李劼慧
中国医学科学院阜外医院 心血管外科
The segmentation of cardiac chambers and the quantification of clinical functional metrics in dynamic echocardiography are the keys to the clinical diagnosis of heart disease. Identifying the end-diastolic frames (EDFs) and end-systolic frames (ESFs) and manually segmenting the left ventricle in the echocardiographic cardiac cycle before obtaining the left ventricular ejection fraction (LVEF) is a time-consuming and tedious task for clinicians. In this work, we proposed a deep learning-based fully automated echocardiographic analysis method. We proposed a multi-attention efficient feature fusion network (MAEF-Net) to automatically segment the left ventricle. Then, EDFs and ESFs in all cardiac cycles were automatically detected to compute LVEF. The MAEF-Net method used a multi-attention mechanism to guide the network to capture heartbeat features effectively, while suppressing noise, and incorporated deep supervision mechanism and spatial pyramid feature fusion to enhance feature extraction capabilities. The proposed method was validated on the public EchoNet-Dynamic dataset (n = 1226). The Dice similarity coefficient (DSC) of the left ventricular segmentation reached (93.10 ± 2.22)%, and the mean absolute error (MAE) of cardiac phase detection was (2.36 ± 2.23) frames. The MAE for predicting LVEF was 6.29 %. The proposed method was also validated on a private clinical dataset (n = 22). The DSC of the left ventricular segmentation reached (92.81 ± 2.85)%, and the MAE of cardiac phase detection was (2.25 ± 2.27) frames. The MAE for predicting LVEF was 5.91 %, and the Pearson correlation coefficient r reached 0.96. The proposed method may be used as a new method for automatic left ventricular segmentation and quantitative analysis in two-dimensional echocardiography. Our code and trained models will be made available publicly at https://github.com/xiaojinmao-code/MAEF-Net.
Ultrasonics 2023
It is rare to use the one-stage model without segmentation for the automatic detection of coronary lesions. This study sequentially enrolled 200 patients with significant stenoses and occlusions of the right coronary and categorized their angiography images into two angle views: The CRA (cranial) view of 98 patients with 2453 images and the LAO (left anterior oblique) view of 176 patients with 3338 images. Randomization was performed at the patient level to the training set and test set using a 7:3 ratio. YOLOv5 was adopted as the key model for direct detection. Four types of lesions were studied: Local Stenosis (LS), Diffuse Stenosis (DS), Bifurcation Stenosis (BS), and Chronic Total Occlusion (CTO). At the image level, the precision, recall, mAP@0.1, and mAP@0.5 predicted by the model were 0.64, 0.68, 0.66, and 0.49 in the CRA view and 0.68, 0.73, 0.70, and 0.56 in the LAO view, respectively. At the patient level, the precision, recall, and F1scores predicted by the model were 0.52, 0.91, and 0.65 in the CRA view and 0.50, 0.94, and 0.64 in the LAO view, respectively. YOLOv5 performed the best for lesions of CTO and LS at both the image level and the patient level. In conclusion, the one-stage model without segmentation as YOLOv5 is feasible to be used in automatic coronary lesion detection, with the most suitable types of lesions as LS and CTO.
Diagnostics (Basel, Switzerland) 2023
BACKGROUND:This study aimed to evaluate the clinical and surgical characteristics of patients who required reoperation after mechanical mitral valve replacement (MVR).METHODS:We retrospectively identified 204 consecutive patients who underwent reoperation after mechanical MVR between 2009 and 2018. Patients were categorized according the reason for reoperation (perivalvular leakage, thrombus formation, or pannus formation). The patients' medical and surgical records were studied carefully and the rates of in-hospital complications were calculated.RESULTS:The mean age was 51±12 years and 44% of the patients were male. The reasons for reoperation were perivalvular leakage (117 patients), thrombus formation (35 patients), and pannus formation (52 patients). The most common positions for perivalvular leakage were at the 6-10 o'clock positions (proportions of ≥25% for each hour position). Most patients had an interval of >10 years between the original MVR and reoperation. The most common reoperation procedure was re-do MVR (157 patients), and 155 of these patients underwent concomitant cardiac procedures. There were 10 in-hospital deaths and 32 patients experienced complications. The 10-year survival rate was 82.2 ± 3.9% in general, and the group of lowest rate was patients with PVL (77.5 ± 5.2%). The independent risk factors were "male" (4.62, 95% CI 1.57-13.58, P = 0.005) and "Hb <9g/dL before redo MV operation" (3.45, 95% CI 1.13-10.49, P = 0.029).CONCLUSION:Perivalvular leakage was the most common reason for reoperation after mechanical MVR, with a low survival rate in long term follow-up relatively.
Frontiers in cardiovascular medicine 2021
OBJECTIVES:To compare the outcomes among patients treated by complete coronary revascularization (CCR) or incomplete coronary revascularization (ICR) and no coronary revascularization (NCR) by myocardial perfusion imaging (MPI), as well as to evaluate the impact of severity of ischemia on patients with coronary artery disease (CAD) by different therapy strategies.BACKGROUND:Using myocardial ischemia severity determined by MPI guiding treatment strategies for CAD patients still lacks strong clinical evidences.METHODS:Consecutive patients (N = 286) underwent clinical stress-rest SPECT MPI and were retrospectively followed-up. For assessment of outcome of treatment, all patients were classified into three groups (CCR, ICR, and NCR), and further divided into two subgroups as mild ischemia (< 10% ischemic myocardium) and moderate-severe ischemia (≥ 10% ischemic myocardium). All-cause death was defined as the primary endpoint, and the composite of deaths, nonfatal myocardial infarction, and repeat revascularization (MACE) as the secondary endpoint.RESULTS:Two-hundred eighty-six patients were followed-up for 46 ± 21 months. Thirty deaths and 65 MACEs were recorded. Patients treated by revascularization had significantly lower MACE (P < .001) but not mortality (P = .158) than patients treated by NCR. Outcomes of CCR related to mortality rate were greater than ICR and NCR (death: P = .019, MACE: P < .001). In patients with moderate-severe ischemia, CCR showed improved outcomes than ICR and NCR (death: P = .034; and MACE: P < .001). In patients with mild ischemia, the outcomes of CCR, ICR, and NCR had no significant difference (P > .05). Multivariate regression Cox analysis revealed that summed difference score [death: HR 1.09 (1.03, 1.15), P = .004] was an independent risk factor and CCR was an independent negative predictor [death: HR 0.31 (0.12, 0.81), P = .017; MACE: HR 0.30 (0.16, 0.57), P < .001].CONCLUSIONS:Outcomes of patients treated by CCR were most likely more promising in comparison with treatment of ICR and NCR, especially when patients had over 10% ischemic myocardium.
Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology 2019
BACKGROUND:Coronary revascularization in patients with coronary artery disease may be guided by coronary angiography (CA) or alternatively by ischemia on stress myocardial perfusion imaging (MPI). Which strategy leads to optimal cardiac outcomes is uncertain.METHODS:We performed a retrospective analysis of 170 patients with MPI ischemia and percutaneous coronary intervention. The primary endpoint was all-cause mortality at a mean follow-up of 47 ± 21 months; the secondary end point was the composite of deaths, nonfatal myocardial infarction, and repeat coronary revascularization (MACE). The coronary revascularization was defined as complete (CCR) or incomplete (ICR) as judged by CA criteria and by MPI ischemia matched with CA criteria.RESULTS:Nighty-two patients (54%) had ICR by CA criteria (ICR-CA) and 84 (49%) had ICR by MPI criteria (ICR-MPI). Mortality and MACE were lower in patients with CCR-MPI than with ICR-MPI (P = .048, and P = .025). Survival of patients with CCR-CA and ICR-CA was not different (P = .081). Patients with both ICR-MPI and ICR-CA had the worst survival, whereas patients with CCR-MPI and CCR-CA had the best survival (P = .047). By multivariate analysis, ICR-MPI + ICR-CA was an independent predictor of death (P = .025).CONCLUSION:Patients with ICR by MPI were at higher risk than those with CCR. Patients with both ICR by MPI and CA were at the highest risk, while patients with CCR by both MPI and CA had the best long-term event-free survival.
Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology 2016
