# 3D MRI Image Pretraining via Controllable 2D Slice Navigation Task

arXiv: https://arxiv.org/abs/2605.06487 · HTML: https://mlsanity.com/paper/2605.06487/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 16 of 16)

- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [Training Agents Inside of Scalable World Models](https://mlsanity.com/paper/2509.24527/) (2025)
- [On the Challenges and Perspectives of Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2306.05705/) (2023)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction](https://mlsanity.com/paper/1907.02757/) (2019)
- [LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching](https://mlsanity.com/paper/2306.11925/) (2023)
- [Revisiting MAE pre-training for 3D medical image segmentation](https://mlsanity.com/paper/2410.23132/) (2024)
- [Deep reinforcement learning in medical imaging: A literature review](https://mlsanity.com/paper/2103.05115/) (2021)
- [Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning](https://mlsanity.com/paper/2506.02327/) (2025)
- [A generalizable 3D framework and model for self-supervised learning in medical imaging](https://mlsanity.com/paper/2501.11755/) (2025)
- [CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning](https://mlsanity.com/paper/2504.13820/) (2025)
- [Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes](https://mlsanity.com/paper/2403.16499/) (2024)
- [Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model](https://mlsanity.com/paper/2406.13165/) (2024)
- [From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models](https://mlsanity.com/paper/2506.07280/) (2025)

## Abstract (arXiv)

Self-supervised pretraining has become the mainstream approach for learning MRI representations from unlabeled scans. However, most existing objectives still treat each scan primarily as static aggregations of slices, patches or volumes. We ask whether there exists an intrinsic form of self-supervision signal that is different from reconstructing the masked patches, through transforming the 3D volumes into controllable 2D rendered sequences: by rendering slices at continuous positions, orientations, and scales, a 3D volume can be converted into dense video-action sequences whose controls are the action trajectories. We study this formulation with an action-conditioned pretraining objective, where a tokenizer encodes slice observations and a latent dynamics model predicts the evolution of latent features. Across representative anatomical and spatial downstream tasks, the proposed pretraining is evaluated against standard static-volume baselines, tokenizer-only pretraining, and dynamics variants without aligned actions. These results suggest that controllable MRI slice navigation provides a useful complementary pretraining interface for learning anatomical and spatial representations from large unlabeled MRI collections.