用粗略标注训练医学图像分割通用模型，大幅降低标注成本
Efficient Universal Models for Medical Image Segmentation via Weakly Supervised In-Context Learning
- 用边界框或点等弱提示替代密集标注进行上下文学习
- 在三个基准上性能接近传统方法，标注成本显著降低
- 适合希望减少标注工作量的医疗影像研究者
医学图像分割的通用模型（如交互式和上下文学习模型）虽具强泛化能力，但需大量标注。交互式模型需对每张图重复用户提示，而上下文学习依赖像素级精细标签。为此，我们提出弱监督上下文学习（WS-ICL），采用弱提示（如边界框或点）作为上下文，避免精细掩码与反复用户交互。该方法显著降低标注成本。我们在三个独立基准上评估了所提模型，结果表明：WS-ICL 在标注成本更低的情况下，性能可媲美标准上下文学习模型；且在交互范式下也表现优异。这些发现确立了 WS-ICL 作为更高效统一医学图像分割通用模型的重要进展。代码与模型已公开于 https://github.com/jiesihu/Weak-ICL。
原文摘要 · Abstract (English)
Universal models for medical image segmentation, such as interactive and in-context learning (ICL) models, offer strong generalization but require extensive annotations. Interactive models need repeated user prompts for each image, while ICL relies on dense, pixel-level labels. To address this, we propose Weakly Supervised In-Context Learning (WS-ICL), a new ICL paradigm that leverages weak prompts (e.g., bounding boxes or points) instead of dense labels for context. This approach significantly reduces annotation effort by eliminating the need for fine-grained masks and repeated user prompting for all images. We evaluated the proposed WS-ICL model on three held-out benchmarks. Experimental results demonstrate that WS-ICL achieves performance comparable to regular ICL models at a significantly lower annotation cost. In addition, WS-ICL is highly competitive even under the interactive paradigm. These findings establish WS-ICL as a promising step toward more efficient and unified universal models for medical image segmentation. Our code and model are publicly available at https://github.com/jiesihu/Weak-ICL.
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。