A brain tumor is a deformity in the tissue where cells divide promptly and uncontrollably. As a consequence, the tumor expands. It is hypothesized that a neural network can successfully identify and predict brain tumors, two of the most challenging medical problems now facing doctors. The abundance of information enhances the diagnostic potential of magnetic resonance imaging (MRI) which provides the anatomical features of brain tumors. To improve the efficiency of the semantic segmentation architecture, we introduce a novel transformer-based attention U-shaped network called TransAttU-Net, in which the multilevel guided attention and multiscale skip connection operate simultaneously and which is also used to extract the pixel on the tumor area. Initially, the input image data are altered and undergo further processing using various preprocessing techniques. Methods such as these can be used to resize or rescale features, data augmentation, reverse or flip data, and alter the orientation of data. These procedures are required before sending data to the TransAttU-Net deep learning (DL) model. The algorithm attained a degree of accuracy on the BraTS 2019, i.e., the dataset provided in multimodal brain tumor image segmentation challenge and BraTS 2020 dataset, indicating great performance on BraTS 2020 dataset. The performance metrics of the models are evaluated using and results are discussed in this article.