Fully Automated Tumor Segmentation for Brain MRI data using Multiplanner UNet

TL;DR

This paper evaluates the Multi-Planner U-Net (MPUnet) for automated brain tumor segmentation across diverse pediatric and adult datasets, highlighting its potential and current limitations in accuracy and robustness.

Contribution

The study introduces and assesses the MPUnet architecture that leverages multi-planar information for improved tumor segmentation in MRI data.

Findings

Higher accuracy in tumor core segmentation

Variable performance across different tumor regions

Potential for further model refinement and data inclusion

Abstract

Automated segmentation of distinct tumor regions is critical for accurate diagnosis and treatment planning in pediatric brain tumors. This study evaluates the efficacy of the Multi-Planner U-Net (MPUnet) approach in segmenting different tumor subregions across three challenging datasets: Pediatrics Tumor Challenge (PED), Brain Metastasis Challenge (MET), and Sub-Sahara-Africa Adult Glioma (SSA). These datasets represent diverse scenarios and anatomical variations, making them suitable for assessing the robustness and generalization capabilities of the MPUnet model. By utilizing multi-planar information, the MPUnet architecture aims to enhance segmentation accuracy. Our results show varying performance levels across the evaluated challenges, with the tumor core (TC) class demonstrating relatively higher segmentation accuracy. However, variability is observed in the segmentation of other classes, such as the edema and enhancing tumor (ET) regions. These findings emphasize the complexity of brain tumor segmentation and highlight the potential for further refinement of the MPUnet approach and inclusion of MRI more data and preprocessing.