提出MaMA方法，让CLIP模型在乳腺钼靶影像上实现高效对齐与精准分析。
Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammography
- 利用多视角和多尺度对齐机制，聚焦高分辨率图像中的关键区域
- 在两个真实数据集上优于现有模型，仅需52%参数量
- 适合医疗视觉-语言预训练、小样本医学影像分析研究者
对比语言-图像预训练（CLIP）在医学图像分析中潜力巨大，但受限于数据与算力，现有应用主要集中在胸片等数据丰富的模态，其他重要模态仍被忽视。本文首次将完整CLIP模型应用于乳腺钼靶影像，应对标签稀缺、高分辨率图像中兴趣区域小、类别不平衡等挑战。我们构建了适配乳腺钼靶的多视角监督框架，设计对称局部对齐模块以增强细节特征捕捉，并引入基于医学知识预训练大语言模型的参数高效微调策略缓解数据不足。所提多视图多尺度对齐（MaMA）方法在两个大规模真实乳腺钼靶数据集EMBED和RSNA-Mammo上，三种任务均超越当前最优基线，模型规模仅为最大基线的52%。代码已开源。
原文摘要 · Abstract (English)
Contrastive Language-Image Pre-training (CLIP) demonstrates strong potential in medical image analysis but requires substantial data and computational resources. Due to these restrictions, existing CLIP applications in medical imaging focus mainly on modalities like chest X-rays that have abundant image-report data available, leaving many other important modalities underexplored. Here, we propose one of the first adaptations of the full CLIP model to mammography, which presents significant challenges due to labeled data scarcity, high-resolution images with small regions of interest, and class-wise imbalance. We first develop a specialized supervision framework for mammography that leverages its multi-view nature. Furthermore, we design a symmetric local alignment module to better focus on detailed features in high-resolution images. Lastly, we incorporate a parameter-efficient fine-tuning approach for large language models pre-trained with medical knowledge to address data limitations. Our multi-view and multi-scale alignment (MaMA) method outperforms state-of-the-art baselines for three different tasks on two large real-world mammography datasets, EMBED and RSNA-Mammo, with only 52% model size compared with the largest baseline. The code is available at https://github.com/XYPB/MaMA
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。