compared with existing methods for specificity, F1 score, MCC, accuracy, Kappa coefficient, sensitivity, and complexity. Critical-K-mean-SSO-RBNN can classify 96%, 92%, and 94% of data [9][10][11].…”