Data-centric strategies enable cross-center generalization of convolutional neural networks for CT brain extraction.

Background: To determine if a small number of annotated scans can enable clinically meaningful adaptation of a pre-trained convolutional neural network across different centers. Using non-contrast head CT brain extraction as the test case, we also sought to identify the factors contributing to performance drops when applying models to new sites. Materials and methods: Non-contrast head CT scans were used in this study, from two separate institutions (Center A: 595 scans; Center B: 486 scans). A public pre-trained U-Net model for brain tissue extraction was first evaluated on Center A dataset as a baseline. The model was then fine-tuned incrementally using stratified subsets of annotated scans (5, 15, 25, and 75). The pre-trained model was subsequently transferred to Center B dataset and adapted through the same incremental fine-tuning strategy. The primary metric of interest was the three-dimensional Dice similarity coefficient (DSC), with a pre-defined minimal important difference (MID) set at 0.01. To identify predictors of baseline DSC and fine-tuning gain driving cross-center performance degradation, variance inflation factor (VIF) screening and logit Gaussian linear models (GLMs) were applied, with SHapley Additive exPlanations (SHAP) analysis providing qualitative feature importance rankings. Results: At center A, the pre-trained model achieved a DSC of 0.9634 ± 0.0151. Fine-tuning with five annotated scans raised DSC to 0.9784 ± 0.0070 ( Conclusion: For NCCT brain extraction assessed across two centers, fine-tuning a publicly pre-trained CNN using five local annotated scans can generate clinically valuable cross-center segmentation gains; slice thickness heterogeneity appears to be the dominant source of inter-center domain shift.