A Review of U-Net Based Deep Learning Frameworks for MRI-Based Brain Tumor Segmentation

TL;DR

This paper reviews U-Net-based deep learning models for segmenting brain tumors in MRI images, analyzing their evolution and effectiveness from 2019 to 2025.

Contribution

A comprehensive review of 35 U-Net-based studies for brain tumor segmentation, highlighting architectural advancements and challenges.

Findings

U-Net variants have evolved from 2D and 3D models to more advanced architectures for improved segmentation.

Benchmark datasets like BRATS are used to evaluate and compare model performance consistently.

Key challenges include improving model efficiency, generalization, and integrating multimodal data for clinical use.

Abstract

Automated segmentation of brain tumors from Magnetic Resonance Imaging (MRI) images is helpful for clinical diagnosis, surgical planning, and post-treatment monitoring. In recent years, the U-Net architecture has been observed as one of the most popular solutions among deep learning models. This article presents a review of 35 studies published between 2019 and 2025 focusing on U-Net-based brain tumor segmentation. The primary focus of this review is an in-depth analysis of commonly used U-Net architectures. The transformation of original 2D and 3D models into more advanced variants is examined in detail. Results from a wide range of studies are synthesized, and standard evaluation criteria are summarized along with benchmark datasets such as the BRATS competition to validate the effectiveness of these models. Additionally, the paper overviews the recent developments in the field, determines fundamental challenges, and provides insight into future directions, including improving model efficiency and generalization, combining multimodal data, and advancing clinical applications. This review serves as a guide for researchers to examine the impact of the U-Net architecture on brain tumor segmentation.

Figures