编码器
分割
编码(内存)
人工智能
卷积神经网络
计算机科学
融合
自编码
模式识别(心理学)
一般化
变压器
计算机视觉
特征(语言学)
人工神经网络
图像分割
深度学习
特征学习
冠状动脉疾病
机器学习
算法
作者
Caixia Dong,Duwei Dai,Xinyi Han,Fan Liu,Xu Yang,Zongfang Li,Songhua Xu
标识
DOI:10.48550/arxiv.2507.12938
摘要
Accurate coronary artery segmentation is critical for computeraided diagnosis of coronary artery disease (CAD), yet it remains challenging due to the small size, complex morphology, and low contrast with surrounding tissues. To address these challenges, we propose a novel segmentation framework that leverages the power of vision foundation models (VFMs) through a parallel encoding architecture. Specifically, a vision transformer (ViT) encoder within the VFM captures global structural features, enhanced by the activation of the final two ViT blocks and the integration of an attention-guided enhancement (AGE) module, while a convolutional neural network (CNN) encoder extracts local details. These complementary features are adaptively fused using a cross-branch variational fusion (CVF) module, which models latent distributions and applies variational attention to assign modality-specific weights. Additionally, we introduce an evidential-learning uncertainty refinement (EUR) module, which quantifies uncertainty using evidence theory and refines uncertain regions by incorporating multi-scale feature aggregation and attention mechanisms, further enhancing segmentation accuracy. Extensive evaluations on one in-house and two public datasets demonstrate that the proposed framework significantly outperforms state-of-the-art methods, achieving superior performance in accurate coronary artery segmentation and showcasing strong generalization across multiple datasets. The code is available at https://github.com/d1c2x3/CAseg.
科研通智能强力驱动
Strongly Powered by AbleSci AI