Structure is Supervision: Multiview Masked Autoencoders for Radiology

Foundation models have transformed vision and language by learning general-purpose representations from large-scale unlabeled data, yet 3D medical imaging lacks analogous approaches. Existing self-supervised methods rely on low-level reconstruction or contrastive objectives that fail to capture the anatomical semantics critical for medical image analysis, limiting transfer to downstream tasks. We present MASS (MAsk-guided Self-Supervised learning), which treats in-context segmentation as the pretext task for learning general-purpose medical imaging representations. MASS's key insight is that automatically generated class-agnostic masks provide sufficient structural supervision for learning semantically rich representations. By training on thousands of diverse mask proposals spanning anatomical structures and pathological findings, MASS learns what semantically defines medical structures: the holistic combination of appearance, shape, spatial context, and anatomical relationships. We demonstrate effectiveness across data regimes: from small-scale pretraining on individual datasets (20-200 scans) to large-scale multi-modal pretraining on 5K CT, MRI, and PET volumes, all without annotations. MASS demonstrates: (i) few-shot segmentation on novel structures, (ii) matching full supervision with only 20-40% labeled data while outperforming self-supervised baselines by over 20 in Dice score in low-data regimes, and (iii) frozen-encoder classification on unseen pathologies that matches full supervised training with thousands of samples. Mask-guided self-supervised pretraining captures broadly generalizable knowledge, opening a path toward 3D medical imaging foundation models without expert annotations. Code is available: https://github.com/Stanford-AIMI/MASS.

Radiology foundation models (RFMs) have largely inherited the scale-first recipe of natural-image vision--language pre-training. This recipe is difficult to deploy in 3D radiology, where training corpora are smaller, reports vary across institutions, and receiving hospitals often need local adaptation under privacy and compute constraints. We ask whether routine radiology reports can instead be converted into auditable diagnostic supervision that shapes the image encoder, text encoder, aligned space, and local-adaptation procedure. We develop GreenRFM, a supervision-centric pre-training framework organized around four empirical principles: More distilled, Ubiquitous, Semantic-enforcing, and Task-aligning (MUST) supervision. These principles convert noisy reports into structured diagnostic signals and use them to learn discriminative unimodal encoders plus an aligned image--text space for diagnosis-centered multimodal use. GreenRFM requires 24 GPU-hours on a single 24GB GPU (lightweight variant: 6GB VRAM, 4~hours) and reaches a zero-shot CT-RATE AUC of 84.8. Evaluations using more than 200,000 volumes from six institutions and two modalities show transfer to private clinical cohorts and to musculoskeletal MRI. On a local institutional cohort, computationally feasible retraining raises macro-AUC from 70.5 to 82.1. The aligned space also improves hepatocellular-carcinoma microvascular-invasion prediction and trans-arterial chemoembolization response analysis over established clinical scores. These results support supervision-centric pre-training as a practical route to resource-efficient, locally adaptable, diagnosis-centered radiology vision--language representations.

MRI self-supervised learning (SSL) has largely emphasized segmentation and dense prediction, while controlled studies of how alternative pretraining objectives shape transferable representations for MRI-based disease detection remain limited. We compare reconstruction-based Masked Autoencoders (MAE) and latent-predictive Joint Embedding Predictive Architectures (JEPA) for 3D structural MRI. We further introduce a spectral-domain reconstruction loss for MAE to promote sensitivity to fine-grained anatomical structure and integrate variance-covariance regularization (VCR) into JEPA to encourage broader, less redundant latent representations. Models are pretrained on heterogeneous MRI datasets using individual single-contrast inputs. Across seven dataset-task settings spanning four clinical problem domains, downstream transfer depends on both the pretraining paradigm and how the representational bias induced by a specific objective aligns with the downstream task. Spectral regularization provides its clearest gains for Alzheimer's disease classification and tumor grading, while its benefit is smaller for NC vs. MCI and ASD. VCR yields its strongest improvements when discrimination appears to involve multiple sources of structural variation. Overall, MAE-based pretraining generally outperforms baseline JEPA, with SL-MAE providing the strongest gains in several disease-detection settings. Representation analyses show that fine-tuning reorganizes learned representations in an objective-, depth-, and task-dependent manner. VCR-JEPA maintains broader effective dimensionality across depth and greater cross-task representational alignment than baseline JEPA. We publicly release subject-level pretraining and downstream evaluation splits.