Prediction of functional recovery after revascularization using quantitative gated myocardial perfusion SPECT: a multi-center cohort study in Japan

Abstract

Backgrounds Prediction of left ventricular functional recovery is important after myocardial infarction. The impact of quantitative perfusion and motion analyses with gated single-photon emission computed tomography (SPECT) on predictive ability has not been clearly defined in multi-center studies. Methods A total of 252 patients with recent myocardial infarction (n=74) and old myocardial infarction (n=175) were registered from 25 institutions. All patients underwent resting gated SPECT using 99m Tc-MIBI, and repeated the study after revascularization after an average follow-up period of 132±81 days. Visual and quantitative assessment of perfusion and wall motion were performed in 5040 segments. Results Non-gated segmental %uptake and end-systolic (ES) %uptake were good predictors of wall motion recovery and significantly differed between improved and non-improved groups (66±17% and 55±18%, p<0.0001 for non-gated, 64±16% and 51±17% for ES %uptake, p<0.0001). The area under the curve (AUC) of receiver-operating characteristics curve (ROC) for non-gated %uptake, ES %uptake, end-diastolic (ED) %uptake and visual perfusion defect score was 0.70, 0.71, 0.61 and 0.56, respectively. Sensitivity and specificity of %uptake were 68% and 64% for non-gated map and 80% and 52% for ES %uptake map. An optimal threshold for predicting segmental improvement was 63% for non-gated and 52% for ES %uptake values. Conclusion Segmental 99m Tc-MIBI uptake provided a useful predictor of wall motion improvement. Application of quantitative approach with non-gated and ES %uptake enhanced predictive accuracy over visual analysis particularly in a multi-center study.

Enhancing Prediction of Myocardial Recovery After Coronary Revascularization: Integrating Radiomics from Myocardial Contrast Echocardiography with Machine Learning

“…The ML-based model developed in this study surpassed previous studies that utilized traditional myocardial perfusion imaging methods such as single-photon emission computed tomography (SPECT), speckle tracking echocardiography, and MCE, which reported AUCs ranging from 0.7 to 0.8 for myocardial function recovery prediction. 8 , 11 , 34 , 35 This demonstrates the substantial potential of the MCE radiomics-based ML model in identifying visually subtle yet highly predictive image features. Although a few reports exist on radiomics-based ML approaches in myocardial function prediction, 19 including the findings of Arian et al 36 which showed that MRI radiomics features combined with ML algorithms provided prognostic information regarding myocardial function in patients after coronary artery bypass grafting with an AUC similar to our report at 0.78, this study represents the first application of a radiomics-based ML approach in MCE.…”

Quantification of Contraction Synchronicity and Contraction Work in Coronary Artery Disease

“…In patients with CAD, LVEF was correlated with CA (r = 0.91), CW (r = 0.88), and SCI (r = 0.78). LVEF has previously been identified as one of the predictors of myocardial viability [17][18][19][20]. However, the information provided by LVEF alone might not be sufficient for it to serve as a predictive index [21,22].…”