让乳腺超声分割模型在有无文本提示时都能准确分割病灶。
NULLBUS: Multimodal Mixed-Supervision for Breast Ultrasound Segmentation via Nullable Global-Local Prompts
- 用可选的空提示机制，统一处理有无文本信息的数据。
- 在三个公开数据集上平均交并比达0.8568，分割性能领先。
- 特别适合缺乏报告标注的临床数据，提升模型实用性。
乳腺超声（BUS）分割可提供病变边界，对辅助诊断与治疗规划至关重要。尽管带提示的方法在有文本或空间提示时能提升分割性能，但多数公开BUS数据集缺乏可靠元数据或报告，导致训练受限于小规模多模态子集，影响模型鲁棒性。我们提出NullBUS，一种多模态混合监督框架，可在同一模型中学习有提示和无提示的图像数据。为应对缺失文本，引入可选提示（nullable prompts），通过可学习的空嵌入与存在掩码实现：无报告时依赖图像自身特征，有报告时融合文本信息。在整合三个公开BUS数据集的统一测试集上，NullBUS取得平均交并比0.8568与平均Dice系数0.9103，表现优于现有方法，在提示混合可用条件下达到当前最优水平。
原文摘要 · Abstract (English)
Breast ultrasound (BUS) segmentation provides lesion boundaries essential for computer-aided diagnosis and treatment planning. While promptable methods can improve segmentation performance and tumor delineation when text or spatial prompts are available, many public BUS datasets lack reliable metadata or reports, constraining training to small multimodal subsets and reducing robustness. We propose NullBUS, a multimodal mixed-supervision framework that learns from images with and without prompts in a single model. To handle missing text, we introduce nullable prompts, implemented as learnable null embeddings with presence masks, enabling fallback to image-only evidence when metadata are absent and the use of text when present. Evaluated on a unified pool of three public BUS datasets, NullBUS achieves a mean IoU of 0.8568 and a mean Dice of 0.9103, demonstrating state-of-the-art performance under mixed prompt availability.
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。