用预训练大模型实现少标注下的卵巢肿块精准分割，提升临床可用性。
Adapting Foundation Models for Annotation-Efficient Adnexal Mass Segmentation in Cine Images
- 基于DINOv3视觉大模型+DPT解码器，融合多尺度特征进行语义与细节重建。
- 在7777帧数据上达到0.945的Dice分数，边界精度提升11.4%。
- 仅需25%数据即可保持高性能，适合标注稀缺的医疗场景。
通过超声评估卵巢肿块是临床中极具挑战的任务，常受主观判断和观察者间差异影响。自动化分割是量化风险评估的基础，但传统全监督卷积架构通常需要大量像素级标注，且难以应对医学影像中的领域偏移问题。本文提出一种标签高效的分割框架，利用预训练DINOv3视觉变换器骨干网络的强语义先验。通过将其与类似DPT的解码器结合，模型分层重组多尺度特征，融合全局语义与精细空间细节。在包含112名患者共7,777帧标注数据的临床数据集上，本方法性能优于多种成熟全监督基线模型（包括U-Net、U-Net++、DeepLabV3、MAnet），Dice分数达0.945，边界贴合度显著提升，95%分位数豪斯多夫距离相比最强卷积基线降低11.4%。此外，我们进行了全面的效率分析，表明在数据匮乏条件下，DINOv3方法仍能保持显著更高的性能，即使仅使用25%数据训练也表现优异。结果表明，利用大规模自监督基础模型为数据受限的临床环境提供了一种有前景且高效的数据解决方案。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。