Surrogate Supervision for Robust and Generalizable Deformable Image Registration

Yihao Liu, Junyu Chen, Lianrui Zuo, Shuwen Wei, Brian D. Boyd, Carmen Andreescu, Olusola Ajilore, Warren D. Taylor, Aaron Carass, Bennett A. LandmanarXiv 2025 · DOI · arXiv

Introduction

Deformable image registration (DIR) is a fundamental task in medical imaging, involving the spatial alignment of "fixed" and "moving" scans to account for anatomical variations or temporal changes. While deep learning has significantly accelerated DIR, existing models often exhibit brittleness when faced with real-world data. Standard unsupervised similarity losses typically fail if input images contain artifacts (e.g., magnetic field distortions in MRI), vary in modality (CT vs. MRI), or have inconsistent fields of view.

To mitigate these issues, researchers traditionally rely on extensive preprocessing, such as skull-stripping or bias correction. However, this approach creates a dependency: the model's performance becomes tethered to the specific preprocessing pipeline used during training. If applied to raw "in the wild" data, these models frequently fail.

The Surrogate Supervision Framework

The authors propose Surrogate Supervision, a training paradigm that decouples the images perceived by the model from the images used to calculate the training loss. This approach allows models to learn robust features from "messy" data while benefiting from the clarity of "clean" supervision.

Overview of the Surrogate Supervision framework. The network predicts a transformation $\phi$ from raw inputs $(I_f, I_m)$, while the loss is calculated using 'clean' surrogate images $(\tilde{I}_f, \tilde{I}_m)$.

The core mechanism involves three steps:

  1. Input Domain: The neural network receives raw, potentially artifact-laden images ($I_f, I_m$) and predicts a spatial transformation field ($\phi$).
  2. Supervision Domain: Instead of calculating similarity on the raw inputs, the predicted transformation $\phi$ is applied to surrogate images ($\tilde{I}_f, \tilde{I}_m$). These surrogates are versions of the data where anatomical correspondence is easier to define, such as pre-processed images, anatomical label maps, or images of a consistent modality.
  3. Loss Calculation: The similarity loss (e.g., Mean Squared Error or Normalized Cross-Correlation) is computed in the surrogate space.

By backpropagating the gradient from the surrogate loss through the transformation to the network, the model learns to extract features from the raw inputs that are relevant for correct alignment in the clean space. At inference time, the surrogates are no longer needed; the model processes raw images directly with high accuracy.

Experimental Evaluation

The framework was evaluated across three distinct registration challenges:

  • Artifact-Robust Brain MR: Using the REMBRANDT dataset, the authors tested resistance to intensity inhomogeneity (bias fields).
  • Mask-Agnostic Lung CT: Using the NLST dataset, the models were tested on their ability to register lung scans where masks were inconsistently applied (e.g., one image masked, the other not).
  • Multi-modal MR: Using the IXI dataset, the task was to register T2-weighted images to T1-weighted images.

Key Results and Insights

The study utilized three popular architectures: VoxelMorph, TransMorph, and VFA. The results demonstrated that surrogate supervision provides significant gains in robustness and accuracy.

Robustness to Artifacts and Masking

In the Brain MR task, standard models experienced a sharp decline in Dice Similarity Coefficient (DSC) as simulated artifacts increased. In contrast, surrogate-supervised models maintained stable, high performance.

Similarly, in the "Mask-Agnostic" lung registration task, standard models failed when presented with "mixed" masking scenarios (where one image is masked and the other is not). The Target Registration Error (TRE) for standard models spiked from ~0.05mm to over 0.4mm, while surrogate-supervised models remained stable at ~0.07mm.

Mask Agnostic Registration in Lung CT. Surrogate supervision allows the model to ignore inconsistent masking and focus on the underlying anatomy.

Multi-modal Performance

For multi-modal registration (T1 to T2 MRI), surrogate supervision using same-modality surrogates and simple NCC loss outperformed traditional, mathematically complex losses like Mutual Information (MI). For the VFA architecture, surrogate supervision achieved a DSC of 0.776, compared to 0.726 for MI and 0.678 for Correlation Ratio.

Conclusion

Surrogate Supervision offers a "zero-overhead" path to robustness. By treating preprocessing as a "teacher" during training rather than a prerequisite for inference, the model distills the knowledge of complex tools into its own weights. This decoupling ensures that the model remains performant on raw clinical data without requiring additional computational steps during deployment. Future applications could include hybrid imaging (PET/CT) and cross-site image harmonization.

Summary updated

Abstract

Objective: Deep learning-based deformable image registration has achieved strong accuracy, but remains sensitive to variations in input image characteristics such as artifacts, field-of-view mismatch, or modality difference. We aim to develop a general training paradigm that improves the robustness and generalizability of registration networks. Methods: We introduce surrogate supervision, which decouples the input domain from the supervision domain by applying estimated spatial transformations to surrogate images. This allows training on heterogeneous inputs while ensuring supervision is computed in domains where similarity is well defined. We evaluate the framework through three representative applications: artifact-robust brain MR registration, mask-agnostic lung CT registration, and multi-modal MR registration. Results: Across tasks, surrogate supervision demonstrated strong resilience to input variations including inhomogeneity field, inconsistent field-of-view, and modality differences, while maintaining high performance on well-curated data. Conclusions: Surrogate supervision provides a principled framework for training robust and generalizable deep learning-based registration models without increasing complexity. Significance: Surrogate supervision offers a practical pathway to more robust and generalizable medical image registration, enabling broader applicability in diverse biomedical imaging scenarios.
BibTeX
@misc{liu2025surrogate,
  author = {Yihao Liu and Junyu Chen and Lianrui Zuo and Shuwen Wei and Brian D. Boyd and Carmen Andreescu and Olusola Ajilore and Warren D. Taylor and Aaron Carass and Bennett A. Landman},
  title = {{Surrogate Supervision for Robust and Generalizable Deformable Image Registration}},
  year = {2025},
  eprint = {2509.09869},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.09869},
}
Figure