- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes VOLT, a 3D medical foundation model for learning discrete volumetric representations from medical scans. The method uses a two-stage training strategy: Stage-1 combines Depth Shuffle pretraining with Additive Binary Spherical Quantization (ABSQ), while Stage-2 introduces patch consistency matching and semantic distillation from a frozen vision-language teacher. The authors pretrain VOLT on 73,648 CT and MRI volumes and evaluate it on reconstruction, synthesis, segmentation, classification, VQA, and report generation. The results show improvements over several existing medical tokenizers across these tasks.
Critical strengths
-
Learning high-quality 3D representations from medical volumes is challenging due to volumetric anisotropy and limited paired scan-text data. The proposed framework is relevant to both medical image understanding and generation.
-
VOLT achieves substantial improvements in reconstruction quality, particularly PSNR and SSIM. The evaluation also covers several downstream tasks, which helps demonstrate the usefulness of the learned representations beyond reconstruction.
Critical weaknesses
-
Depth Shuffle is closely related to existing reconstruction-based pretraining strategies, while ABSQ extends binary spherical quantization using additive residual refinement. Stage-2 also relies on relatively standard contrastive learning and knowledge distillation objectives. Although their combination is effective, I find the methodological novelty somewhat limited.
-
The paper reports better reconstruction quality than VQ, BSQ, LFQ, and RVQ. However, it does not clearly compare these methods under matched bitrates or discrete representation capacities.
-
VOLT is initialized from a pretrained WAN2.2 VAE and uses a frozen M3D-CLIP teacher during Stage-2. While the authors acknowledge that the teacher has been trained using paired scan-text data, this makes it difficult to isolate the contribution of the proposed scan-only objectives from that of existing pretrained models.
Questions for authors
-
Can the authors clarify the main technical novelty of ABSQ compared with existing residual quantization methods? How does ABSQ perform against BSQ, LFQ, and RVQ when the bitrate and representation capacity are matched?
-
How much of VOLT's improvement comes from the WAN2.2 initialization and the pretrained M3D-CLIP teacher? Could the authors provide a controlled comparison using the same pretrained backbone without the proposed objectives?
-
Since M3D-CLIP provides semantic supervision and M3D benchmarks are used for downstream evaluation, can the authors clarify how potential overlap between the teacher's training data and downstream evaluation data is handled?