小狗阅读会员会员
医学顶刊SCI精读工具

扫码登录小狗阅读

阅读SCI医学文献
Document
订阅泛读方向 订阅泛读期刊
  • 我的关注
  • 我的关注
  • {{item.title}}

    按需关注领域/方向,精准获取前沿热点

  • {{item.title}}

    {{item.follow}}人关注

  • {{item.subscribe_count}}人订阅

    IF:{{item.impact_factor}}

    {{item.title}}

Diagnostic performance of deep learning-based vascular extraction and stenosis detection technique for coronary artery disease.

基于深度学习的血管提取和狭窄检测技术对冠心病的诊断性能。

  • 影响因子:2.12
  • DOI:10.1259/bjr.20191028
  • 作者列表:"Chen M","Wang X","Hao G","Cheng X","Ma C","Guo N","Hu S","Tao Q","Yao F","Hu C
  • 发表时间:2020-09-01
Abstract

OBJECTIVE:To investigate the diagnostic performance of deep learning (DL)-based vascular extraction and stenosis detection technology in assessing coronary artery disease (CAD). METHODS:The diagnostic performance of DL technology was evaluated by retrospective analysis of coronary computed tomography angiography in 124 suspected CAD patients, using invasive coronary angiography as reference standard. Lumen diameter stenosis ≥50% was considered obstructive, and the diagnostic performances were evaluated at per-patient, per-vessel and per-segment levels. The diagnostic performances between DL model and reader model were compared by the areas under the receiver operating characteristics curves (AUCs). RESULTS:In patient-based analysis, AUC of 0.78 was obtained by DL model to detect obstructive CAD [sensitivity of 94%, specificity of 63%, positive predictive value of 94%, and negative predictive value of 59%], While AUC by reader model was 0.74 (sensitivity of 97%, specificity of 50%, positive predictive value of 93%, negative predictive value of 73%). In vessel-based analysis, the AUCs of DL model and reader model were 0.87 and 0.89 respectively. In segment-based analysis, the AUCs of 0.84 and 0.89 were obtained by DL model and reader model respectively. It took 0.47 min to analyze all segments per patient by DL model, which is significantly less than reader model (29.65 min) (p < 0.001). CONCLUSION:The DL technology can accurately and effectively identify obstructive CAD, with less time-consuming, and it could be a reliable diagnostic tool to detect CAD. ADVANCES IN KNOWLEDGE:The DL technology has valuable prospect with the diagnostic ability to detect CAD.

摘要

目的: 探讨基于深度学习 (DL) 的血管提取和狭窄检测技术在评估冠心病 (CAD) 中的诊断性能。 方法: 以有创冠状动脉造影为参考标准,回顾性分析124例疑似CAD患者的冠状动脉ct血管造影结果,评价DL技术的诊断效能。管腔直径狭窄 ≥ 50% 被认为是阻塞性的,在每例患者、每支血管和每段水平评估诊断性能。通过接受者操作特征曲线 (auc) 下的面积比较DL模型和读取器模型之间的诊断性能。 结果: 在基于患者的分析中,DL模型检测阻塞性CAD的AUC为0.78 [灵敏度为94%,特异度为63%,阳性预测值为94%,阴性预测值为59%],而reader模型的AUC为0.74 (灵敏度为97%,特异度为50%,阳性预测值为93%,73%) 的阴性预测值。在基于血管的分析中,DL模型和读取器模型的auc分别为0.87和0.89。在基于片段的分析中,分别通过DL模型和读取器模型获得0.84和0.89的auc。DL模型分析每个患者的所有节段花费0.47  min,显著少于reader模型 (29.65  min) (p <0.001)。 结论: DL技术能准确、有效地识别梗阻性CAD,耗时少,是一种可靠的诊断手段。 知识进展: DL技术具有检测CAD的诊断能力,具有宝贵的前景。

关键词:
阅读人数:5人
下载该文献
小狗阅读

帮助医生、学生、科研工作者解决SCI文献找不到、看不懂、阅读效率低的问题。提供领域精准的SCI文献,通过多角度解析提高文献阅读效率,从而使用户获得有价值研究思路。

相关文献
影响因子:0.96
发表时间:2020-02-01
DOI:10.1002/jcu.22732
作者列表:["Tadic M","Belyavskiy E","Cuspidi C","Pieske B","Haßfeld S"]

METHODS::We present the case of a 61-year-old woman with a large tumoral infiltration extending from the pelvis throughout the inferior vena cava inferior to the right atrium, protruding into the right ventricle and right ventricular outflow tract. She had been treated 10 years before for low-grade endometrial stromal sarcoma by hysterectomy and adnexectomy followed by hormone- and radio-therapy. Due to cancer recurrence, she underwent peritonectomy, appendectomy, and resection of terminal ileum.

翻译标题与摘要 下载文献
影响因子:2.41
发表时间:2020-06-12
DOI:10.4244/EIJ-D-18-01138
作者列表:["Pellicano M","Di Gioia G","Ciccarelli G","Xaplanteris P","Delrue L","Toth GG","Van Durme F","Heyse A","Wyffels E","Vanderheyden M","Bartunek J","De Bruyne B","Barbato E"]

METHODS:AIMS:Significant platelet activation after long stented coronary segments has been associated with periprocedural microvascular impairment and myonecrosis. In long lesions treated either with an everolimus-eluting bioresorbable vascular scaffold (BVS) or an everolimus-eluting stent (EES), we aimed to investigate (a) procedure-related microvascular impairment, and (b) the relationship of platelet activation with microvascular function and related myonecrosis. METHODS AND RESULTS:Patients (n=66) undergoing elective percutaneous coronary intervention (PCI) in long lesions were randomised 1:1 to either BVS or EES. The primary endpoint was the difference between groups in changes of pressure-derived corrected index of microvascular resistance (cIMR) after PCI. Periprocedural myonecrosis was assessed by high-sensitivity cardiac troponin T (hs-cTnT), platelet reactivity by high-sensitivity adenosine diphosphate (hs-ADP)-induced platelet reactivity with the Multiplate Analyzer. Post-dilatation was more frequent in the BVS group, with consequent longer procedure time. A significant difference was observed between the two groups in the primary endpoint of ΔcIMR (p=0.04). hs-ADP was not different between the groups at different time points. hs-cTnT significantly increased after PCI, without difference between the groups. CONCLUSIONS:In long lesions, BVS implantation is associated with significant acute reduction in IMR as compared with EES, with no significant interaction with platelet reactivity or periprocedural myonecrosis.

关键词: 暂无
翻译标题与摘要 下载文献
影响因子:1.67
发表时间:2020-01-01
DOI:10.2174/1573403X15666190513105231
作者列表:["Dev M","Sharma M","Rana N"]

METHODS:BACKGROUND:Aortopulmonary window is an uncommon congenital heart disease, with untreated cases not surviving beyond childhood. However, very rarely it can present in adult patients with features of pulmonary hypertension. Clinically these patients cannot be differentiated from other more common conditions with left to right shunt. Transthoracic echocardiography if performed meticulously, can depict the defect in aortopulmonary septum. RESULTS:We report a case of large unrepaired aortopulmonary window in a 23 years old patient, diagnosed on transthoracic echocardiography.

心脏影像技术方向

心脏结构和心脏血流的可视化,用于诊断评估或通过内窥镜、放射性核素成像等技术来指导心脏手术。

复制标题
发送后即可在该邮箱或我的下载查看该文献
发送
该文献默认存储到我的下载

科研福利

临床科研之家订阅号

报名咨询

建议反馈
问题标题:
联系方式:
电子邮件:
您的需求: