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, is introduced and Hidden States Orthogonal Regularization (HSOR) is proposed, which aligns student-teacher hidden states and reduces feature redundancy throughout the encoder.
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.
Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume. 3D CT foundation models could assist this process by providing generalizable representations of anatomy and pathology. To evaluate their diagnostic breadth, we benchmark ten frozen CT encoders across three cohorts of thoracic CT scans, including an unseen internal clinical dataset, using $k$-nearest neighbors, zero-shot prompting, and linear probing. We find no universal state-of-the-art, with rankings fluctuating significantly depending on the evaluation context. While models combining fine-grained image tokenization with vision-language alignment generally perform best, a lightweight supervised encoder remains highly competitive, demonstrating that explicit labels can effectively substitute for scale. Crucially, rather than model architecture, we observe that the primary determinant of performance is a physical bottleneck: a finding's detectability scales with its contrast against surrounding tissue and its spatial extent. Through controlled within-organ comparisons, we empirically demonstrate that widespread or high-contrast abnormalities, such as devices and effusions, are reliably recovered. Conversely, small, low-contrast focal lesions remain a persistent challenge across all evaluated encoders. We attribute this to the inherent limitations of globally pooled embeddings, suggesting that accurately representing small, low-contrast structures will require region- or lesion-level pretraining.
Maulik Chevli, Johannes Brandt, R. Braren et al.· 0 citations
Large vision-language models are becoming increasingly dominant in 3D medical image interpretation, but we rarely knowwhichinternal units encode clinical findings orwherethat information lives in the representation. We first study this on a 3D chest vision-language model (Pillar-0) by probing its frozen vision embeddings. We show that (i) each radiological finding is encoded by asparseset of ~10 vision-encoder channels that match full-feature classification performance and far exceed a zero-shot text prompting; (ii) turning off the channels tied to one finding, that finding's score collapses while unrelated labels stay stable; and (iii) the same sparse probereplicateson an architecturally unrelated 3D abdominal VLM (Merlin) suggesting a general property of frozen medical encoders. Our training-free concept channel probe (CCP) method, paired with a corpus-derived report template, outperforms published CT-CHAT on clinical efficacy and NLG metrics (F1 0.549 vs. 0.184; BLEU 0.483 vs. 0.373) at 22x lower latency. Our results provide a clear, reproducible characterization of how frozen medical encoders represent findings, demonstrating direct applicability across models.
F. Nooralahzadeh, L. Bogensperger, C. Bluethgen et al.· arXiv.org· 0 citations
Findings establish joint-embedding predictive generation as a promising direction for 3D medical image synthesis and encourage further research in this direction.
Meng Zhou, Wen-Hao You, Yu-Xin Chen et al.· 0 citations
Effective segmentation of multi-modal MRI is central to improving neural network accuracy in brain tumor recognition. Existing methods typically compress 3D volumes into token sequences via fixed patch encoding or learned attention pooling (e.g., TokenLearner). However, these compression schemes discard explicit spatial shape information; the resulting tokens convey no notion of lesion morphology or spatial extent. Meanwhile, end-to-end evaluation entangles a tokenizer's information retention with the reconstruction capacity of the downstream decoder, and the lack of a unified capacity contract across methods makes performance differences difficult to attribute. In this paper, we introduce Gaussian tokens to multi-modal brain tumor segmentation for the first time: each token carries not only a semantic feature but also a learned 3D center, anisotropic scale, and orientation, endowing the representation with explicit geometric support at negligible parameter cost. We further propose a frozen-token utility evaluation protocol: the trained tokenizer is frozen, its output is cast into a fixed-capacity serialized contract, and a shared lightweight Transformer probe independently measures each tokenizer's retained information under strictly matched conditions. Multi-seed paired statistical testing shows that GSToken consistently and substantially outperforms capacity-matched adaptive baselines under frozen probing, with uniform advantages across all tumor sub-regions, surface, and distance metrics. These results demonstrate that explicitly encoding spatial geometry within tokens significantly improves the information density of volumetric representations, offering a new design principle for compact 3D medical image representation and downstream reading.
Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visual-token sequences with considerable spatial and inter-slice redundancy. Existing token compression methods typically apply uniform reduction or rely on a single importance signal, increasing the risk of removing regions that are clinically relevant to the query or structurally distinctive. To address this limitation, we propose MedARC, a unified, training-free framework for Adaptive Redundancy Compression of visual tokens in 3D medical VLMs. MedARC estimates token importance by integrating three complementary cues: self-attention from the VLM vision encoder, which reflects the model's intrinsic visual focus; similarity between projected visual tokens and text embeddings, which identifies query-relevant regions; and deviations of local visual foundation model features from the volume-level feature center, which highlight structurally distinctive anatomy. The resulting importance distribution guides a saliency-aware merging strategy that preserves informative tokens while consolidating redundant ones rather than simply discarding them. Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance. Its multi-cue scoring cost is outweighed by the savings from processing fewer tokens, with greater benefits expected for larger language models.
Yitao Zhu, Meng-Jun Liu, Yingji Fu et al.· arXiv.org· 0 citations
