Objective To quantitatively evaluate the associations of infarct size,regional myocardial function examined by cardiac magnetic resonance feature tracking(CMR-FT)strain analysis with infarct location in patients with ...Objective To quantitatively evaluate the associations of infarct size,regional myocardial function examined by cardiac magnetic resonance feature tracking(CMR-FT)strain analysis with infarct location in patients with ST-segment elevation myocardial infarction(STEMI)treated by primary percutaneous coronary intervention.Methods Cardiac magnetic resonance images were retrospectively analyzed in 95 consecutive STEMI patients with successful reperfusion.The patients were divided into the anterior wall myocardial infarction(AWMI)and nonanterior wall myocardial infarction(NAWMI)groups.Infarct characteristics were assessed by late gadolinium enhancement.Global and regional strains and associated strain rates in the radial,circumferential and longitudinal directions were assessed by CMR-FT based on standard cine images.The associations of infarct size,regional myocardial function examined by CMR-FT strain analysis with infarct location in STEMI patients were evaluated by the Spearman or Pearsonmethod.Results There were 44 patients in the AWMI group and 51 in the NAWMI group.The extent of left ventricular enhanced mass was significantly larger in patients with AWMI compared with the NAWMI group(24.47±11.89,21.06±12.08%LV;t=3.928,P=0.008).In infarct zone analysis,strains in the radial,circumferential and longitudinal directions were remarkably declined in the AWMI group compared with the NAWMI group(z=-20.873,-20.918,-10.357,all P<0.001).The volume(end-systolic volume index),total enhanced mass and extent of enhanced mass of the left ventricular were correlated best with infarct zone strain in the AWMI group(all P<0.001).Conclusion In STEMI patients treated by percutaneous coronary intervention,myocardial damage is more extensive and regional myocardial function in the infarct zone is lower in the AWMI group compared with the NAWMI group.展开更多
Soft-tissue motion introduces significant challenges in robotic teleoperation,especially in medical scenarios where precise target tracking is critical.Latency across sensing,computation,and actuation chains leads to ...Soft-tissue motion introduces significant challenges in robotic teleoperation,especially in medical scenarios where precise target tracking is critical.Latency across sensing,computation,and actuation chains leads to degraded tracking performance,particularly around high-acceleration segments and trajectory inflection points.This study investigates machine learning-based predictive compensation for latency mitigation in soft-tissue tracking.Three models—autoregressive(AR),long short-term memory(LSTM),and temporal convolutional network(TCN)—were implemented and evaluated on both synthetic and real datasets.By aligning the prediction horizon with the end-to-end system delay,we demonstrate that prediction-based compensation significantly reduces tracking errors.Among the models,TCN achieved superior robustness and accuracy on complex motion patterns,particularly in multi-step prediction tasks,and exhibited better latency–horizon compatibility.The results suggest that TCN is a promising candidate for real-time latency compensation in teleoperated robotic systems involving dynamic soft-tissue interaction.展开更多
文摘Objective To quantitatively evaluate the associations of infarct size,regional myocardial function examined by cardiac magnetic resonance feature tracking(CMR-FT)strain analysis with infarct location in patients with ST-segment elevation myocardial infarction(STEMI)treated by primary percutaneous coronary intervention.Methods Cardiac magnetic resonance images were retrospectively analyzed in 95 consecutive STEMI patients with successful reperfusion.The patients were divided into the anterior wall myocardial infarction(AWMI)and nonanterior wall myocardial infarction(NAWMI)groups.Infarct characteristics were assessed by late gadolinium enhancement.Global and regional strains and associated strain rates in the radial,circumferential and longitudinal directions were assessed by CMR-FT based on standard cine images.The associations of infarct size,regional myocardial function examined by CMR-FT strain analysis with infarct location in STEMI patients were evaluated by the Spearman or Pearsonmethod.Results There were 44 patients in the AWMI group and 51 in the NAWMI group.The extent of left ventricular enhanced mass was significantly larger in patients with AWMI compared with the NAWMI group(24.47±11.89,21.06±12.08%LV;t=3.928,P=0.008).In infarct zone analysis,strains in the radial,circumferential and longitudinal directions were remarkably declined in the AWMI group compared with the NAWMI group(z=-20.873,-20.918,-10.357,all P<0.001).The volume(end-systolic volume index),total enhanced mass and extent of enhanced mass of the left ventricular were correlated best with infarct zone strain in the AWMI group(all P<0.001).Conclusion In STEMI patients treated by percutaneous coronary intervention,myocardial damage is more extensive and regional myocardial function in the infarct zone is lower in the AWMI group compared with the NAWMI group.
基金Support by Sichuan Science and Technology Program[2023YFSY0026,2023YFH0004]Guangzhou Huashang University[2024HSZD01,HS2023JYSZH01].
文摘Soft-tissue motion introduces significant challenges in robotic teleoperation,especially in medical scenarios where precise target tracking is critical.Latency across sensing,computation,and actuation chains leads to degraded tracking performance,particularly around high-acceleration segments and trajectory inflection points.This study investigates machine learning-based predictive compensation for latency mitigation in soft-tissue tracking.Three models—autoregressive(AR),long short-term memory(LSTM),and temporal convolutional network(TCN)—were implemented and evaluated on both synthetic and real datasets.By aligning the prediction horizon with the end-to-end system delay,we demonstrate that prediction-based compensation significantly reduces tracking errors.Among the models,TCN achieved superior robustness and accuracy on complex motion patterns,particularly in multi-step prediction tasks,and exhibited better latency–horizon compatibility.The results suggest that TCN is a promising candidate for real-time latency compensation in teleoperated robotic systems involving dynamic soft-tissue interaction.
