Optimizing Brain Tumor Segmentation with MedNeXt: BraTS 2024 SSA and Pediatrics
Sarim-Hash
Abstract
Identifying key pathological features in brain MRIs is crucial for the long-term survival of glioma patients. However, manual segmentation is time-consuming, requiring expert intervention and is susceptible to human error. Therefore, significant research has been devoted to developing machine learning methods that can accurately segment tumors in 3D multimodal brain MRI scans. Despite their progress, state-of-the-art models are often limited by the data they are trained on, raising concerns about their reliability when applied to diverse populations that may introduce distribution shifts. Such shifts can stem from lower quality MRI technology (e.g., in sub-Saharan Africa) or variations in patient demographics (e.g., children). The BraTS-2024 challenge provides a platform to address these issues. This study presents our methodology for segmenting tumors in the BraTS-2024 SSA and Pediatric Tumors tasks using MedNeXt, comprehensive model ensembling, and thorough postprocessing. Our approach demonstrated strong performance on the unseen validation set, achieving an average Dice Similarity Coefficient (DSC) of 0.896 on the BraTS-2024 SSA dataset and an average DSC of 0.830 on the BraTS Pediatric Tumor dataset. Additionally, our method achieved an average Hausdorff Distance (HD95) of 14.682 on the BraTS-2024 SSA dataset and an average HD95 of 37.508 on the BraTS Pediatric dataset. Our GitHub repository can be accessed here: Project Repository : https://github.com/python-arch/BioMbz-Optimizing-Brain-Tumor-Segmentation-with-MedNeXt-BraTS-2024-SSA-and-Pediatrics
Community
Accurate brain tumor segmentation in MRI scans is critical for glioma patient survival but remains challenging due to the time-intensive nature of manual segmentation and its susceptibility to human error. Machine learning models have shown promise, yet their performance often suffers from dataset biases, limiting their reliability across diverse populations. The BraTS 2024 challenge addresses these issues, particularly in regions with lower-quality MRI technology (e.g., sub-Saharan Africa) and among underrepresented demographics (e.g., pediatric patients). Our approach leverages MedNeXt, model ensembling, and thorough postprocessing, achieving an average Dice Similarity Coefficient (DSC) of 0.896 and a Hausdorff Distance (HD95) of 14.682 on the SSA dataset, and a DSC of 0.830 with an HD95 of 37.508 on the Pediatric dataset. This methodology earned us 3rd place in both the BraTS 2024 Sub-Saharan Africa and Pediatric Tumor challenges, demonstrating the effectiveness of our model in handling distribution shifts and diverse patient populations.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- An Ensemble Approach for Brain Tumor Segmentation and Synthesis (2024)
- Transferring Knowledge from High-Quality to Low-Quality MRI for Adult Glioma Diagnosis (2024)
- A New Logic For Pediatric Brain Tumor Segmentation (2024)
- Segmentation of Pediatric Brain Tumors using a Radiologically informed, Deep Learning Cascade (2024)
- Improved Multi-Task Brain Tumour Segmentation with Synthetic Data Augmentation (2024)
- ICPR 2024 Competition on Multiple Sclerosis Lesion Segmentation -- Methods and Results (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper