Multi-parametric assessment of cardiac magnetic resonance images to distinguish myocardial infarctions: A tensor-based radiomics feature.

AIM: This study assessed the myocardial infarction (MI) using a novel fusion approach (multi-flavored or tensor-based) of multi-parametric cardiac magnetic resonance imaging (CMRI) at four sequences; T1-weighted (T1W) in the axial plane, sense-balanced turbo field echo (sBTFE) in the axial plane, late gadolinium enhancement of heart short axis (LGE-SA) in the sagittal plane, and four-chamber views of LGE (LGE-4CH) in the axial plane. METHODS: After considering the inclusion and exclusion criteria, 115 patients (83 with MI diagnosis and 32 as healthy control patients), were included in the present study. Radiomic features were extracted from the whole left ventricular myocardium (LVM). Feature selection methods were Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-Square (Chi2), Analysis of Variance (Anova), Recursive Feature Elimination (RFE), and SelectPersentile. The classification methods were Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF). Different metrics, including receiver operating characteristic curve (AUC), accuracy, F1- score, precision, sensitivity, and specificity were calculated for radiomic features extracted from CMR images using stratified five-fold cross-validation. RESULTS: For the MI detection, Lasso (as the feature selection) and RF/LR (as the classifiers) in sBTFE sequences had the best performance (AUC: 0.97). All features and classifiers of T1 + sBTFE sequences with the weighted method (as the fused image), had a good performance (AUC: 0.97). In addition, the results of the evaluated metrics, especially mean AUC and accuracy for all models, determined that the T1 + sBTFE-weighted fused method had strong predictive performance (AUC: 0.93±0.05; accuracy: 0.93±0.04), followed by T1 + sBTFE-PCA fused method (AUC: 0.85±0.06; accuracy: 0.84±0.06). CONCLUSION: Our selected CMRI sequences demonstrated that radiomics analysis enables to detection of MI accurately. Among the investigated sequences, the T1 + sBTFE-weighted fused method with the highest AUC and accuracy values was chosen as the best technique for MI detection.

Optimization of the Acquisition Time and Injected Dose of 18 F-Fluorodeoxyglucose Based on Patient Specifications for High-Sensitive Positron Emission Tomography/Computed Tomography Scanner.

Background This study was aimed to optimize the fluorodeoxyglucose (FDG)-administered dose and scan time based on patient specifications using a highly sensitive five-ring bismuth germanium oxide (BGO)-based positron emission tomography/computed tomography (PET/CT) scanner (Discovery IQ). Methods We retrospectively analyzed 101 whole-body 18 F-FDG PET/CT images. Patient data were reconstructed using ordered subset expectation maximization with resolution recovery algorithms (OSEM + SharpIR). Signal-to-noise ratio (SNR) was calculated for each patient, standardized to SNR norm , and plotted against three body index parameters (weight, body mass index, and lean body mass). Two professional physicians blindly examined image quality at different patient time per bed positions to determine the minimum acceptable quality. To select images of acceptable quality, the noise index parameter was also measured. A new dose-time product (DTP) was established for each patient, and a predicted injected dose was assumed. Results We found an almost linear association between patient weight and normalized SNR, and patient weight had the highest R 2 in the fitting. The redesigned DTP can reduce results by approximately 74 and 38% compared with ordinary DTP for 80- and 160-s scan durations. The new dose regimen formula was found to be DTP = c/t × m 1.24 , where m is the patient weight, t is the scan time per bed position, and c is 1.8 and 4.3 for acceptable and higher confidence states, respectively, in Discovery IQ PET/CT. Conclusion Patient weight is the best clinical parameter for the implementation of 18 F-FDG PET/CT image quality assessment. A new dose-time regimen based on body weight was proposed for use in highly sensitive five-ring BGO PET-CT scanners to significantly reduce the injection dose and scan times while maintaining sufficient image quality for diagnosis.