MSA-UNet3+: 带新监督原型对比损失的多尺度注意力UNet3+用于冠状动脉DSA图像分割
MSA-UNet3+: Multi-Scale Attention UNet3+ with New Supervised Prototypical Contrastive Loss for Coronary DSA Image Segmentation
AI总结：
本文提出MSA-UNet3+和SPCL，通过结合监督和原型对比学习提升冠状动脉DSA图像分割精度，实验表明其在Dice系数和F1分数上优于现有方法。
摘要：
准确分割冠状动脉数字减影血管造影（DSA）图像对诊断和治疗冠状动脉疾病（CAD）至关重要。尽管深度学习取得了进展，但高类内方差和类不平衡等挑战限制了精确血管勾勒。现有方法无法有效解决这些问题。此外，现有分割网络编码器无法直接生成语义嵌入，这可能阻碍解码器更有效地重建分割掩码。我们提出了一种监督原型对比损失（SPCL），结合监督和原型对比学习以增强冠状动脉DSA图像分割。监督对比损失在编码器中强制语义嵌入，提高特征区分度。原型对比损失使模型专注于前景类别，通过仅关注难以分类的背景样本缓解高类内方差和类不平衡。我们将在MSA-UNet3+中实现所提出的SPCL，这是一种多尺度注意力增强的UNet3+架构。该架构集成了多尺度注意力编码器（M-编码器）、多尺度扩张瓶颈（MSD-瓶颈）用于多尺度特征提取，以及上下文注意力融合模块（CAFM）以保留细粒度细节并提高上下文理解。在私人冠状动脉DSA数据集上的实验表明，MSA-UNet3+优于现有方法，实现了最高的Dice系数和F1分数，同时显著减少ASD和ACD。该框架为精确血管分割提供了准确的识别冠状动脉狭窄的支持，并支持有根据的诊断和治疗决策。代码将在https://github.com/rayanmerghani/MSA-UNet3plus发布。
英文摘要：
Accurate segmentation of coronary Digital Subtraction Angiography (DSA) images is essential for diagnosing and treating coronary artery disease (CAD). Despite advances in deep learning, challenges such as high intra-class variance and class imbalance limit precise vessel delineation. Existing approaches for coronary DSA segmentation cannot effectively address these issues. Furthermore, existing segmentation network encoders do not directly generate semantic embeddings, which could enable the decoder to reconstruct segmentation masks more effectively. We propose a Supervised Prototypical Contrastive Loss (SPCL) that combines supervised and prototypical contrastive learning to enhance coronary DSA image segmentation. The supervised contrastive loss enforces semantic embeddings in the encoder, improving feature differentiation. The prototypical contrastive loss enables the model to focus on the foreground class while alleviating high intra-class variance and class imbalance by concentrating only on hard-to-classify background samples. We implement the proposed SPCL within MSA-UNet3+, a Multi-Scale Attention-Enhanced UNet3+ architecture. The architecture integrates a Multi-Scale Attention Encoder (M-encoder), a Multi-Scale Dilated Bottleneck (MSD-Bottleneck) for multi-scale feature extraction, and a Contextual Attention Fusion Module (CAFM) to preserve fine-grained details while improving contextual understanding. Experiments on a private coronary DSA dataset demonstrate that MSA-UNet3+ outperforms state-of-the-art methods, achieving the highest Dice coefficient and F1-score while significantly reducing ASD and ACD. The framework provides precise vessel segmentation for accurate identification of coronary stenosis and supports informed diagnostic and therapeutic decisions. The code will be released at https://github.com/rayanmerghani/MSA-UNet3plus.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
