The aim of this study was to develop a deep learning model for classifying frames with versus without optical coherence tomography (OCT)-derived thin-cap fibroatheroma (TCFA).A total of 602 coronary lesions from 602 angina patients were randomised into training and test sets in a 4:1 ratio. A DenseNet model was developed to classify OCT frames with or without OCT-derived TCFA. Gradient-weighted class activation mapping was used to visualise the area of attention. In the training sample (35,678 frames of 480 lesions), the model with fivefold cross-validation had an overall accuracy of 91.6±1.7%, sensitivity of 88.7±3.4%, and specificity of 91.8±2.0% (averaged AUC=0.96±0.01) in predicting the presence of TCFA. In the test samples (9,722 frames of 122 lesions), the overall accuracy at the frame level was 92.8% within the lesion (AUC=0.96) and 91.3% in the entire OCT pullback. The correlation between the %TCFA burden per vessel predicted by the model compared with that identified by experts was significant (r=0.87, p<0.001). The region of attention was localised at the site of the thin cap in 93.4% of TCFA-containing frames. Total computational time per pullback was 2.1±0.3 seconds.A deep learning algorithm can accurately detect an OCT-TCFA with high reproducibility. The time-saving computerised process may assist clinicians to recognise high-risk lesions easily and to make decisions in the catheterisation laboratory.
Background: The microvascular function was known to be an useful predictor of left ventricular functional changes and clinical outcomes in ST-segment elevation myocardial infarction (STEMI). We evaluated the usefulness of integrated approach by using coronary flow velocity reserve (CFR) and diastolic deceleration time (DDT) in the prediction of long-term major adverse cardiac events in STEMI. Methods and Results: Using an intracoronary Doppler wire, CFR, DDT and hyperemic microvascular resistance index (MVRI) were evaluated in 202 patients with first STEMI received reperfusion therapy within 24 hours after onset of symptoms. Major adverse cardiac events were the composite of cardiac death, recurrent myocardial infarction, congestive heart failure and stroke during an average follow-up period of 60 ± 39 months. Follow-up echocardiography was performed at 12 ± 9 months. CFR, DDT and MVRI had significant correlations with left ventricular regional wall motion score index at follow-up echocardiography (r =−0.441, p<0.001; r = 0.413, p<0.001; r =−0.485, p<0.001, respectively). Using receiver-operating characteristics analysis, CFR ≤1.3 (sensitivity: 51%, specificity: 78%), DDT ≤577 ms (sensitivity: 72%, specificity: 62%) and MVRI >2.7 (sensitivity: 68%, specificity: 67%) were the best cutoff values in the prediction of occurring the adverse cardiac events. In patients with CFR ≤1.3, DDT ≤577 ms, cardiac events were occurred in 18 patients (40.0 %) of 45 patients, whereas cardiac events were occurred in 12 patients (20.3%) of 59 patients with CFR >1.3 and DDT ≤577 ms or CFR ≤1.3 and DDT >577 ms (p= 0.048), 9 patients (9.1%) of 99 patients with CFR>1.3 and DDT >577 ms (p<0.001). Ejection fraction at admission (p=0.009), MVRI (p =0.002) and DDT (p=0.023) were independent predictors in the prediction of long-term adverse cardiac outcomes during follow-up. Conclusions: Integrated approach by using CFR and DDT was useful in the prediction of long-term adverse cardiac events. MVRI and DDT were strong independent predictors of long-term adverse cardiac events in STEMI patients.
Although smoking is a risk factor for coronary atherosclerosis, the age-related impact on lesion characteristics and plaque instability remains unclear.In ADAPT-DES, 780 patients with 916 culprit lesions were evaluated by preprocedural grayscale and virtual histology-intravascular ultrasound.Current smokers (smoking within 1 month) more often presented with acute coronary syndrome (67 vs. 51 vs. 51%, P<0.05) compared with former smokers (no smoking for >1 month) or nonsmokers. In patients 65 or more years of age, current smokers (vs. nonsmokers) showed larger normalized volumes of plaque and media [8.6 (7.8-9.4) vs. 7.2 (6.8-7.7) mm/mm, P=0.016] and external elastic membrane [14.4 (13.2-15.5) vs. 12.8 (12.2-13.4) mm/mm, P=0.05]. At the minimal lumen area site, despite a greater plaque burden, the larger external elastic membrane area [14.4 (13.1-15.7) vs. 12.0 (11.3-12.7) mm, P=0.003] contributed toward preserving the minimal lumen area [2.6 (2.4-2.7) vs. 2.6 (2.5-2.7) mm, P=0.91] in current smokers (vs. nonsmokers) 65 or more years of age. Moreover, current smokers (vs. nonsmokers) 65 or more years of age showed a greater normalized necrotic core volume [1.19 (0.96-1.46) vs. 0.75 (0.66-0.85) mm/mm, P=0.0007], more thin-cap fibroatheromas (61 vs. 48%, P=0.04), and plaque ruptures (38 vs. 26%, P=0.051). Conversely, in patients younger than 65 years of age, there was no significant difference in culprit lesion morphology among current, former, and nonsmokers.In patients 65 or more years (not in patients<65 years), smoking increased culprit lesion plaque instability (greater plaque with more necrotic core, thin-cap fibroatheromas, positive remodeling, and plaque ruptures).
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)
