A review of deep learning models (U-Net architectures) for segmenting brain tumors

Abstract

Highly accurate tumor segmentation and classification are required to treat the brain tumor appropriately. Brain tumor segmentation (BTS) approaches can be categorized into manual, semi-automated, and full-automated. The deep learning (DL) approach has been broadly deployed to automate tumor segmentation in therapy, treatment planning, and diagnosing evaluation. It is mainly based on the U-Net model that has recently attained state-of-the-art performances for multimodal BTS. This paper demonstrates a literature review for BTS using U-Net models. Additionally, it represents a common way to design a novel U-Net model for segmenting brain tumors. The steps of this DL way are described to obtain the required model. They include gathering the dataset, pre-processing, augmenting the images (optional), designing/selecting the model architecture, and applying transfer learning (optional). The model architecture and the performance accuracy are the two most important metrics used to review the works of literature. This review concluded that the model accuracy is proportional to its architectural complexity, and the future challenge is to obtain higher accuracy with low-complexity architecture. Challenges, alternatives, and future trends are also presented.