Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography

• URL: http://arxiv.org/abs/2607.26196v1
• Date: Tue, 28 Jul 2026 19:00:17 GMT
• Title: Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography
• Abstract summary: We introduce Rad-JEPA 3D, a joint-embedding predictive framework that learns volumetric CT representations.<n>To improve the quality of intermediate representations, we propose Hidden States Orthogonal Regularization (HSOR)<n>HSOR aligns student-teacher hidden states and reduces feature redundancy throughout the encoder.
• Score: 10.665332135327205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised pretraining is central to 3D medical image analysis, where unlabeled CT volumes are abundant but expert annotations are scarce. Yet existing volumetric encoders often fail to preserve the coarse spatial and geometric structure that downstream reasoning depends on, limiting their performance on organ disentanglement, abnormality detection, and spatial understanding when paired with language models. We introduce Rad-JEPA 3D, a joint-embedding predictive framework that learns volumetric CT representations by predicting the latent features of a complete scan from a masked view. At its core is a hybrid H-Mamba encoder that fuses a Mamba state-space branch, which models inter-slice continuity through sequential scanning, with a grouped-query attention branch, which captures cross-plane spatial context, combined through a lightweight per-token router. To improve the quality of intermediate representations, we further propose Hidden States Orthogonal Regularization (HSOR), which aligns student-teacher hidden states and reduces feature redundancy throughout the encoder. This layer-wise regularization produces more consistent and discriminative volumetric representations, leading to improved performance on organ recognition and spatial reasoning tasks. Pretrained on approximately 120,000 CT scans, Rad-JEPA 3D attains state-of-the-art results despite its compact size: with only 4.0B total parameters, it achieves competitive results with state-of-the-art on closed-ended VQA and the best average spatial-reasoning score on the Spatial-Med benchmark. Ablation studies confirm that the hybrid block and HSOR contribute complementary gains, and that the induced spatial structure can substitute for raw language-model scale on volumetric reasoning tasks.

Related papers

• Big, Bright, or Invisible: A Frozen-Feature Benchmark of 3D CT Foundation Models [30.102620002840904]
  3D CT foundation models could assist routine interpretation by providing generalizable representations of anatomy and pathology.<n>We benchmark ten frozen CT encoders across three cohorts of thoracic CT scans.<n>We find no universal state-of-the-art, with rankings fluctuating significantly depending on the evaluation context.
  arXiv  Detail & Related papers  (2026-08-06T12:34:17Z)
• Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CT [4.758987047240808]
  Grounding of free-text findings in 3D chest Computed Tomography (CT) is critical for clinical interpretability.<n>We propose a novel decoupled framework that disentangles the problem into two specialized stages: class-agnostic lesion segmentation and text-volume reasoning.<n>Our method achieves state-of-the-art performance in overall grounding quality on the official leaderboard.
  arXiv  Detail & Related papers  (2026-07-14T10:26:14Z)
• Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models [24.834339924064505]
  We propose a voxel-wise framework for dense prediction tasks in 3D medical imaging.<n>Our framework estimates transferability directly from the alignment between the sparse 1-skeleton geometric graph of dense features and semantic labels.<n>Our framework achieves state-of-the-art transferability estimation with an average weighted Kendall (outperforming by 0.36) while accelerating evaluation by 56 times.
  arXiv  Detail & Related papers  (2026-07-05T09:45:18Z)
• 3D Ultrasound-Derived Pseudo-CT Synthesis Using a Transformer-Augmented Residual Network for Real-Time Operator Guidance [0.0]
  Ultrasound (US) is non-ionizing and widely accessible; however, it is highly operator dependent and lacks quantitative tissue characterization.<n>This work presents a 3D ultrasound-derived pseudo-CT framework that generates CT-like anatomical reference volumes inferred from US.<n>The proposed method outperforms established baselines in structural fidelity and perceptual image quality.
  arXiv  Detail & Related papers  (2026-05-06T12:52:59Z)
• 3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification [80.43401018217367]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction.<n>Its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows.<n>Existing methods rely on semantic cues extracted from pre-trained vision models to identify and suppress these distractors.<n>We propose 3DGS- HPC, a framework that circumvents these limitations by combining two complementary principles.
  arXiv  Detail & Related papers  (2026-03-08T11:16:30Z)
• Preoperative-to-intraoperative Liver Registration for Laparoscopic Surgery via Latent-Grounded Correspondence Constraints [51.7011449975586]
  Land-Reg is a deformable registration framework that learns latent-grounded 2D-3D landmark correspondences.<n>For rigid registration, Land-Reg embraces a Cross-modal Latent Alignment module.<n>An Uncertainty-enhanced Overlap Landmark Detector with similarity matching is proposed to robustly estimate explicit 2D-3D landmark correspondences.
  arXiv  Detail & Related papers  (2026-03-02T10:44:03Z)
• Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification [69.87877580725768]
  Multimodal Visual Surrogate Compression (MVSC) learns to compress and adapt large 3D sMRI volumes into compact 2D features.<n>MVSC has two key components: a Volume Context that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner.
  arXiv  Detail & Related papers  (2026-01-29T13:05:46Z)
• Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion [57.09673862519791]
  This paper introduces textbfJGA-LBD, a novel framework that unifies the modeling of geometry and appearance into a joint latent representation.<n> Experiments demonstrate that JGA-LBD outperforms current state-of-the-art approaches in terms of both geometry fidelity and appearance quality.
  arXiv  Detail & Related papers  (2026-01-01T12:48:56Z)
• Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans [0.0]
  We propose a new graph-based approach that models CT scans as structured graphs, leveraging axial slice triplets nodes processed through spectral domain convolution to enhance anomaly classification performance.<n>Our method exhibits strong cross-dataset generalization, and competitive performance while achieving robustness to z-axis translation.
  arXiv  Detail & Related papers  (2025-08-01T19:52:34Z)
• MOSAIC: A Multi-View 2.5D Organ Slice Selector with Cross-Attentional Reasoning for Anatomically-Aware CT Localization in Medical Organ Segmentation [0.8747606955991707]
  Existing 3D segmentation approaches are computationally and memory intensive, often processing entire volumes that contain many anatomically irrelevant slices.<n>We propose a novel, anatomically-aware slice selector pipeline that reduces input volume prior to segmentation.<n>Our proposed model acts as an "expert" in anatomical localization, reasoning over multi-view representations to selectively retain slices with high structural relevance.
  arXiv  Detail & Related papers  (2025-05-15T19:32:28Z)
• JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery [84.67823511418334]
  This paper presents 3D JOint contrastive learning with TRansformers framework for handling occluded 3D human mesh recovery. Our method includes an encoder-decoder transformer architecture to fuse 2D and 3D representations for achieving 2D$&$3D aligned results.
  arXiv  Detail & Related papers  (2023-07-31T02:58:58Z)
• A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning [56.52933974838905]
  Current medical workflow requires manual delineation of organs-at-risk (OAR) In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation. Our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging.
  arXiv  Detail & Related papers  (2022-03-01T17:08:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.