Magnetic Resonance Imaging Feature-Based Subtyping and Model Ensemble for Enhanced Brain Tumor Segmentation

TL;DR

This paper presents a deep learning ensemble approach utilizing MRI-based radiomic features for improved brain tumor segmentation across diverse tumor types in the BraTS 2024 challenge, achieving high accuracy and generalizability.

Contribution

It introduces an innovative ensemble model with adaptive pre- and post-processing techniques that incorporate radiomic analyses for better tumor subtype differentiation.

Findings

Achieved lesion-wise Dice scores of 0.926, 0.801, and 0.688 for different tumor types.

Enhanced segmentation accuracy and robustness across heterogeneous brain tumor datasets.

Provided open-source code and web application for reproducibility and clinical use.

Abstract

Accurate and automatic segmentation of brain tumors in multi-parametric magnetic resonance imaging (mpMRI) is essential for quantitative measurements, which play an increasingly important role in clinical diagnosis and prognosis. The International Brain Tumor Segmentation (BraTS) Challenge 2024 offers a unique benchmarking opportunity, including various types of brain tumors in both adult and pediatric populations, such as pediatric brain tumors (PED), meningiomas (MEN-RT) and brain metastases (MET), among others. Compared to previous editions, BraTS 2024 has implemented changes to substantially increase clinical relevance, such as refined tumor regions for evaluation. We propose a deep learning-based ensemble approach that integrates state-of-the-art segmentation models. Additionally, we introduce innovative, adaptive pre- and post-processing techniques that employ MRI-based radiomic analyses to differentiate tumor subtypes. Given the heterogeneous nature of the tumors present in the BraTS datasets, this approach enhances the precision and generalizability of segmentation models. On the final testing sets, our method achieved mean lesion-wise Dice similarity coefficients of 0.926, 0.801, and 0.688 for the whole tumor in PED, MEN-RT, and MET, respectively. These results demonstrate the effectiveness of our approach in improving segmentation performance and generalizability for various brain tumor types. The source code of our implementation is available at https://github.com/Precision-Medical-Imaging-Group/HOPE-Segmenter-Kids. Additionally, an open-source web-application is accessible at https://segmenter.hope4kids.io/ which uses the docker container aparida12/brats-peds-2024:v20240913 .