Model Ensemble for Brain Tumor Segmentation in Magnetic Resonance Imaging

TL;DR

This paper introduces an ensemble deep learning approach combining nnU-Net and Swin UNETR models with post-processing for improved brain tumor segmentation across multiple tumor types, achieving top rankings in the BraTS challenge.

Contribution

The paper presents a novel ensemble strategy with targeted post-processing for brain tumor segmentation, demonstrating superior performance on new tumor cases in multiple tasks.

Findings

Achieved high lesion-wise Dice scores for pediatric tumors, meningiomas, and metastases.

Ranked first in pediatric tumor segmentation, third in meningioma, and fourth in metastases tasks.

Effective region-wise ensembling and threshold-based post-processing improve segmentation accuracy.

Abstract

Segmenting brain tumors in multi-parametric magnetic resonance imaging enables performing quantitative analysis in support of clinical trials and personalized patient care. This analysis provides the potential to impact clinical decision-making processes, including diagnosis and prognosis. In 2023, the well-established Brain Tumor Segmentation (BraTS) challenge presented a substantial expansion with eight tasks and 4,500 brain tumor cases. In this paper, we present a deep learning-based ensemble strategy that is evaluated for newly included tumor cases in three tasks: pediatric brain tumors (PED), intracranial meningioma (MEN), and brain metastases (MET). In particular, we ensemble outputs from state-of-the-art nnU-Net and Swin UNETR models on a region-wise basis. Furthermore, we implemented a targeted post-processing strategy based on a cross-validated threshold search to improve the segmentation results for tumor sub-regions. The evaluation of our proposed method on unseen test cases for the three tasks resulted in lesion-wise Dice scores for PED: 0.653, 0.809, 0.826; MEN: 0.876, 0.867, 0.849; and MET: 0.555, 0.6, 0.58; for the enhancing tumor, tumor core, and whole tumor, respectively. Our method was ranked first for PED, third for MEN, and fourth for MET, respectively.