Improving skull-stripping for infant MRI via weakly supervised domain adaptation using adversarial learning.
Authors
Affiliations (6)
Affiliations (6)
- Electrical and Software Engineering, University of Calgary, Calgary AB, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary AB, Canada. Electronic address: [email protected].
- Electrical and Software Engineering, University of Calgary, Calgary AB, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary AB, Canada. Electronic address: [email protected].
- Electrical and Software Engineering, University of Calgary, Calgary AB, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary AB, Canada. Electronic address: [email protected].
- Alberta Children's Hospital Research Institute, Calgary AB, Canada; Department of Pediatrics, Section of Neonatology, University of Calgary, Calgary AB, Canada. Electronic address: [email protected].
- Hotchkiss Brain Institute, University of Calgary, Calgary AB, Canada; Alberta Children's Hospital Research Institute, Calgary AB, Canada; Department of Pediatrics, Section of Neonatology, University of Calgary, Calgary AB, Canada. Electronic address: [email protected].
- Electrical and Software Engineering, University of Calgary, Calgary AB, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary AB, Canada. Electronic address: [email protected].
Abstract
Skull-stripping is an essential preprocessing step in the analysis of brain Magnetic Resonance Imaging (MRI). While deep learning-based methods have shown success with this task, strong domain shifts between adult and newborn brain MR images complicate model transferability. We previously developed unsupervised domain adaptation techniques to address the domain shift between these data, without requiring newborn MRI data to be labeled. In this work, we build upon our previous domain adaptation framework by extensively expanding the training and validation datasets using weakly labeled newborn MRI scans from the Developing Human Connectome Project (dHCP), our private newborn dataset, and synthetic data generated by a Gaussian Mixture Model (GMM). While the core model architecture remains similar, we focus on validating the model's generalization across four diverse domains, adult, synthetic, public newborn, and private newborn MRI, demonstrating improved performance and robustness over our prior methods. These results highlight the impact of incorporating broader training data under weak supervision for newborn brain imaging analysis. The experimental results reveal that our proposed approach outperforms our previous work achieving a Dice coefficient of 0.9509±0.0055 and a Hausdorff distance of 3.0883±0.1833 for newborn MRI data, surpassing state-of-the-art models such as SynthStrip (Dice =0.9412±0.0063, Hausdorff =3.1570±0.1389). These results reveal that including weakly labeled newborn data results in improvements in model performance and generalization and is useful for newborn brain imaging analysis. Our code is available at: https://github.com/abbasomidi77/Weakly-Supervised-DAUnet.