RESUMEN
Purpose: To assess the feasibility of a newly developed algorithm, called deep learning synthetic strain (DLSS), to infer myocardial velocity from cine steady-state free precession (SSFP) images and detect wall motion abnormalities in patients with ischemic heart disease. Materials and Methods: In this retrospective study, DLSS was developed by using a data set of 223 cardiac MRI examinations including cine SSFP images and four-dimensional flow velocity data (November 2017 to May 2021). To establish normal ranges, segmental strain was measured in 40 individuals (mean age, 41 years ± 17 [SD]; 30 men) without cardiac disease. Then, DLSS performance in the detection of wall motion abnormalities was assessed in a separate group of patients with coronary artery disease, and these findings were compared with consensus results of four independent cardiothoracic radiologists (ground truth). Algorithm performance was evaluated by using receiver operating characteristic curve analysis. Results: Median peak segmental radial strain in individuals with normal cardiac MRI findings was 38% (IQR: 30%-48%). Among patients with ischemic heart disease (846 segments in 53 patients; mean age, 61 years ± 12; 41 men), the Cohen κ among four cardiothoracic readers for detecting wall motion abnormalities was 0.60-0.78. DLSS achieved an area under the receiver operating characteristic curve of 0.90. Using a fixed 30% threshold for abnormal peak radial strain, the algorithm achieved a sensitivity, specificity, and accuracy of 86%, 85%, and 86%, respectively. Conclusion: The deep learning algorithm had comparable performance with subspecialty radiologists in inferring myocardial velocity from cine SSFP images and identifying myocardial wall motion abnormalities at rest in patients with ischemic heart disease.Keywords: Neural Networks, Cardiac, MR Imaging, Ischemia/Infarction Supplemental material is available for this article. © RSNA, 2023.
RESUMEN
Intra-articular or peri-articular corticosteroid injections are often used for treatment of sacroiliac joint (SIJ) pain. However, response to these injections is variable and many patients require multiple injections for sustained benefit. In this study, we aim to identify patient-specific predictors of response or non-response to SIJ injections. Identification of these predictors would allow providers to better determine what treatment would be appropriate for a patient with SIJ pain. A retrospective review of 100 consecutive patient charts spanning a 2-year period at an academic multi-specialty pain center was conducted and a multivariate regression analysis was used to identify patient-specific predictors of response to SIJ injections. Our analysis identified that a history of depression and anxiety (OR: 0.233, 95%CI: 0.057-0.954) and increased age (OR: 0.946, 95%CI: 0.910-0.984) significantly reduced the odds of responding to injections. We also found that the associated NPRS score change for SIJ injection responders was less than the minimally clinically significant value of a 2-point differential, suggesting that reported changes in pain scores may not accurately represent a patient's perception of success after SIJ injection. These findings warrant further investigation through a prospective study and can potentially influence clinical decision making and prognosis for patients receiving SIJ injections.