StrainNet: Improved Myocardial Strain Analysis of Cine MRI by Deep Learning from DENSE.

Purpose: To develop a three-dimensional (two dimensions + time) convolutional neural network trained with displacement encoding with stimulated echoes (DENSE) data for displacement and strain analysis of cine MRI. Materials and Methods: In this retrospective multicenter study, a deep learning model (StrainNet) was developed to predict intramyocardial displacement from contour motion. Patients with various heart diseases and healthy controls underwent cardiac MRI examinations with DENSE between August 2008 and January 2022. Network training inputs were a time series of myocardial contours from DENSE magnitude images, and ground truth data were DENSE displacement measurements. Model performance was evaluated using pixelwise end-point error (EPE). For testing, StrainNet was applied to contour motion from cine MRI. Global and segmental circumferential strain (Ecc) derived from commercial feature tracking (FT), StrainNet, and DENSE (reference) were compared using intraclass correlation coefficients (ICCs), Pearson correlations, Bland-Altman analyses, paired t tests, and linear mixed-effects models. Results: The study included 161 patients (110 men; mean age, 61 years ± 14 [SD]), 99 healthy adults (44 men; mean age, 35 years ± 15), and 45 healthy children and adolescents (21 males; mean age, 12 years ± 3). StrainNet showed good agreement with DENSE for intramyocardial displacement, with an average EPE of 0.75 mm ± 0.35. The ICCs between StrainNet and DENSE and FT and DENSE were 0.87 and 0.72, respectively, for global Ecc and 0.75 and 0.48, respectively, for segmental Ecc. Bland-Altman analysis showed that StrainNet had better agreement than FT with DENSE for global and segmental Ecc. Conclusion: StrainNet outperformed FT for global and segmental Ecc analysis of cine MRI.Keywords: Image Postprocessing, MR Imaging, Cardiac, Heart, Pediatrics, Technical Aspects, Technology Assessment, Strain, Deep Learning, DENSE Supplemental material is available for this article. © RSNA, 2023.

Telemetric Blood Pressure Assessment in Angiotensin II-Infused ApoE-/- Mice: 28 Day Natural History and Comparison to Tail-Cuff Measurements.

Abdominal aortic aneurysm (AAA) is a disease of the aortic wall, which can progress to catastrophic rupture. Assessment of mechanical characteristics of AAA, such as aortic distensibility, may provide important insights to help identify at-risk patients and understand disease progression. While the majority of studies on this topic have focused on retrospective patient data, recent studies have used mouse models of AAA to prospectively evaluate the evolution of aortic mechanics. Quantification of aortic distensibility requires accurate measurement of arterial blood pressure, particularly pulse pressure, which is challenging to perform accurately in murine models. We hypothesized that volume/pressure tail-cuff measurements of arterial pulse pressure in anesthetized mice would have sufficient accuracy to enable calculations of aortic distensibility with minimal error. Telemetry devices and osmotic mini-pumps filled with saline or angiotensin-II were surgically implanted in male apolipoprotein-E deficient (ApoE(-/-)) mice. Blood pressure in the aortic arch was measured continuously via telemetry. In addition, simultaneous blood pressure measurements with a volume/pressure tail-cuff system were performed under anesthesia at specific intervals to assess agreement between techniques. Compared to controls, mice infused with angiotensin-II had an overall statistically significant increase in systolic pressure, with no overall difference in pulse pressure; however, pulse pressure did increase significantly with time. Systolic measurements agreed well between telemetry and tail-cuff (coefficient of variation = 10%), but agreement of pulse pressure was weak (20%). In fact, group-averaged pulse pressure from telemetry was a better predictor of a subject's pulse pressure on a given day than a simultaneous tail-cuff measurement. Furthermore, these approximations introduced acceptable errors (15.1 ± 12.8%) into the calculation of aortic distensibility. Contrary to our hypothesis, we conclude that tail-cuff measures of arterial pulse pressure have limited accuracy. Future studies of aneurysm mechanics using the ApoE(-/-)/angiotensin-II model would be better in assuming pulse pressure profiles consistent with our telemetry findings instead of attempting to measure pulse pressure in individual mice.

Hot or cold? Is monothermal caloric testing useful and cost-effective?

OBJECTIVES: Videonystagmography (VNG) is used widely in the assessment of balance dysfunction. The full test battery can be time-consuming and can induce patient discomfort. The purpose of this study was to examine the value of monothermal caloric testing in predicting unilateral caloric weakness, as well as abnormal VNG vestibular and nonvestibular eye movement, while considering the time and reimbursement associated with these tests. METHODS: In a retrospective review of 645 patients who completed a comprehensive VNG test battery with bithermal caloric testing, we calculated the specificity, sensitivity, and predictive values of monothermal caloric testing in relation to bithermal caloric results and noncaloric VNG results. RESULTS: With unilateral vestibular weakness (UVW) defined as a 25% interear difference, warm-air monothermal caloric testing yielded a sensitivity of 87% and a negative predictive value of 90% for predicting UVW. With a 10% UVW definition, the warm-air caloric testing sensitivity increased to 95% and the negative predictive value to 92%. Warm-air monothermal caloric testing had a positive predictive value of 85% and a negative predictive value of 18% for predicting noncaloric VNG findings; cold-air monothermal and bithermal testing displayed similar results. CONCLUSIONS: Isolated monothermal testing is a sensitive screening tool for detecting UVW, but is not adequate for predicting noncaloric VNG results.