CoralBay: A Self-Supervised CT Foundation Model

• URL: http://arxiv.org/abs/2606.03888v1
• Date: Tue, 02 Jun 2026 16:51:14 GMT
• Title: CoralBay: A Self-Supervised CT Foundation Model
• Abstract summary: Self-supervised learning has enabled large-scale pre-training on 2D natural images, producing general-purpose visual representations that transfer effectively across tasks.<n>We introduce CoralBay, a framework that extends DINO by using a hierarchical 3D Swin backbone and applying self-distillation to multi-scale features.<n>As a result, CoralBay transfers effectively to a wide range of downstream radiological tasks, demonstrating strong and consistent performance across diverse anatomical targets.
• Score: 3.2293427577063194
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised learning has enabled large-scale pre-training on 2D natural images, producing general-purpose visual representations that transfer effectively across tasks. However, many medical imaging modalities, such as CT scans, are inherently three-dimensional and differ fundamentally from natural images in both structure and semantics. Volumetric modalities capture spatial continuity, organ anatomy, and intensity-based tissue properties (e.g., Hounsfield Units), which are not adequately modeled by 2D pre-training. To bridge this gap, we introduce CoralBay, a self-distillation framework that extends DINO by using a hierarchical 3D Swin backbone and applying self-distillation to concatenated multi-scale features, enabling data-efficient self-supervised learning of rich spatial representations that encode both global semantics and fine-grained local structure. As a result, CoralBay transfers effectively to a wide range of downstream radiological tasks, demonstrating strong and consistent performance across diverse anatomical targets. In addition, we contribute to the open-source \eva framework by introducing a public, reproducible 3D radiology leaderboard that unifies multiple datasets and establishes a standardized benchmark for evaluating volumetric representation learning methods.

Related papers

• VolTA-3D: Self-Supervised Learning for Brain MRI using 3D Volumetric Token Alignment [7.836810501854232]
  We present Volta-3D, a self-supervised 3D Vision Transformer framework designed to learn transferable representations.<n>We evaluate Volta-3D on multiple out-of-distribution downstream tasks, including hippocampal segmentation and classification of sex and Alzheimer's disease versus healthy controls.
  arXiv  Detail & Related papers  (2026-05-16T03:09:25Z)
• MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning [9.46850781308982]
  Self-Supervised Learning on unlabeled medical data has emerged as a powerful solution, but prominent frameworks often fail to exploit the inherent 3D nature of CT scans.<n>We propose the autoencoder for enhanced self-supervised medical image learning(MAESIL), a novel self-supervised learning framework designed to capture 3D structural information efficiently.<n>Our framework partitions the volume into superpatches and employs a 3D masked autoencoder strategy with a dual-masking strategy to learn comprehensive spatial representations.
  arXiv  Detail & Related papers  (2026-04-01T05:56:39Z)
• MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models [59.180043227905294]
  We propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework for efficient 3D medical image understanding.<n>We show that MedPruner enables models such as MedGemma to maintain or even exceed their original performance while retaining fewer than 5% of visual tokens.
  arXiv  Detail & Related papers  (2026-03-12T07:37:00Z)
• 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)
• Abnormality-Driven Representation Learning for Radiology Imaging [0.8321462983924758]
  We introduce lesion-enhanced contrastive learning (LeCL), a novel approach to obtain visual representations driven by abnormalities in 2D axial slices across different locations of the CT scans. We evaluate our approach across three clinical tasks: tumor lesion location, lung disease detection, and patient staging, benchmarking against four state-of-the-art foundation models.
  arXiv  Detail & Related papers  (2024-11-25T13:53:26Z)
• MAP: Domain Generalization via Meta-Learning on Anatomy-Consistent Pseudo-Modalities [12.194439938007672]
  We propose Meta learning on Anatomy-consistent Pseudo-modalities (MAP) MAP improves model generalizability by learning structural features. We evaluate our model on seven public datasets of various retinal imaging modalities.
  arXiv  Detail & Related papers  (2023-09-03T22:56:22Z)
• Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training [51.16994853817024]
  This work focuses on designing an effective pre-training framework for 3D radiology images. We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations. The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-07-31T17:59:42Z)
• Multi-View Vertebra Localization and Identification from CT Images [57.56509107412658]
  We propose a multi-view vertebra localization and identification from CT images. We convert the 3D problem into a 2D localization and identification task on different views. Our method can learn the multi-view global information naturally.
  arXiv  Detail & Related papers  (2023-07-24T14:43:07Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences [77.56222946832237]
  We present a novel framework to detect the densepose of multiple people in an image. The proposed method, which we refer to Knowledge Transfer Network (KTN), tackles two main problems. It simultaneously maintains feature resolution and suppresses background pixels, and this strategy results in substantial increase in accuracy.
  arXiv  Detail & Related papers  (2022-06-21T03:11:37Z)
• CORPS: Cost-free Rigorous Pseudo-labeling based on Similarity-ranking for Brain MRI Segmentation [3.1657395760137406]
  We propose a semi-supervised segmentation framework built upon a novel atlas-based pseudo-labeling method and a 3D deep convolutional neural network (DCNN) for 3D brain MRI segmentation. The experimental results demonstrate the superiority of the proposed framework over the baseline method both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-05-19T14:42:49Z)
• PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation [87.50205728818601]
  We propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space. Our PGL model learns the distinctive representations of local regions, and hence is able to retain structural information.
  arXiv  Detail & Related papers  (2020-11-25T11:03:11Z)

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.