- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes MVR, a method for using 2D foundation models with 3D brain MRI data. Instead of processing MRI slices separately, the method first reduces the 3D volume into a smaller set of 2D images using PCA and multiscale information. These images are then passed through a frozen DINOv3 model.
The authors evaluate the method on ADNI, OASIS, and ABIDE, with an additional test on AIBL. The results are generally better than the selected baselines, especially when the foundation model is frozen.
Critical strengths
-
The main idea is simple and practical. Reducing the MRI volume before passing it to a 2D foundation model is an interesting alternative to processing individual slices. The method also does not require additional training of the foundation model.
-
The experiments cover multiple datasets and include external validation on AIBL. I also like the ablation studies, which show that both the multiscale information and the detail components help improve performance.
Critical weaknesses
-
My main concern is that the method is tested with only one 2D foundation model, DINOv3. Since the paper proposes a general approach for 2D foundation models, it is not clear whether the same improvements would be seen with other models. Also, most parts of the method are based on existing techniques such as PCA and Gaussian smoothing, so the methodological novelty seems somewhat limited.
-
Some improvements over the baselines are quite small. For example, on ABIDE, MVR achieves an AUC of 66.02, compared to 65.99 for uniform slice sampling. The paper does not provide statistical tests to show whether these differences are significant. The computational cost is also not fully evaluated, although efficiency is one of the motivations for the method.
Questions for authors
-
Have the authors tested MVR with other 2D foundation models, such as DINOv2 or a medical imaging model? I think this would help show whether the method works well beyond DINOv3.
-
Can the authors provide statistical significance tests for the main comparisons? Also, how much inference time and GPU memory does MVR require compared to the other methods? This would help better understand the practical benefits of reducing the volume before encoding.
4 comments
Statistical Uncertainty
As suggested, we conducted a paired, class-stratified bootstrap analysis with 5,000 iterations to measure two-sided 95% confidence intervals for AUC differences, similar to RAPTOR (An et al., 2025).
Compared to second-best methods The paired comparisons with second-best methods below provide additional statistical evidence for MVR’s AUC improvements. It shows the performance superiority is statistically significant in 6 of 7 comparisons based on 95% CIs across four datasets. Specifically, on ADNI, OASIS, and the out-of-distribution AIBL evaluation, MVR achieves positive AUC differences over the evaluated competitive methods, with all differences being statistically significant. On ABIDE, the difference relative to uniform slice sampling remains inconclusive. However, MVR achieves substantially higher mean AUC than uniform slice sampling on ADNI, OASIS, and AIBL, with improvements of 7.98%, 8.15%, and 9.32%. Overall, these results support the generally favorable performance of our method.
| Dataset | MVR vs. Baseline | ΔAUC | AUC 95% CI |
|---|---|---|---|
| ADNI | MVR vs. MedicalNet | +2.25 | [0.33, 4.29] |
| ADNI | MVR vs. 3DINO | +2.89 | [0.92, 4.96] |
| OASIS | MVR vs. MedicalNet | +1.95 | [0.15, 3.58] |
| OASIS | MVR vs. Eigenslices | +1.37 | [0.02, 2.83] |
| AIBL | MVR vs. MedicalNet | +1.06 | [0.03, 2.21] |
| AIBL | MVR vs. 3DINO | +3.54 | [0.12, 7.04] |
| ABIDE | MVR vs. Uniform slice sampling | +0.03 | [−1.56, 1.54] |
Statical significance in Ablation study As shown below, removing the "detail components" consistently reduces AUC across all three datasets, with all three CIs positive difference. Removing "Gaussian scale space" also reduces AUC across datasets, with two of three CIs showing statisticslly significant improvement. Overall, These results provide additional statistical support for the contributions of the proposed multiscale construction and residual detail components.
| Dataset | MVR vs. Ablation Variant | ΔAUC | AUC 95% CI |
|---|---|---|---|
| ADNI | MVR vs. w/o Gaussian scale space | +1.84 | [0.41, 3.11] |
| ADNI | MVR vs. w/o detail components | +3.41 | [1.72, 5.13] |
| OASIS | MVR vs. w/o Gaussian scale space | +0.91 | [−0.36, 2.21] |
| OASIS | MVR vs. w/o detail components | +3.01 | [0.95, 5.15] |
| ABIDE | MVR vs. w/o Gaussian scale space | +2.64 | [0.76, 4.90] |
| ABIDE | MVR vs. w/o detail components | +4.49 | [2.02, 6.83] |
Inference Efficiency
We measured inference efficiency on ADNI using the same NVIDIA H200 GPU for compared methods.
Our MVR achieves the highest inference speed while achieving best AUC. Our MVR is approximately twice as fast as Eigenslices, 54 times as fast as RAPTOR, and 1.4 times as fast as AnyMC3D. Although MVR requires slightly higher peak GPU memory, it is affordable even with a consumer PC.
| Method | Volumes/s | Peak VRAM (GB) | AUC (%) | BAcc (%) |
|---|---|---|---|---|
| Eigenslices | 3.11 | 1.19 | 84.97 ± 2.27 | 76.89 ± 3.43 |
| RAPTOR (DINOv3) | 0.11 | 1.19 | 84.93 ± 1.96 | 77.62 ± 4.32 |
| AnyMC3D | 4.39 | 1.295 | 84.45 ± 2.93 | 76.90 ± 3.81 |
| MVR | 6.14 | 2.70 | 88.85 ± 1.22 | 80.92 ± 1.02 |
Score Update After Author Rebuttal
The authors' responses addressed some of my concerns, but my main concern about the novelty of the basis and details remains. Nevertheless, I think this is a good paper, and I have raised my score to 3.
We thank the reviewer for their constructive feedback and for reconsidering the assessment. We appreciate the positive evaluation of our work. We will further clarify the technical contributions and incorporate the additional experimental evidence into the revised manuscript.
We thank the reviewer for the constructive feedback.
Generalization Across 2D Foundation Models
As suggested, we additionally evaluated MVR using a frozen DINOv2 encoder on ADNI. The results are presented below. Our MVR achieves the highest AUC and BAcc, outperforming strong second-best RAPTOR, AnyMC3D, and Eigenslices. In particular, MVR exceeds Eigenslices by 3.51% AUC and 2.86% BAcc under matched encoder and downstream classification settings.
Novelty of MVR
Our MVR is a carefully designed method rather than a trivial combination of existing techniques.
1. Novel volumetric reduction design. Our volumetric reduction goes beyond conventional PCA-based methods such as Eigenslices. Specifically, we first construct descriptors that combine through-plane information with in-plane spatial variation at multiscales, providing a diverse information basis for reduction. Second, we design a base-and-detail construction scheme that separates a dominant intensity-based reference from complementary residual multiscale variation, enabling the detail components to capture variation not linearly explained by the base reference. These designs create a new representation space in which PCA is performed and allow complementary information to be allocated across the reduced components. Its superiority has been demonstrated by the favorable performance improvements across ADNI, OASIS, ABIDE and AIBL datasets shown in Tables 1 and 2.
2. New architecture level design. Existing approaches that utilize forzen 2D foundation models, such as RAPTOR and AnyMC3D, primarily incorporate cross-slice information after independently encoding each slice using 2D foundation models, which may lose structure infomation across slices. Our MVR instead constructs volume-informed inputs before sending to 2D foundation models, preseving information across slices. The experimental results in both the main paper and the rebutall demonstrate this is a promising architecture worthing further exploration in the future.
Our additional experiments below on AdrenalMNIST3D (abdominal CT) and VesselMNIST3D (brain MRA) (Yang et al., 2023) further demonstrate the superiority of MVR for adapting frozen 2D foundation models to medical volumes beyond brain MRI.