基于计算机断层血管造影图像的U-Net++模型在脑动脉分割中的应用与优化
本研究将基于深度学习的U-Net++模型用于CTA图像脑动脉分割,利用双能CTA与直接减影CTA数据集分割邻近骨结构的内颈动脉与椎动脉,比较四种剪枝水平(L1-L4)的分割性能与计算成本。L4分割性能最高,L3训练与推理时间平均分别缩短51.56%和22.62%,分割性能仅较L4下降7.08%,提示L3在性能与计算成本间达到最优平衡。
要点
- L4剪枝水平分割性能最高,L3较L4分割性能仅下降7.08%。
- L3较L4训练时间平均缩短51.56%,推理时间平均缩短22.62%。
- L3在分割性能与计算成本之间达到最优平衡。
核心结论
- U-Net++模型的剪枝水平可优化,以在保持有效分割性能的同时降低计算成本。
- L3在分割性能与计算成本之间达到最优平衡。
研究设计与样本
- 研究采用基于深度学习的U-Net++模型进行CTA图像脑动脉分割,使用双能CTA与直接减影CTA数据集,分割邻近骨结构的内颈动脉与椎动脉,设置L1-L4四种剪枝水平,以准确率、交并比、F1分数、边界F1分数和Hausdorff距离评价分割性能,并测量训练与推理时间。
诊断标准与关键数值
- 分割性能评价指标为准确率、交并比、F1分数、边界F1分数和Hausdorff距离。
- L4剪枝水平分割性能最高,L3较L4分割性能下降7.08%。
- L3较L4训练时间平均缩短51.56%,推理时间平均缩短22.62%。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Accurate segmentation of cerebral arteries on computed tomography angiography (CTA) images is essential for the diagnosis and management of cerebrovascular diseases, including ischemic stroke. This study implemented a deep learning-based U-Net++ model for cerebral artery segmentation in CTA images, focusing on optimizing pruning levels by analyzing the trade-off between segmentation performance and computational cost. Dual-energy CTA and direct subtraction CTA datasets were utilized to segment the internal carotid and vertebral arteries in close proximity to the bone. We implemented four pruning levels (L1-L4) in the U-Net++ model and evaluated the segmentation performance using accuracy, intersection over union, F1-score, boundary F1-score, and Hausdorff distance. Statistical analyses were conducted to assess the significance of segmentation performance differences across pruning levels. In addition, we measured training and inference times to evaluate the trade-off between segmentation performance and computational efficiency. Applying deep supervision improved segmentation performance across all factors. While the L4 pruning level achieved the highest segmentation performance, L3 significantly reduced training and inference times (by an average of 51.56 % and 22.62 %, respectively), while incurring only a small decrease in segmentation performance (7.08 %) compared to L4. These results suggest that L3 achieves an optimal balance between performance and computational cost. This study demonstrates that pruning levels in U-Net++ models can be optimized to reduce computational cost while maintaining effective segmentation performance. By simplifying deep learning models, this approach can improve the efficiency of cerebrovascular segmentation, contributing to faster and more accurate diagnoses in clinical settings.
引用
- Kim H, Seo KH, Kim K, et al. Application and optimization of the U-Net++ model for cerebral artery segmentation based on computed tomographic angiography images. Eur J Radiol. 2025. PMID: 40367559. doi:10.1016/j.ejrad.2025.112137
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。