摘要
【Abstract】Even though deep learning is fascinated in fields of coronary vessel segmentation in X-ray angiography and achieves prominent progresses, most of those models probably bring high false and missed detections due to indistinct contrast between coronary vessels and background, especially for tiny sub-branches. Image improvement technique is able to better such contrast, while boosting extraneous information, e.g., other tissues with similar intensities and noise. If incorporating features derived from original and enhanced images, the segmentation performance is improved because those images comprise complementary information from different contrasts. Accordingly, inspired from advantages of contrast improvement and encoding-decoding architecture, a dual multi-scale feature aggregation network (named DFA-Net) is introduced for coronary vessel segmentation in digital subtraction angiography (DSA). DFA-Net integrates the contrast improvement using exponent transformation into a semantic segmentation network that individually accepts original and enhanced images as inputs. Through parameter sharing, multi-scale complementary features are aggregated from different contrasts, which strengthens leaning capabilities of networks, and thus achieves an efficient segmentation. Meanwhile, a risk cross-entropy loss is enforced on the segmentation, for availably decreasing false negatives, which is incorporated with Dice loss for joint optimization of the proposed strategy during training. Experimental results demonstrate that DFA-Net can not only work more robustly and effectively for DSA images under diverse conditions, but also achieve better performance, in comparison with state-of-the-art methods. Consequently, DFA-Net has high fidelity and structure similarity to the reference, providing a way for early diagnosis of cardiovascular diseases.
摘要译文
【摘要】尽管深度学习在X射线血管造影中着迷于冠状动脉血管分割的领域，并取得了突出的进步，但大多数模型可能会导致冠状动脉和背景之间的鲜明对比，尤其是对于微小的Sub Sub Sub，可能带来高的错误和错过的检测。- 分支。图像改进技术能够更好地对比度，同时促进其他信息，例如其他具有相似强度和噪声的组织。如果合并了来自原始图像和增强图像的特征，则将分割性能提高，因为这些图像包含来自不同对比度的互补信息。因此，从对比度改进和编码编码架构的优点中启发，引入了双重尺度特征聚合网络（命名为DFA-NET），以用于数字减法血管造影（DSA）中的冠状动脉血管分割。DFA-NET使用指数转换将对比度改进整合到语义分割网络中，该网络单独接受原始图像和增强的图像作为输入。通过参数共享，多尺度互补的特征是从不同的对比度汇总的，这些功能增强了网络的倾斜功能，从而实现了有效的分割。同时，在分段时会实施风险跨凝结损失，以降低虚假负面因素，并在培训期间与骰子损失进行了损失，以置于骰子损失。实验结果表明，与最先进的方法相比，DFA-NET不仅可以在不同条件下对DSA图像更有效地工作，而且可以实现更好的性能。因此，DFA-NET具有与参考的高保真度和结构相似性，为早期诊断心血管疾病提供了一种方法。
He Deng [1];Xu Liu [2];Tong Fang [3];Yuqing Li [4];Xiangde Min [5];. DFA-Net: Dual multi-scale feature aggregation network for vessel segmentation in X-ray digital subtraction angiography[J]. Journal of Big Data, 2024,11(1): 57