Efficient Meningioma Tumor Segmentation Using Ensemble Learning

TL;DR

This paper introduces an ensemble deep learning approach for meningioma tumor segmentation in MRI scans, achieving high accuracy with reduced training time, making it accessible for limited hardware environments.

Contribution

The study presents a novel ensemble of three diverse architectures that improves segmentation robustness and accuracy while significantly reducing training requirements.

Findings

Achieved Lesion-Wise Dice scores of 77.30%, 76.37%, and 73.9% for ET, TC, and WT respectively.

Ensemble models trained with only 20 epochs outperform some existing methods.

Demonstrated effectiveness of ensemble learning under hardware constraints.

Abstract

Meningiomas represent the most prevalent form of primary brain tumors, comprising nearly one-third of all diagnosed cases. Accurate delineation of these tumors from MRI scans is crucial for guiding treatment strategies, yet remains a challenging and time-consuming task in clinical practice. Recent developments in deep learning have accelerated progress in automated tumor segmentation; however, many advanced techniques are hindered by heavy computational demands and long training schedules, making them less accessible for researchers and clinicians working with limited hardware. In this work, we propose a novel ensemble-based segmentation approach that combines three distinct architectures: (1) a baseline SegResNet model, (2) an attention-augmented SegResNet with concatenative skip connections, and (3) a dual-decoder U-Net enhanced with attention-gated skip connections (DDUNet). The ensemble aims to leverage architectural diversity to improve robustness and accuracy while significantly reducing training demands. Each baseline model was trained for only 20 epochs and Evaluated on the BraTS-MEN 2025 dataset. The proposed ensemble model achieved competitive performance, with average Lesion-Wise Dice scores of 77.30%, 76.37% and 73.9% on test dataset for Enhancing Tumor (ET), Tumor Core (TC) and Whole Tumor (WT) respectively. These results highlight the effectiveness of ensemble learning for brain tumor segmentation, even under limited hardware constraints. Our proposed method provides a practical and accessible tool for aiding the diagnosis of meningioma, with potential impact in both clinical and research settings.