analiza aiqbench
This research addresses a critical gap in clinical AI deployment by introducing a calibration method that accounts for specific missing MRI modalities rather than assuming uniform difficulty reductions. By adapting confidence estimates to the exact combination of available data, the proposed approach enhances the reliability of brain tumor segmentation models under real-world protocol heterogeneity. The work advances trustworthy machine learning in medical imaging through precise uncertainty quantification tailored to modality-specific challenges.
Missing Modality-Aware Calibration for Trustworthy Brain Tumor Segmentation
arXiv:2610.11419v1 Announce Type: cross Abstract: Multimodal brain tumor segmentation typically leverages multiple MRI modalities, yet incomplete modality acquisition is common in clinical practice due to protocol heterogeneity and scan failures. Although recent methods maintain segmentation accuracy under missing modality conditions, they frequently overlook prediction reliability, leading to miscalibrated confidence estimates that hinder clinical adoption. Existing calibration techniques are largely modality-agnostic or assume that prediction difficulty decreases monotonically as additional modalities become available. However, in brain tumor segmentation, prediction difficulty depends primarily on which modalities are absent rather than how many, leading to combination-specific and spatially heterogeneous calibration errors. To address this, we propose Missing Modality-Aware Local Temperature Scaling (MMA-LTS), a post-hoc voxel-wise confidence calibration method. It estimates a spatially adaptive temperature field conditioned on a modality-availability learnable token and a voxel-wise difficulty score. Experiments on BraTS 2020 and FeTS 2024 show that MMA-LTS improves calibration while preserving the segmentation accuracy of state-of-the-art models across diverse missing-modality scenarios, thereby enhancing trustworthiness toward clinical deployment.
Abstract:Multimodal brain tumor segmentation typically leverages multiple MRI modalities, yet incomplete modality acquisition is common in clinical practice due to protocol heterogeneity and scan failures. Although recent methods maintain segmentation accuracy under missing modality conditions, they frequently overlook prediction reliability, leading to miscalibrated confidence estimates that hinder clinical adoption. Existing calibration techniques are largely modality-agnostic or assume that prediction difficulty decreases monotonically as additional modalities become available. However, in brain tumor segmentation, prediction difficulty depends primarily on which modalities are absent rather than how many, leading to combination-specific and spatially heterogeneous calibration errors. To address this, we propose Missing Modality-Aware Local Temperature Scaling (MMA-LTS), a post-hoc voxel-wise confidence calibration method. It estimates a spatially adaptive temperature field conditioned on a modality-availability learnable token and a voxel-wise difficulty score. Experiments on BraTS 2020 and FeTS 2024 show that MMA-LTS improves calibration while preserving the segmentation accuracy of state-of-the-art models across diverse missing-modality scenarios, thereby enhancing trustworthiness toward clinical deployment.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.11419 [cs.CV]
(or arXiv:2610.11419v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.11419 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 258 cuvinte
Subiecte conexe
Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation
arXiv · 28 iul. 2026
Towards Trustworthy AI for Glioma Diagnosis: A Task-Aware Evaluation of Uncertainty Quantification
arXiv · 1 oct. 2026
Biomedical Imaging's Real Bottleneck Is the Data, Not the Model
Databricks · 8 oct. 2026
Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesion Segmentation
arXiv · 5 aug. 2026