NeuroWeave-3D: Uncertainty-Aware Evidence Completion for Brain Tumor Segmentation with Missing MRI Modalities
- 1German Research Center for Artificial Intelligence (DFKI)
Abstract
Multi-parametric MRI segmentation models are accurate when all prescribed sequences are available but can be brittle under missing or corrupted modalities. We propose NeuroWeave-3D, a 3D glioma segmentation framework that treats missing modalities as uncertain evidence rather than deterministic channels to reconstruct. The model combines spatial modality routing, probabilistic latent feature completion, complete-to-missing consistency, and voxel-level uncertainty estimation. A curriculum over all non-empty MRI modality subsets trains one network for arbitrary sequence availability. We define a BraTS-centered evaluation that reports complete-input accuracy, macro and worst-case missing-modality performance, corruption robustness, calibration, and failure detection.
Related
- UAMP: Consistent video object segmentation with uncertainty-aware memory propagation
- From ecDNA structure to tumor immune escape and therapeutic resistance: evidence, uncertainty, and clinical priorities
- Evidence and Uncertainty in the Future Pathways of Insects Under Global Change
- Neural effects of expectation violation generalise across sensory modalities
- A comprehensive physiological dataset of pain and aversive modalities for pain biomarkers research
BibTeX
@misc{miller2026neuroweave3d,
title = {{NeuroWeave-3D: Uncertainty-Aware Evidence Completion for Brain Tumor Segmentation with Missing MRI Modalities}},
author = {D. Miller and L. A. Weber},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.29.762804},
url = {https://www.biorxiv.org/content/10.64898/2026.10.29.762804v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - NeuroWeave-3D: Uncertainty-Aware Evidence Completion for Brain Tumor Segmentation with Missing MRI Modalities
AU - D. Miller
AU - L. A. Weber
PY - 2026
DA - 2026/10/29
PB - bioRxiv
DO - 10.64898/2026.10.29.762804
UR - https://www.biorxiv.org/content/10.64898/2026.10.29.762804v1
AB - Multi-parametric MRI segmentation models are accurate when all prescribed sequences are available but can be brittle under missing or corrupted modalities. We propose NeuroWeave-3D, a 3D glioma segmentation framework that treats missing modalities as uncertain evidence rather than deterministic channels to reconstruct. The model combines spatial modality routing, probabilistic latent feature completion, complete-to-missing consistency, and voxel-level uncertainty estimation. A curriculum over all non-empty MRI modality subsets trains one network for arbitrary sequence availability. We define a BraTS-centered evaluation that reports complete-input accuracy, macro and worst-case missing-modality performance, corruption robustness, calibration, and failure detection.
ER -