Ramasamy Anantharaman, Sokooti Hessam, Zhang Xiaotong, Tzorovili Evangelia, Bajaj Retesh, Kitslaar Pieter, Broersen Alexander, Amersey Rajiv, Jain Ajay, Ozkor Mick, Reiber Johan H C, Dijkstra Jouke, Serruys Patrick W, Moon James C, Mathur Anthony, Baumbach Andreas, Torii Ryo, Pugliese Francesca, Bourantas Christos V
Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, West Smithfield, London EC1A 7BE, UK.
Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University of London, Mile End Road, London E1 4NS, UK.
Eur Heart J Open. 2023 Oct 30;3(5):oead090. doi: 10.1093/ehjopen/oead090. eCollection 2023 Sep.
Coronary computed tomography angiography (CCTA) is inferior to intravascular imaging in detecting plaque morphology and quantifying plaque burden. We aim to, for the first time, train a deep-learning (DL) methodology for accurate plaque quantification and characterization in CCTA using near-infrared spectroscopy-intravascular ultrasound (NIRS-IVUS).
Seventy patients were prospectively recruited who underwent CCTA and NIRS-IVUS imaging. Corresponding cross sections were matched using an in-house developed software, and the estimations of NIRS-IVUS for the lumen, vessel wall borders, and plaque composition were used to train a convolutional neural network in 138 vessels. The performance was evaluated in 48 vessels and compared against the estimations of NIRS-IVUS and the conventional CCTA expert analysis. Sixty-four patients (186 vessels, 22 012 matched cross sections) were included. Deep-learning methodology provided estimations that were closer to NIRS-IVUS compared with the conventional approach for the total atheroma volume (Δ: -37.8 ± 89.0 vs. Δ: 243.3 ± 183.7 mm3, variance ratio: 4.262, < 0.001) and percentage atheroma volume (-3.34 ± 5.77 vs. 17.20 ± 7.20%, variance ratio: 1.578, < 0.001). The DL methodology detected lesions more accurately than the conventional approach (Area under the curve (AUC): 0.77 vs. 0.67, < 0.001) and quantified minimum lumen area (Δ: -0.35 ± 1.81 vs. Δ: 1.37 ± 2.32 mm, variance ratio: 1.634, < 0.001), maximum plaque burden (4.33 ± 11.83% vs. 5.77 ± 16.58%, variance ratio: 2.071, = 0.004), and calcific burden (-51.2 ± 115.1 vs. -54.3 ± 144.4, variance ratio: 2.308, < 0.001) more accurately than conventional approach. The DL methodology was able to segment a vessel on CCTA in 0.3 s.
The DL methodology developed for CCTA analysis from co-registered NIRS-IVUS and CCTA data enables rapid and accurate assessment of lesion morphology and is superior to expert analysts (Clinicaltrials.gov: NCT03556644).
在检测斑块形态和量化斑块负荷方面，冠状动脉计算机断层扫描血管造影（CCTA）不如血管内成像。我们旨在首次训练一种深度学习（DL）方法，使用近红外光谱 - 血管内超声（NIRS-IVUS）在CCTA中进行准确的斑块量化和特征描述。
前瞻性招募了70例接受CCTA和NIRS-IVUS成像的患者。使用内部开发的软件匹配相应的横截面，并将NIRS-IVUS对管腔、血管壁边界和斑块成分的估计用于在138条血管中训练卷积神经网络。在48条血管中评估性能，并与NIRS-IVUS的估计值和传统CCTA专家分析进行比较。纳入了64例患者（186条血管，22012个匹配的横截面）。与传统方法相比，深度学习方法在总动脉粥样硬化体积方面提供的估计值更接近NIRS-IVUS（差值：-37.8±89.0 vs.差值：243.3±183.7 mm³，方差比：4.262，<0.001）以及动脉粥样硬化体积百分比（-3.34±5.77 vs. 17.20±7.20%，方差比：1.578，<0.001）。DL方法比传统方法更准确地检测病变（曲线下面积（AUC）：0.77 vs. 0.67，<0.001），并且在量化最小管腔面积（差值：-0.35±1.81 vs.差值：1.37±2.32 mm，方差比：1.634，<0.001）、最大斑块负荷（4.33±11.83% vs. 5.77±16.58%，方差比：2.071，=0.004）和钙化负荷（-51.2±115.1 vs. -54.3±144.4，方差比：2.308，<0.001）方面比传统方法更准确。DL方法能够在0.3秒内对CCTA上的血管进行分割。
从共同注册的NIRS-IVUS和CCTA数据开发的用于CCTA分析的DL方法能够快速准确地评估病变形态，并且优于专家分析（Clinicaltrials.gov：NCT03556644）。
