Adapting Foundation Models for Annotation-Efficient Adnexal Mass Segmentation in Cine Images

• URL: http://arxiv.org/abs/2604.08045v1
• Date: Thu, 09 Apr 2026 09:48:50 GMT
• Title: Adapting Foundation Models for Annotation-Efficient Adnexal Mass Segmentation in Cine Images
• Abstract summary: Adnexal mass evaluation via ultrasound is a challenging clinical task, often hindered by subjective interpretation and significant inter-observer variability.<n>We propose a label-efficient segmentation framework that leverages the robust semantic priors of a pretrained DINOv3 foundational vision transformer backbone.<n>Our method achieves state-of-the-art performance compared to established fully supervised baselines, including U-Net, U-Net++, DeepLabV3, and MAnet.
• Score: 4.42778347374376
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adnexal mass evaluation via ultrasound is a challenging clinical task, often hindered by subjective interpretation and significant inter-observer variability. While automated segmentation is a foundational step for quantitative risk assessment, traditional fully supervised convolutional architectures frequently require large amounts of pixel-level annotations and struggle with domain shifts common in medical imaging. In this work, we propose a label-efficient segmentation framework that leverages the robust semantic priors of a pretrained DINOv3 foundational vision transformer backbone. By integrating this backbone with a Dense Prediction Transformer (DPT)-style decoder, our model hierarchically reassembles multi-scale features to combine global semantic representations with fine-grained spatial details. Evaluated on a clinical dataset of 7,777 annotated frames from 112 patients, our method achieves state-of-the-art performance compared to established fully supervised baselines, including U-Net, U-Net++, DeepLabV3, and MAnet. Specifically, we obtain a Dice score of 0.945 and improved boundary adherence, reducing the 95th-percentile Hausdorff Distance by 11.4% relative to the strongest convolutional baseline. Furthermore, we conduct an extensive efficiency analysis demonstrating that our DINOv3-based approach retains significantly higher performance under data starvation regimes, maintaining strong results even when trained on only 25% of the data. These results suggest that leveraging large-scale self-supervised foundations provides a promising and data-efficient solution for medical image segmentation in data-constrained clinical environments. Project Repository: https://github.com/FrancescaFati/MESA

Related papers

• Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images [48.646448077284276]
  We propose Spatial-FAD, a framework for effective few-shot medical anomaly detection.<n>It improves lesion localization by combining VFM spatial priors with CLIP semantics.<n>Our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC.
  arXiv  Detail & Related papers  (2026-09-11T05:21:01Z)
• Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision [3.3240679960197514]
  It is often desirable to generalize medical imaging AI models trained with dense annotations to data acquired from different ultrasound scanners or clinical sites.<n>We propose a target-informed self-supervised pretraining and model-ensemble strategy.<n>Our method used labeled source data for supervised training and leveraged target-domain pretraining to improve generalization.
  arXiv  Detail & Related papers  (2026-05-27T21:29:31Z)
• Breaking the Data Barrier: Robust Few-Shot 3D Vessel Segmentation using Foundation Models [0.0]
  State-of-the-art vessel segmentation methods typically require large-scale annotated datasets and suffer from severe performance degradation under domain shifts.<n>We propose a novel framework leveraging a pre-trained Vision Foundation Model (DINOv3) adapted for volumetric vessel segmentation.
  arXiv  Detail & Related papers  (2026-02-27T08:24:44Z)
• HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis [1.8747639074211104]
  We present the first comprehensive validation of hyperbolic representation learning for medical image analysis.<n>We demonstrate statistically significant gains across eleven in-distribution datasets and three ViT models.<n>Our proposed method promotes domain-invariant features and outperforms state-of-the-art Euclidean methods by an average of $+2.1%$ AUC.
  arXiv  Detail & Related papers  (2026-02-03T08:50:24Z)
• Longitudinal Vestibular Schwannoma Dataset with Consensus-based Human-in-the-loop Annotations [3.1898695141875772]
  This dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients.<n>We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution.<n>It is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process.
  arXiv  Detail & Related papers  (2025-11-01T09:53:28Z)
• Towards the Automatic Segmentation, Modeling and Meshing of the Aortic Vessel Tree from Multicenter Acquisitions: An Overview of the SEG.A. 2023 Segmentation of the Aorta Challenge [44.01488489205175]
  We introduce the SEG.A. challenge to catalyze progress in this field.<n>The challenge benchmarked automated algorithms on a hidden test set.<n>A key result was that an ensemble of the highest-ranking algorithms significantly outperformed individual models.
  arXiv  Detail & Related papers  (2025-10-28T02:33:45Z)
• Hybrid Deep Learning-Based for Enhanced Occlusion Segmentation in PICU Patient Monitoring [0.0]
  We propose a hybrid approach to segment common occlusions encountered in remote monitoring applications within PICUs. Our approach centers on creating a deep-learning pipeline for limited training data scenarios. The proposed framework yields an overall classification performance with 92.5% accuracy, 93.8% recall, 90.3% precision, and 92.0% F1-score.
  arXiv  Detail & Related papers  (2024-07-18T09:37:55Z)
• Self-supervised Semantic Segmentation: Consistency over Transformation [3.485615723221064]
  We propose a novel self-supervised algorithm, textbfS$3$-Net, which integrates a robust framework based on the proposed Inception Large Kernel Attention (I-LKA) modules. We leverage deformable convolution as an integral component to effectively capture and delineate lesion deformations for superior object boundary definition. Our experimental results on skin lesion and lung organ segmentation tasks show the superior performance of our method compared to the SOTA approaches.
  arXiv  Detail & Related papers  (2023-08-31T21:28:46Z)
• Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
  We propose a learnable weight-based hybrid medical image segmentation approach. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-15T17:55:05Z)
• Hepatic vessel segmentation based on 3Dswin-transformer with inductive biased multi-head self-attention [46.46365941681487]
  We propose a robust end-to-end vessel segmentation network called Indu BIased Multi-Head Attention Vessel Net. We introduce the voxel-wise embedding rather than patch-wise embedding to locate precise liver vessel voxels. On the other hand, we propose inductive biased multi-head self-attention which learns inductive biased relative positional embedding from absolute position embedding.
  arXiv  Detail & Related papers  (2021-11-05T10:17:08Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)

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.