Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea.
Cardiology Division, Massachusetts General Hospital, Harvard Medical School, 55 Fruit Street, GRB 800, Boston, MA, 02114, USA.
Sci Rep. 2023 Dec 27;13(1):22992. doi: 10.1038/s41598-023-50483-9.
Patients with acute coronary syndromes caused by plaque erosion might be managed conservatively without stenting. Currently, the diagnosis of plaque erosion requires an invasive imaging procedure. We sought to develop a deep learning (DL) model that enables an accurate diagnosis of plaque erosion using coronary computed tomography angiography (CTA). A total of 532 CTA scans from 395 patients were used to develop a DL model: 426 CTA scans from 316 patients for training and internal validation, and 106 separate scans from 79 patients for validation. Momentum Distillation-enhanced Composite Transformer Attention (MD-CTA), a novel DL model that can effectively process the entire set of CTA scans to diagnose plaque erosion, was developed. The novel DL model, compared to the convolution neural network, showed significantly improved AUC (0.899 [0.841-0.957] vs. 0.724 [0.622-0.826]), sensitivity (87.1 [70.2-96.4] vs. 71.0 [52.0-85.8]), and specificity (85.3 [75.3-92.4] vs. 68.0 [56.2-78.3]), respectively, for the patient-level prediction. Similar results were obtained at the slice-level prediction AUC (0.897 [0.890-0.904] vs. 0.757 [0.744-0.770]), sensitivity (82.2 [79.8-84.3] vs. 68.9 [66.2-71.6]), and specificity (80.1 [79.1-81.0] vs. 67.3 [66.3-68.4]), respectively. This newly developed DL model enables an accurate CT diagnosis of plaque erosion, which might enable cardiologists to provide tailored therapy without invasive procedures.Clinical Trial Registration: http://www.clinicaltrials.gov , NCT04523194.
斑块侵蚀引起的急性冠状动脉综合征患者可能可以不进行支架置入而保守治疗。目前，斑块侵蚀的诊断需要进行有创影像学检查。我们试图开发一种深度学习（DL）模型，以便使用冠状动脉计算机断层扫描血管造影（CTA）准确诊断斑块侵蚀。共使用 395 名患者的 532 次 CTA 扫描来开发 DL 模型：来自 316 名患者的 426 次 CTA 扫描用于训练和内部验证，来自 79 名患者的 106 次单独扫描用于验证。开发了一种新颖的深度学习模型 Momentum Distillation-enhanced Composite Transformer Attention（MD-CTA），该模型可以有效地处理整套 CTA 扫描以诊断斑块侵蚀。与卷积神经网络相比，新型 DL 模型在患者水平的预测中，AUC（0.899[0.841-0.957] 比 0.724[0.622-0.826]）、敏感性（87.1[70.2-96.4] 比 71.0[52.0-85.8]）和特异性（85.3[75.3-92.4] 比 68.0[56.2-78.3]）均有显著提高；在切片水平的预测 AUC（0.897[0.890-0.904] 比 0.757[0.744-0.770]）、敏感性（82.2[79.8-84.3] 比 68.9[66.2-71.6]）和特异性（80.1[79.1-81.0] 比 67.3[66.3-68.4]）方面也获得了类似的结果。该新开发的 DL 模型能够进行准确的 CT 诊断斑块侵蚀，这可能使心脏病专家能够在无需进行有创程序的情况下提供个体化治疗。临床试验注册：http://www.clinicaltrials.gov，NCT04523194。
