Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation

• URL: http://arxiv.org/abs/2605.25402v2
• Date: Tue, 02 Jun 2026 02:03:14 GMT
• Title: Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation
• Abstract summary: Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging.<n>We propose an anatomy-anchored ultrasound self-supervision framework ANAUS that shifts representation learning from generic visual regions to clinically meaningful anatomical structures.
• Score: 29.61647712180762
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing methods for ultrasound (US) images operate at the image or frame level, overlooking the anatomical context for clinical-aligned representation learning. In this work, we propose an anatomy-anchored ultrasound self-supervision framework ANAUS that shifts representation learning from generic visual regions to clinically meaningful anatomical structures. Utilizing a learnable latent prompt engine alongside a one-time domain adaptation on existing public image--mask pairs, we empower the LP-SAM module to achieve annotation-free anatomy delineation at scale. Building upon this anatomical grounding, we propose a dual-policy self-supervised learning paradigm consisting of inter-view semantics-aware anatomy-separating alignment and contextual core-region prediction to enhance representation learning. Specifically, the former enforces feature invariance within identical anatomical regions while promoting discriminability across distinct structures; the latter compels the model to reconstruct corrupted regions, thereby capturing fine-grained structural details. Extensive evaluations on six public datasets demonstrate that \ours{} consistently outstrips current state-of-the-art methods while maintaining the computational efficiency essential for clinical deployment. Code is available at https://github.com/zhcz328/ANAUS.

Related papers

• EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment [15.371433625713232]
  EndoVLM is a novel vision-language FM pre-trained on over 348K endoscopic examinations.<n>An Anatomy-Guided Sparse Pooling mechanism utilizes textual descriptions as queries to drive sparse attention.<n>A Progressive Semantic-Aware Alignment strategy models clinical taxonomy (anatomy and pathological status) via structured soft targets.<n>A Semantic-Concentrated Masked Autoencoder is applied exclusively to these semantic-rich frames, integrating low-level visual precision with robust high-level semantic representation.
  arXiv  Detail & Related papers  (2026-08-05T05:56:41Z)
• Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classification [1.2081034098848615]
  Locus is a regularization framework that balances attention between anatomical (foreground) and background regions.<n>We validate Locus on eight diverse medical imaging datasets spanning dermoscopy, X-ray, histopathology, and cardiac MRI.
  arXiv  Detail & Related papers  (2026-07-12T17:26:17Z)
• Towards Voxel Spacing Consistency for Medical Image Segmentation [56.992050146446495]
  We study the correlation between image resampling and segmentation, and propose Consispace, a semantic-aware resampling framework.<n> Consispace achieves consistent voxel spacing in the axial direction while preserving anatomical and semantic consistency.
  arXiv  Detail & Related papers  (2026-06-30T15:42:23Z)
• CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs [3.369056928100267]
  CheXanatomy is a framework that integrates explicit anatomical knowledge into a pretrained vision-language model.<n>To enable scalable supervision, we synthesize realistic chest radiographs from CT volumes and forward-project CT segmentation labels.<n>We evaluate the approach on synthetic and real chest radiographs against a U-Net baseline, including ablations on model scale, input resolution, and vision encoder fine-tuning.
  arXiv  Detail & Related papers  (2026-06-07T02:41:05Z)
• Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation [1.5532758127091075]
  We propose a retrieval-augmented approach for Text-to-CT generation that integrates semantic and anatomical information under a realistic inference setting.<n>Experiments on the CT-RATE dataset show that retrieval-augmented generation improves image fidelity and clinical consistency compared to text-only baselines.<n>This work introduces a principled and scalable mechanism to bridge semantic conditioning and anatomical plausibility in volumetric medical image synthesis.
  arXiv  Detail & Related papers  (2026-03-09T12:27:17Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• GRASPing Anatomy to Improve Pathology Segmentation [67.98147643529309]
  We introduce GRASP, a modular plug-and-play framework that enhances pathology segmentation models.<n>We evaluate GRASP on two PET/CT datasets, conduct systematic ablation studies, and investigate the framework's inner workings.
  arXiv  Detail & Related papers  (2025-08-05T12:26:36Z)
• CheXLearner: Text-Guided Fine-Grained Representation Learning for Progression Detection [14.414457048968439]
  We present CheXLearner, the first end-to-end framework that unifies anatomical region detection, structure alignment, and semantic guidance.<n>Our proposed Med-Manifold Alignment Module (Med-MAM) leverages hyperbolic geometry to robustly align anatomical structures.<n>Our model attains a 91.52% average AUC score in downstream disease classification, validating its superior feature representation.
  arXiv  Detail & Related papers  (2025-05-11T08:51:38Z)
• Anatomical Structure-Guided Medical Vision-Language Pre-training [21.68719061251635]
  We propose an Anatomical Structure-Guided (ASG) framework for learning medical visual representations. For anatomical region, we design an automatic anatomical region-sentence alignment paradigm in collaboration with radiologists. For finding and existence, we regard them as image tags, applying an image-tag recognition decoder to associate image features with their respective tags within each sample.
  arXiv  Detail & Related papers  (2024-03-14T11:29:47Z)
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration [59.062085785106234]
  This article presents a general Bayesian learning framework for multi-modal groupwise image registration.<n>We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables.<n>Experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images.
  arXiv  Detail & Related papers  (2024-01-04T08:46:39Z)
• Region-based Contrastive Pretraining for Medical Image Retrieval with Anatomic Query [56.54255735943497]
  Region-based contrastive pretraining for Medical Image Retrieval (RegionMIR) We introduce a novel Region-based contrastive pretraining for Medical Image Retrieval (RegionMIR)
  arXiv  Detail & Related papers  (2023-05-09T16:46:33Z)
• Stain based contrastive co-training for histopathological image analysis [61.87751502143719]
  We propose a novel semi-supervised learning approach for classification of histovolution images. We employ strong supervision with patch-level annotations combined with a novel co-training loss to create a semi-supervised learning framework. We evaluate our approach in clear cell renal cell and prostate carcinomas, and demonstrate improvement over state-of-the-art semi-supervised learning methods.
  arXiv  Detail & Related papers  (2022-06-24T22:25:31Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• Learning to Segment Anatomical Structures Accurately from One Exemplar [34.287877547953194]
  Methods that permit to produce accurate anatomical structure segmentation without using a large amount of fully annotated training images are highly desirable. We propose Contour Transformer Network (CTN), a one-shot anatomy segmentor including a naturally built-in human-in-the-loop mechanism. We demonstrate that our one-shot learning method significantly outperforms non-learning-based methods and performs competitively to the state-of-the-art fully supervised deep learning approaches.
  arXiv  Detail & Related papers  (2020-07-06T20:27:38Z)

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.