Deep learning approach for detecting and localizing brain tumor from magnetic resonance imaging images

Abstract

<span lang="EN-US">Brain is the most important part of the nervous system. Brain tumor is mainly a mass or growth of abnormal tissues in a brain. Early detection of brain tumor can reduce complex treatment process. Magnetic resonance images (MRI) are used to detect brain tumor. In this paper, we have introduced a deep convolutional neural network (CNN) to automatic brain tumor segmentation using MRI medical images which can solve the vanishing gradient problem. Classifying the brain MRI images with Resnet-50 and InceptionV3 in order to identify whether there is tumor or not. After this step, we have compared the accuracy level of both of the CNN models. Thereafter, applied U-Net architecture individually with encoder Resnet-50 and InceptionV3 to avieved promising results. The publicly available low grade gliomas (LGG) segmentation dataset has been utilized to test the model. Before applying the model on the MRI images preprocessing and several augmentation techniques have been done to obtain quality a dataset. U-net architecture with InceptionV3 provided 99.55% accuracy. On the other hand, our proposed method U-net with encoder ResNet-50 showed 99.77% accuracy.</span>

Survey of Brain Tumor Image Segmentation Using Artificial Intelligence Techniques

“…[12] The researcher (Iqbal, Muhammad Javaid, et al 2022) presents model sets the updated parameters and uses the U-Net deep learning segmentation technique with an enhanced layered structure. The BRATS 2018 dataset, which contains multimodal MRI sequences including T1, T2, T1Gd, and FLAIR, is used by the model [3]. In comparison to cuttingedge techniques, the suggested model achieves high Dice Coefficient values for both high-grade and low-grade glioma (HGG) volumes [4].…”

“…When there are no tumorous photos, the suggested model stops the algorithm; otherwise, tumorous images are forwarded to the following stage of the architecture. [3] The researcher (Naik Snehalatha et al 2023) presents a deep learning-based method for classifying brain tumors utilizing linear neighborhood semantic segmentation, GoogleNet, and SLIC segmentation with super pixel fusion. The brain MRI image is segmented using SLIC segmentation with super pixel fusion, and the segments are then fed into a trained GoogleNet model for tumor diagnosis.…”

“…Nonetheless, cancer cells from secondary brain tumors have moved from other body parts, including the lung or breast, into the brain. [3], Brain metastasis is the term used to describe the uncontrolled and abnormal development of cells in the brain. Briefs the most prevalent intracranial tumor in adults is brain metastases (BMs), [4] the main symptoms of borderline personality disorder (BTs) are changes in mood and personality, difficulty walking, headaches, difficulty speaking, vomiting, and elevated blood pressure.…”