Guo Yin, Akcicek Ebru Yaman, Hippe Daniel S, HashemizadehKolowri SeyyedKazem, Wang Xin, Akcicek Halit, Canton Gador, Balu Niranjan, Geleri Duygu Baylam, Kim Taewon, Shibata Dean, Zhang Kaiyu, Ma Xiaodong, Ferguson Marina S, Mossa-Basha Mahmud, Hatsukami Thomas S, Yuan Chun
Department of Bioengineering, University of Washington, Seattle, WA, USA.
Department of Radiology and Imaging Science, University of Utah School of Medicine, Salt Lake City, UT, USA.
medRxiv. 2025 Feb 19:2024.12.09.24318661. doi: 10.1101/2024.12.09.24318661.
Carotid atherosclerosis is a major contributor in the etiology of ischemic stroke. Although intraplaque hemorrhage (IPH) is known to increase stroke risk and plaque burden, its long-term effects on plaque dynamics remain unclear. This study aimed to evaluate the long-term impact of IPH on carotid plaque burden progression using deep learning-based segmentation on multi-contrast magnetic resonance vessel wall imaging (VWI).
Twenty-eight asymptomatic subjects with carotid atherosclerosis underwent an average of 4.7 ± 0.6 VWI scans over 5.8 ± 1.1 years. Deep learning pipelines were developed and validated to segment the carotid vessel walls and IPH. Bilateral plaque progression was analyzed using generalized estimating equations, and linear mixed-effects models evaluated long-term associations between IPH occurrence, IPH volume, and plaque burden (%WV) progression.
IPH was detected in 23/50 of arteries. Of arteries without IPH at baseline, 11/39 developed new IPH that persisted, while 5/11 arteries with baseline IPH exhibited it throughout the study. Bilateral plaque growth was significantly correlated (r = 0.54, p < 0.001), but this symmetry was weakened with IPH presence. The progression rate for arteries without IPH was -0.001 %/year (p = 0.90). However, IPH presence or development at any point was associated with a 2.3% absolute increase in %WV on average (p < 0.001). The volume of IPH was also positively associated with increased %WV (p = 0.005).
Deep learning-based segmentation pipelines were utilized to identify IPH, quantify IPH volume, and measure their effects on carotid plaque burden during long-term follow-up. Findings demonstrated that IPH may persist for extended periods. While arteries without IPH demonstrated minimal progression under contemporary treatment, presence of IPH and greater IPH volume significantly accelerated long-term plaque growth.
颈动脉粥样硬化是缺血性卒中病因中的主要因素。虽然已知斑块内出血(IPH)会增加卒中风险和斑块负荷,但其对斑块动态变化的长期影响仍不清楚。本研究旨在使用基于深度学习的分割方法对多对比磁共振血管壁成像(VWI)进行分析,以评估IPH对颈动脉斑块负荷进展的长期影响。
28例无症状颈动脉粥样硬化患者在5.8±1.1年的时间里平均接受了4.7±0.6次VWI扫描。开发并验证了基于深度学习的流程,用于分割颈动脉血管壁和IPH。使用广义估计方程分析双侧斑块进展情况,并使用线性混合效应模型评估IPH发生、IPH体积与斑块负荷(%WV)进展之间的长期关联。
在50条动脉中的23条检测到IPH。基线时无IPH的动脉中,39条中有11条出现了持续存在的新IPH,而基线时有IPH的11条动脉中有5条在整个研究过程中都有IPH。双侧斑块生长显著相关(r = 0.54,p < 0.001),但随着IPH的出现,这种对称性减弱。无IPH的动脉进展率为-0.001%/年(p = 0.90)。然而,在任何时间点出现或发生IPH与%WV平均绝对增加2.3%相关(p < 0.001)。IPH体积也与%WV增加呈正相关(p = 0.005)。
基于深度学习的分割流程被用于识别IPH、量化IPH体积,并在长期随访期间测量其对颈动脉斑块负荷的影响。研究结果表明,IPH可能会持续很长时间。虽然在当代治疗下无IPH的动脉进展极小,但IPH的存在和更大的IPH体积显著加速了长期斑块生长。