Masked and Predictive Self-Supervised Foundation Models for 3D Brain MRI

• URL: http://arxiv.org/abs/2606.13315v1
• Date: Thu, 11 Jun 2026 13:09:59 GMT
• Title: Masked and Predictive Self-Supervised Foundation Models for 3D Brain MRI
• Abstract summary: We investigate two major self-supervised pretraining paradigms for MRI-based disease detection.<n>We study the role of auxiliary objectives by introducing a novel spectral-domain reconstruction loss for MAE.<n>Our results highlight the importance of self-supervised objective design for medical foundation model pretraining.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised foundation models have shown strong promise in medical imaging. However, existing MRI foundation-model studies have primarily emphasized segmentation and dense prediction tasks, while systematic investigation of self-supervised foundation models for MRI-based disease detection remains limited. In this work, we investigate two major self-supervised pretraining paradigms for MRI-based disease detection: reconstruction-based learning via Masked Autoencoders (MAE) and predictive representation learning via Joint Embedding Predictive Architectures (JEPA). We study the role of auxiliary objectives by introducing a novel spectral-domain reconstruction loss for MAE to enhance sensitivity to fine-grained anatomical structure, and by integrating variance--covariance regularization (VCR) within our JEPA framework to encourage decorrelated latent representations. Our models are pretrained on heterogeneous single-contrast MRI volumes in a contrast-agnostic setting, without modality concatenation. Across five downstream disease detection tasks, our results highlight the importance of self-supervised objective design for medical foundation model pretraining, demonstrating that the downstream benefit of each objective is determined by its relevance to the task's structure. Specifically, spectral regularization yields the largest improvements when the downstream discriminative signal is characterized by strong high-frequency anatomical structures, while covariance regularization is most beneficial when discriminative information spans multiple decorrelated feature dimensions. MAE with spectral-domain supervision consistently achieves superior downstream performance for MRI-based disease detection. These findings suggest that self-supervised objectives in medical imaging encode specific biases, and their downstream benefit is fundamentally conditioned on the task's structure.

Related papers

• Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement [81.27196033392559]
  We propose a Collaborative Meta Knowledge Enhancement (COME) framework for dementia etiology diagnosis.<n>COME injects multi-center acquisition semantics, source identifiers, and modality indicators as heterogeneity-aware embeddings into a unified Transformer architecture for scale-up training.<n>Our method achieves state-of-the-art in-domain performance with a mean macro-averaged AUC of 85.62% and a 4.29-point gain over the strongest baseline.
  arXiv  Detail & Related papers  (2026-07-24T04:26:47Z)
• Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models [56.29123284262618]
  This work proposes leveraging the universal representation capabilities of visual foundation models to estimate inherent data uncertainty.<n>We analyze the feature diversity of the model's decoded representations and quantify their singular value energy to define the semantic perception scale for each class.<n>Based on this foundation, we design two uncertainty-driven application strategies: (1) the aleatoric uncertainty-aware data filtering mechanism to eliminate potentially noisy samples and enhance model learning quality; and (2) the dynamic uncertainty-aware optimization strategy that adaptively adjusts class-specific loss weights during training based on the semantic perception scale, combined with a label denoising mechanism to improve training stability
  arXiv  Detail & Related papers  (2026-04-13T03:59:54Z)
• Removing Motion Artifact in MRI by Using a Perceptual Loss Driven Deep Learning Framework [6.697790479726774]
  PERCEPT-Net is a deep learning framework that enhances structure preserving and suppresses artifact through dedicated perceptual supervision.<n>At the core of the framework is the third Motion Perceptual Loss (MPL), an artifact-aware perceptual supervision strategy.<n>PerCEPT-Net outperformed state-of-the-art methods on clinical data.
  arXiv  Detail & Related papers  (2026-04-12T03:30:39Z)
• Aligning Findings with Diagnosis: A Self-Consistent Reinforcement Learning Framework for Trustworthy Radiology Reporting [37.57009831483529]
  Multimodal Large Language Models (MLLMs) have shown strong potential for radiology report generation.<n>Our framework restructures generation into two distinct components: a think block for detailed findings and an answer block for structured disease labels.
  arXiv  Detail & Related papers  (2026-01-06T14:17:44Z)
• Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model [0.7771985426812056]
  We introduce an ROI-guided masking strategy to selectively mask semantically coherent brain regions during self-supervised pretraining.<n>We show that our method achieves a 4.23% improvement in classification accuracy for distinguishing healthy controls from individuals diagnosed with ADHD.<n>Our results demonstrate that masking anatomical regions during model pretraining not only enhances interpretability but also yields more robust and discriminative representations.
  arXiv  Detail & Related papers  (2025-11-01T08:12:00Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations [57.054499278843856]
  Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies.<n>Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs.<n>We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured fMRI data.
  arXiv  Detail & Related papers  (2025-10-05T12:35:01Z)
• Decipher-MR: A Vision-Language Foundation Model for 3D MRI Representations [12.805804608410739]
  We present Decipher-MR, a 3D MRI-specific vision-language foundation model trained on a large-scale dataset.<n>Decipher-MR integrates self-supervised vision learning with report-guided text supervision to build robust, generalizable representations.<n>Our results establish Decipher-MR as a scalable and versatile foundation for MRI-based AI, facilitating efficient development across clinical and research domains.
  arXiv  Detail & Related papers  (2025-09-25T14:43:33Z)
• LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models [59.961172635689664]
  "Knowledge Decomposition" aims to improve the performance on specific medical tasks. We propose a novel framework named Low-Rank Knowledge Decomposition (LoRKD) LoRKD explicitly separates gradients from different tasks by incorporating low-rank expert modules and efficient knowledge separation convolution.
  arXiv  Detail & Related papers  (2024-09-29T03:56:21Z)
• Guided Reconstruction with Conditioned Diffusion Models for Unsupervised Anomaly Detection in Brain MRIs [35.46541584018842]
  Unsupervised Anomaly Detection (UAD) aims to identify any anomaly as an outlier from a healthy training distribution.<n>generative models are used to learn the reconstruction of healthy brain anatomy for a given input image.<n>We propose conditioning the denoising process of diffusion models with additional information derived from a latent representation of the input image.
  arXiv  Detail & Related papers  (2023-12-07T11:03:42Z)
• ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models [69.9178140563928]
  Colonoscopy analysis is essential for assisting clinical diagnosis and treatment. The scarcity of annotated data limits the effectiveness and generalization of existing methods. We propose an Adaptive Refinement Semantic Diffusion Model (ArSDM) to generate colonoscopy images that benefit the downstream tasks.
  arXiv  Detail & Related papers  (2023-09-03T07:55:46Z)
• Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis [55.03872260158717]
  Resting-state MRI functional (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains. But acquiring source data is challenging due to concerns and/or data storage burdens in multi-site studies. We design a source-free collaborative domain adaptation framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible.
  arXiv  Detail & Related papers  (2023-08-24T01:30:18Z)

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.