- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
Paper Summary: The paper proposes Recurrent Amortized Solver (RAS) designed to enable step-wise regularization control during unrolled, iterative medical image registration. The network (LapIRN) is conditioned on both a step index and the regularization weight allowing users to vary the regularization schedule at inference time without retraining the model. The evaluation is performed across 3 benchmarks, well known in the registration community. Moreover, the authors report improved accuracy-regularity Pareto fronts compared to single-pass baselines (VoxelMorph and single-pass LapIRN) and they also propose a label-free per-case selection rule that enforces a per-pair folding limit, together with a “per-case Pareto” view of evaluation.
Critical strengths
- The paper introduces a conditioning mechanism and unrolled optimization allowing learning based registration to get best of both worlds, namely iterative optimization and controlling the regularization weight at run-time.
- Although per-case Pareto selection is not novel in itself, I appreciate that the paper reintroduces it: it is relevant to clinical practice, yet the registration community has largely neglected it.
- I appreciate the length of the experiments and results and the further results in the appendix.
Critical weaknesses
- Although I know that it is very common to compare single and multi-resolution models, I find this slightly unfair. I would appreciate very much to compare, e.g., single resolution models Voxelmorph, vs Hypermorph, vs RAS on Voxelmorph. This would allow us to dissentangle whether the benefit comes from the multi-resolution, the reg weight conditioning or the proposed method.
- In the same direction, I believe that the paper should perform statistical testing on the results of Table 1 since some of the reported differences might not be significant. Going beyond the performance in saturated benchmarks and discussing honestly the results and the methods would only benefit the field. I do not believe that we always need to have this bold line at the end of the table for a paper to have significant contribution.
- It would be nice to have a table that shows training time, test time, encoder parameters, and network parameters in total. Iterative optimization methods should also be included. This would help assess when and how each method can be used. Larger encoders (more parameters), see for example the comparison between Transmorph and Voxelmorph, help improve the performance, making the comparison a bit unfair again.
- Although the paper has extensive baselines for the brain datasets, the best performing methods on NLST on Learn2Reg are missing, e.g., Convex Adam[1].
- Results on standard Learn2Reg setups (the 128³ resampled OASIS is not comparable to published numbers).
- The continuation motivation (large λ early, small λ late) conflicts with the results: the best NLST schedule increases λ, and decreasing schedules hurt on OASIS. The claim that one-step models generalize poorly is also not supported by any experiments.
[1] Siebert H, Großbröhmer C, Hansen L, Heinrich MP. Convexadam: Self-configuring dual-optimization-based 3d multitask medical image registration. IEEE Transactions on Medical Imaging. 2024 Sep 16;44(2):738-48.
Questions for authors
- Can the authors run a single-scale unrolled model (e.g. VoxelMorph RAS)? This would cleanly isolate the effect of recurrent -scheduling without the confounding benefits of a multi-resolution pyramid.
- Can the authors include a table that shows training time, test time, encoder parameters, and network parameters in total? Iterative optimization methods should also be included.
- Given that a simple 2-pass execution of standard LapIRN (Appendix B.5) achieves comparable Dice, what is the practical justification for the added complexity of training unrolled, step-wise lambda conditioned hypernetworks? Can you please revise the limitation sections to report any further limitations that were omitted during the submission?
- Can the authors provide paired Wilcoxon signed-rank tests across all entries in Table 1 to confirm whether the minor accuracy gains are statistically significant?
- How does RAS compare on NLST against classical Learn2Reg methods like ConvexAdam[1]?