Dataset related to the article "A deep-learning approach for myocardial fibrosis detection in early contrast-enhanced cardiac CT images"

This record contains raw data related to the article "A deep-learning approach for myocardial fibrosis detection in early contrast-enhanced cardiac CT images" <strong>Aims:</strong> Diagnosis of myocardial fibrosis is commonly performed with late gadolinium contrast-enhanced (CE) cardiac magnetic resonance (CMR), which might be contraindicated or unavailable. Coronary computed tomography (CCT) is emerging as an alternative to CMR. We sought to evaluate whether a deep learning (DL) model could allow identification of myocardial fibrosis from routine early CE-CCT images. <strong>Methods and results:</strong> Fifty consecutive patients with known left ventricular (LV) dysfunction (LVD) underwent both CE-CMR and (early and late) CE-CCT. According to the CE-CMR patterns, patients were classified as ischemic (<em>n</em> =&amp;thinsp;15, 30%) or non-ischemic (<em>n</em> =&amp;thinsp;35, 70%) LVD. Delayed enhancement regions were manually traced on late CE-CCT using CE-CMR as reference. On early CE-CCT images, the myocardial sectors were extracted according to AHA 16-segment model and labeled as with scar or not, based on the late CE-CCT manual tracing. A DL model was developed to classify each segment. A total of 44,187 LV segments were analyzed, resulting in accuracy of 71% and area under the ROC curve of 76% (95% CI: 72%−81%), while, with the bull’s eye segmental comparison of CE-CMR and respective early CE-CCT findings, an 89% agreement was achieved. <strong>Conclusions:</strong> DL on early CE-CCT acquisition may allow detection of LV sectors affected with myocardial fibrosis, thus without additional contrast-agent administration or radiational dose. Such tool might reduce the user interaction and visual inspection with benefit in both efforts and time.本数据集包含与论文《早期对比增强心脏CT图像中心肌纤维化检测的深度学习方法》相关的原始数据。 <strong>Aims:</strong> 心肌纤维化的临床诊断通常采用晚期钆对比增强（contrast-enhanced, CE）心脏磁共振（cardiac magnetic resonance, CMR）技术，但该方法可能存在禁忌证或无法开展。冠状动脉计算机断层扫描（coronary computed tomography, CCT）正逐渐成为CMR的替代方案。本研究旨在评估深度学习（deep learning, DL）模型能否从常规早期CE-CCT图像中识别心肌纤维化。 <strong>Methods and results:</strong> 50例确诊左心室功能不全（left ventricular dysfunction, LVD）的连续性患者均接受了CE-CMR以及（早期与晚期）CE-CCT检查。根据CE-CMR影像特征，患者被分为缺血性亚组（n=15，占比30%）与非缺血性亚组（n=35，占比70%）。以CE-CMR为参照标准，在晚期CE-CCT图像上手动勾画延迟强化区域。在早期CE-CCT图像中，依据美国心脏协会（American Heart Association, AHA）16节段模型提取心肌节段，并根据晚期CE-CCT的手动勾画结果标记为存在瘢痕或无瘢痕。构建深度学习模型对每个节段进行分类。本研究共分析44187个左心室节段，模型分类准确率达71%，受试者工作特征曲线（Receiver Operating Characteristic, ROC）下面积为76%（95% CI：72%−81%）；通过靶心图（bull’s eye）比对CE-CMR与对应早期CE-CCT的节段结果，二者一致性达89%。 <strong>Conclusions:</strong> 基于早期CE-CCT成像的深度学习模型可实现对存在心肌纤维化的左心室节段的检测，无需额外注射对比剂或增加辐射剂量。该工具可减少人工交互与视觉阅片的工作量，同时节约人力与时间成本。