arXiv 2507.058832025-07-08eess.IVcs.CV

一种用于血管内超声与光学相干断层扫描成像数据全自动配准的新框架

A novel framework for fully-automated co-registration of intravascular ultrasound and optical coherence tomography imaging data

Barts Health NHS Trust（巴茨健康国民医疗服务信托）；Huazhong University of Science and Technology（华中科技大学）；Queen Mary, University of London（伦敦玛丽女王大学）；Queen Mary University London（伦敦玛丽女王大学）；University College London（伦敦大学学院）；Leiden University Medical Center（莱顿大学医学中心）；University of Bern（伯尔尼大学）

Xingwei He, Kit Mills Bransby, Ahmet Emir Ulutas, Thamil Kumaran, Nathan Angelo Lecaros Yap, Gonul Zeren, Hesong Zeng, Yaojun Zhang, Andreas Baumbach, James Moo… 展开作者

Xingwei He, Kit Mills Bransby, Ahmet Emir Ulutas, Thamil Kumaran, Nathan Angelo Lecaros Yap, Gonul Zeren, Hesong Zeng, Yaojun Zhang, Andreas Baumbach, James Moon, Anthony Mathur, Jouke Dijkstra, Qianni Zhang, Lorenz Raber, Christos V Bourantas

备注：: Preprint

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究提出一种基于深度学习的全自动框架，结合动态时间规整和动态规划，实现IVUS与OCT图像的纵向及环向配准，速度快且与专家分析高度一致。

摘要：

目的：开发一种深度学习（DL）框架，以实现血管内超声（IVUS）和光学相干断层扫描（OCT）图像的纵向和 circumferential 全自动配准。方法与结果：本研究纳入了230例急性冠脉综合征患者（714条血管）的非罪犯血管，这些血管接受了近红外光谱（NIRS）-IVUS 和 OCT 成像。专家分析员在61,655帧 NIRS-IVUS 和62,334帧 OCT 图像中标注了管腔边界，并在10,000帧 NIRS-IVUS 和10,000帧 OCT 图像中识别了分支血管和钙化组织，这些标注用于训练深度学习解决方案以自动提取这些特征。训练好的深度学习解决方案用于处理 NIRS-IVUS 和 OCT 图像，其输出由动态时间规整算法用于纵向配准 NIRS-IVUS 和 OCT 图像，而 IVUS 和 OCT 的 circumferential 配准通过动态规划进行优化。在来自22例患者的77条血管的测试集上，深度学习方法与专家分析员在两组图像的纵向和 circumferential 配准方面表现出高度一致性（纵向配准的一致性相关系数>0.99，circumferential 配准>0.90）。纵向配准的 Williams 指数为0.96，circumferential 配准为0.97，表明其性能与分析员相当。深度学习流程处理一条血管的成像数据所需时间<90秒。结论：本研究提出的基于深度学习的全自动 IVUS 和 OCT 配准框架速度快，且提供的估计结果可与专家分析员相媲美。这些特点使其在分析包含多模态成像以表征斑块组成的研究中收集的大规模数据时具有实用价值。

英文摘要：

Aims: To develop a deep-learning (DL) framework that will allow fully automated longitudinal and circumferential co-registration of intravascular ultrasound (IVUS) and optical coherence tomography (OCT) images. Methods and results: Data from 230 patients (714 vessels) with acute coronary syndrome that underwent near-infrared spectroscopy (NIRS)-IVUS and OCT imaging in their non-culprit vessels were included in the present analysis. The lumen borders annotated by expert analysts in 61,655 NIRS-IVUS and 62,334 OCT frames, and the side branches and calcific tissue identified in 10,000 NIRS-IVUS frames and 10,000 OCT frames, were used to train DL solutions for the automated extraction of these features. The trained DL solutions were used to process NIRS-IVUS and OCT images and their output was used by a dynamic time warping algorithm to co-register longitudinally the NIRS-IVUS and OCT images, while the circumferential registration of the IVUS and OCT was optimized through dynamic programming. On a test set of 77 vessels from 22 patients, the DL method showed high concordance with the expert analysts for the longitudinal and circumferential co-registration of the two imaging sets (concordance correlation coefficient >0.99 for the longitudinal and >0.90 for the circumferential co-registration). The Williams Index was 0.96 for longitudinal and 0.97 for circumferential co-registration, indicating a comparable performance to the analysts. The time needed for the DL pipeline to process imaging data from a vessel was <90s. Conclusion: The fully automated, DL-based framework introduced in this study for the co-registration of IVUS and OCT is fast and provides estimations that compare favorably to the expert analysts. These features renders it useful in research in the analysis of large-scale data collected in studies that incorporate multimodality imaging to characterize plaque composition.

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。