Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
This work addresses domain generalization and uncertainty calibration for brain MRI segmentation, which is crucial for reliable medical imaging applications, though it is incremental as it adapts an existing model.
The paper tackled the problem of domain shift and overconfidence in applying the Segment Anything Model (SAM) to brain MRI segmentation, proposing CalSAM, a lightweight adaptation framework that improved accuracy and calibration, achieving a +7.4% relative improvement in DSC and a -39.5% reduction in ECE on a scanner-shift evaluation.
The Segment Anything Model (SAM) exhibits strong zero-shot performance on natural images but suffers from domain shift and overconfidence when applied to medical volumes. We propose \textbf{CalSAM}, a lightweight adaptation framework that (i) reduces encoder sensitivity to domain shift via a \emph{Feature Fisher Information Penalty} (FIP) computed on 3D feature maps and (ii) penalizes overconfident voxel-wise errors through a \emph{Confidence Misalignment Penalty} (CMP). The combined loss, \(\mathcal{L}_{\mathrm{CalSAM}}\) fine-tunes only the mask decoder while keeping SAM's encoders frozen. On cross-center and scanner-shift evaluations, CalSAM substantially improves accuracy and calibration: e.g., on the BraTS scanner split (Siemens$\to$GE) CalSAM shows a $+7.4\%$ relative improvement in $\mathrm{DSC}$ (80.1\% vs.\ 74.6\%), a $-26.9\%$ reduction in $\mathrm{HD95}$ (4.6 mm vs.\ 6.3 mm), and a $-39.5\%$ reduction in $\mathrm{ECE}$ (5.2\% vs.\ 8.6\%). On ATLAS-C (motion corruptions), CalSAM achieves a $+5.3\%$ relative improvement in $\mathrm{DSC}$ (75.9\%) and a $-32.6\%$ reduction in $\mathrm{ECE}$ (5.8\%). Ablations show FIP and CMP contribute complementary gains ($p<0.01$), and the Fisher penalty incurs a modest $\sim$15\% training-time overhead. CalSAM therefore delivers improved domain generalization and better-calibrated uncertainty estimates for brain MRI segmentation, while retaining the computational benefits of freezing SAM's encoder.