Yao J, Tridandapani S, Bhatti P T
1School of Electrical and Computer EngineeringGeorgia Institute of TechnologyAtlantaGA30332-0250USA.
2Department of RadiologyUniversity of Alabama at BirminghamBirminghamAL35294USA.
IEEE J Transl Eng Health Med. 2019 Sep 13;7:1900404. doi: 10.1109/JTEHM.2019.2923353. eCollection 2019.
Accurate gating for data acquisition of computed tomography (CT) is crucial to obtaining high quality images for diagnosing cardiovascular diseases. To illustrate the feasibility of an optimized cardiac gating strategy, we present a near real-time implementation based on fusing seismocardiography (SCG) and ECG. : The implementation was achieved via integrating commercial hardware and software platforms. Testing was performed on five healthy subjects (age: 24-27; m/f: 4/1) and three cardiac patients (age: 41-71; m/f: 2/1), and compared with baseline quiescence derived from echocardiography. : The average latency introduced by computerized processing was 5.1 ms, well within a 100 ms tolerance bounded by data accumulation time for quiescence prediction. The average prediction error associated with conventional ECG-only versus SCG-ECG-based method over all subjects were 59.58 ms and 27.24 ms, respectively. : The results demonstrate that the multimodal framework can achieve improved quiescence prediction accuracy over the ECG-only-based method in near real-time.
计算机断层扫描（CT）数据采集的精确门控对于获取用于诊断心血管疾病的高质量图像至关重要。为了说明优化心脏门控策略的可行性，我们提出了一种基于融合心震图（SCG）和心电图（ECG）的近实时实现方法。该实现是通过整合商业硬件和软件平台来完成的。对五名健康受试者（年龄：24 - 27岁；男/女：4/1）和三名心脏病患者（年龄：41 - 71岁；男/女：2/1）进行了测试，并与超声心动图得出的静息基线进行了比较。计算机处理引入的平均延迟为5.1毫秒，完全在由静息预测的数据积累时间所界定的100毫秒容限范围内。在所有受试者中，仅基于传统心电图方法与基于SCG - ECG方法的平均预测误差分别为59.58毫秒和27.24毫秒。结果表明，多模态框架能够在近实时情况下比仅基于心电图的方法实现更高的静息预测准确率。
