Evaluating SegResNet for single-modality meningioma segmentation on T1 contrast-enhanced MRI on a New Zealand clinical cohort

Abstract

Accurate and automated meningioma segmentation remains a biomedical engineering challenge, particularly when relying on single-modality MRI data. We evaluate SegResNet, a U-Net-based deep learning architecture, for meningioma segmentation using 817 T1 contrast-enhanced (T1CE) magnetic resonance imaging (MRI) images from 282 patients across Auckland, New Zealand. We investigate the effect of incorporating additional images from the 2023 Brain Tumor Segmentation (BraTS) meningioma challenge during training on model performance. The baseline model trained solely on the Auckland dataset achieved 75.67 % mean Dice. Incorporating an additional 200 and 400 BraTS images improved segmentation performance to 77.89 % and 76.73 %, respectively. A separate experiment involving pre-training on BraTS data followed by fine-tuning on Auckland data achieved 75.90 % Dice. Our results suggest that while leveraging external datasets can enhance model robustness, the extent of improvement depends on dataset heterogeneity and alignment with the target domain.

Analysis of a subset of images unaffected by skull-stripping artifacts indicated notably higher segmentation accuracy (up to 84.02 % Dice), highlighting the influence of preprocessing on performance. Evaluations using the 2023 and 2024 BraTS lesion-wise metrics demonstrated the importance of context-appropriate metric selection. Our findings highlight the adaptability of SegResNet to a single-modality T1CE – a widely available sequence in standard clinical protocols – clinical dataset and emphasize how public data integration, careful preprocessing, and task-aligned evaluation can support robust segmentation models for diverse and resource-constrained environments.