Automated Segmentation of Left Ventricular Myocardium on Cardiac Computed Tomography Using Deep Learning

Objective@#To evaluate the accuracy of a deep learning-based automated segmentation of the left ventricle (LV) myocardium using cardiac CT. @*Materials and Methods@#To develop a fully automated algorithm, 100 subjects with coronary artery disease were randomly selected as a development set (50 training / 20 validation / 30 internal test). An experienced cardiac radiologist generated the manual segmentation of the development set. The trained model was evaluated using 1000 validation set generated by an experienced technician. Visual assessment was performed to compare the manual and automatic segmentations. In a quantitative analysis, sensitivity and specificity were calculated according to the number of pixels where two three-dimensional masks of the manual and deep learning segmentations overlapped. Similarity indices, such as the Dice similarity coefficient (DSC), were used to evaluate the margin of each segmented masks. @*Results@#The sensitivity and specificity of automated segmentation for each segment (1–16 segments) were high (85.5– 100.0%). The DSC was 88.3 ± 6.2%. Among randomly selected 100 cases, all manual segmentation and deep learning masks for visual analysis were classified as very accurate to mostly accurate and there were no inaccurate cases (manual vs. deep learning: very accurate, 31 vs. 53; accurate, 64 vs. 39; mostly accurate, 15 vs. 8). The number of very accurate cases for deep learning masks was greater than that for manually segmented masks. @*Conclusion@#We present deep learning-based automatic segmentation of the LV myocardium and the results are comparable to manual segmentation data with high sensitivity, specificity, and high similarity scores.

Feasibility of the Radial Artery as a Vascular Access Route in Performing Primary Percutaneous Coronary Intervention

We aimed to evaluate the feasibility of transradial primary percutaneous coronary intervention (PCI) in patients with ST elevation myocardial infarction (STEMI) by comparing the procedural results and complications with those of transfemoral intervention. From April 1997 to October 2004, we enrolled 352 consecutive cases of STEMI who underwent primary PCI. The femoral route was used in 132 cases (TFI group) and the radial route was used in 220 cases (TRI group). Cases with Killips class IV, a negative Allen test or a non-palpable radial artery were excluded from our study. Baseline clinical and angiographic profiles were comparable in both groups. Vascular access time was 3.8 +/- 3.5 min in the TFI group and 3.6 +/- 3.1 min in the TRI group, and cath room to reperfusion time was 25 +/- 11 min in the TRI group and 26 +/- 13 min in the TRI group. The procedural success rate was 89% in the TFI group and 88% in the TRI group. Crossover occurred in 9 cases (4%) due to approaching vessel tortuosity in the TRI group. Major access site complications occurred in 7 cases (5%) in the TFI group, and there were no complications in the TRI group (p < 0.001). Although radial occlusion occurred in 5 cases of the TRI group, there was no evidence of hand ischemia. The total hospital stay was significantly shorter in TRI group than in TFI group. In conclusion, use of the radial artery might be a potential vascular access route in performing primary PCI in selected cases.

Predictive Factors of Survival for Intra-aortic Balloon Pump in Acute Myocardial Infarction Treated with Angioplasty

BACKGROUND AND OBJECTIVES: Intra-aortic balloon pumps (IABP) are useful tools for hemodynamic support in patients with hemodynamic instability or cardiogenic shock due to acute myocardial infarction (AMI). The purpose of this study was to examine the clinical characteristics and outcomes in patients with AMI who underwent IABP support, and to identify predictors of in-hospital mortality. SUBJECTS AND METHODS: We retrospectively analyzed 46 consecutive patients with an acute myocardial infarction, who underwent primary or rescue percutaneous coronary intervention, with IABP support, between March 1997 and June 2002. The patients were divided into survivors and non-survivors. We compared the clinical characteristics, hemodynamic parameters and therapeutic outcomes between the two groups, and assessed the clinical and angiographic predictors of in-hospital mortality. RESULTS: The overall survival rate was 39%. The indications of IABP support were cardiogenic shock (50%), unstable hemodynamics during coronary angioplasty (13%) and high risk intervention (35%). There were no significant differences in clinical diagnosis, infarct location, Killips classification, risk factors, ejection fraction, pain to balloon time, clinical indications for IABP, extents of coronary artery disease and left ventricular end diastolic pressure between the two groups. The survival group was younger than the non-survival group (p=0.04), and the TIMI III flow after PCI was more frequent in the survival group (p=0.01). The TIMI III flow was a predictor of in-hospital mortality (p=0.01). CONCLUSION: The predictive factor of survival following IABP was the TIMI III flow in patients with AMI who underwent primary or rescue PCI.

The Comparison of Reasons for not Receiving Reperfusion Therapy on Acute Myocardial Infarction for the Recent 10 Years

BACKGROUND AND OBJECTIVES: This study was performed to evaluate the changing aspects of the reasons why patients with an acute myocardial infarction were not given the adequate reperfusion therapy over the last 10 years. SUBJECTS AND METHODS: All patients were divided into a reperfusion group (phase I=55, phase II=289) who received reperfusion therapy such as a thrombolytic trial or direct PCI, and a conservative group who had not received reperfusion therapy (phase I=83, phase II=81). We analyzed the clinical characteristics and the various time delays from chest pain onset, the first hospital arrival time, the transfer time, the ER arrival time, and the door to reperfusion time in 138 patients with acute myocardial infarction admitted to Wonju Christian Hospital from Jan. 1991 to Oct. 1993 and 370 patients from Jan. 1997 to Jun. 2002. RESULTS: 55 cases (39.9%) received an adequate reperfusion therapy during phase I and 289 cases (78.1%) received an adequate reperfusion therapy on phase II. 213 cases (78.1%) received direct PTCA on phase II and 12 cases on phase I. The patient time delay was 305.0+/-346.8 min and 253.7+/-233.4 min, the first hospital time delay, 237.2+/-320.7 min and 183.0+/-243.6 min in phase I and phase II. Only 4.8% of patients was were transferred from the first hospital after reperfusion therapy in phase I, but 43.1% of patients were transferred in phase II. The Patient time delay was the most common reason for not receiving reperfusion therapy in phase I, and II, and the time delay and lack of adequate reperfusion therapy at the first hospital despite the early arrival were the second most common reason. Other reasons included a contraindication to lytic therapy, a subsidence of pain or a ST segment elevation, no initial change in the ST segment on EKG and a delay in therapy. CONCLUSION: The most common reason of not receiving reperfusion therapy was patient delay and the time delay at the first hospital. In addition, reperfusion therapy in the first hospital has increased over the last 10 years. To maximize the effectiveness of reperfusion therapy, it is important to shorten the hospital arrival time delay and to use reperfusion therapy at the first hospital.

A Case of Asymptomatic Left Ventricular Pseudoaneurysm after Myocardial Infarction

Left ventricular pseudoaneurysms are result of localized rupture of myocardium. The etiologies of pseudo-aneurysm are mainly transmural myocardial infarction, myocarditis, tuberculosis, syphilis, blunt or penestrating chest trauma and various types of cardiac surgery. It is important to be aware of any characteristic clinical, radiographic, echocardiographic or angiographic features, which distinguish pseudoaneurysm from true aneurysm. Pseudoaneurysm has a relatively high incidence of cardiac rupture than true aneurysm. Therefore, a surgical repair is mandatory in most cases of left ventricular pseudoaneurysm. We report a case of 71-year-old male with coronary artery disease of 3 vessel and asymptomatic left ventricular pseudoaneurysm after silent myocardial infarction.