Advanced Tumor Segmentation in Medical Imaging: An Ensemble Approach for BraTS 2023 Adult Glioma and Pediatric Tumor Tasks

TL;DR

This study outlines the methodology for segmenting tumors in the context of two distinct tasks from the BraTS 2023 challenge, and leverages two encoder-decoder-based CNN models, namely SegResNet and MedNeXt, for segmenting three distinct subregions of tumors.

Abstract

Automated segmentation proves to be a valuable tool in precisely detecting tumors within medical images. The accurate identification and segmentation of tumor types hold paramount importance in diagnosing, monitoring, and treating highly fatal brain tumors. The BraTS challenge serves as a platform for researchers to tackle this issue by participating in open challenges focused on tumor segmentation. This study outlines our methodology for segmenting tumors in the context of two distinct tasks from the BraTS 2023 challenge: Adult Glioma and Pediatric Tumors. Our approach leverages two encoder-decoder-based CNN models, namely SegResNet and MedNeXt, for segmenting three distinct subregions of tumors. We further introduce a set of robust postprocessing to improve the segmentation, especially for the newly introduced BraTS 2023 metrics. The specifics of our approach and comprehensive performance analyses are expounded upon in this work. Our proposed approach achieves third place in the BraTS 2023 Adult Glioma Segmentation Challenges with an average of 0.8313 and 36.38 Dice and HD95 scores on the test set, respectively.

Figures (4)

• Figure 1: The MedNeXt network roy2023mednext.
• Figure 2: The SegResNet network myronenko20193d.
• Figure 3: The figure shows the qualitative results for the adult-glioma task on the validation sample for three cases.
• Figure 4: The figure shows the qualitative results for the pediatric task on the validation sample for the best-performing model.