Live Imaging of Cutaneous Wound Healing after Rotary Tool Injury in Zebrafish.

Cutaneous wounds are common afflictions that follow a stereotypical healing process involving hemostasis, inflammation, proliferation, and remodeling phases. In the elderly and those suffering from vascular or metabolic diseases, poor healing after cutaneous injuries can lead to open chronic wounds susceptible to infection. The discovery of new therapeutic strategies to improve this defective wound healing requires a better understanding of the cellular behaviors and molecular mechanisms that drive the different phases of wound healing and how these are altered with age or disease. The zebrafish provides an ideal model for visualization and experimental manipulation of the cellular and molecular events during wound healing in the context of an intact, living vertebrate. To facilitate studies of cutaneous wound healing in zebrafish, we have developed an inexpensive, simple, and effective method for generating reproducible cutaneous injuries in adult zebrafish using a rotary tool. We demonstrate that our injury system can be used in combination with high-resolution live imaging to monitor skin re-epithelialization, immune cell recruitment and activation, and vessel regrowth in the same animal over time. This injury system provides a valuable experimental platform to study key cellular and molecular events during wound healing in vivo with unprecedented resolution.

Relation of Myocardial Perfusion Reserve and Left Ventricular Ejection Fraction in Ischemic and Nonischemic Cardiomyopathy.

Quantification of myocardial perfusion reserve (MPR) using vasodilator stress cardiac magnetic resonance is increasingly used to detect coronary artery disease. However, MPR can also be altered because of changes in microvascular function. We aimed to determine whether MPR can distinguish between ischemic cardiomyopathy (IC) secondary to coronary artery disease and non-IC (NIC) with microvascular dysfunction and no underlying epicardial coronary disease. A total of 60 patients (mean age 65 ± 14 years, 30% women), including 31 with IC and 29 with NIC, were identified from a pre-existing vasodilator stress cardiac magnetic resonance registry. Short-axis cine slices were used to measure left ventricular ejection fraction (LVEF) using the Simpson method of disks. MPR index (MPRi) was determined from first-pass myocardial perfusion images during stress and rest using the upslope ratio, normalized for the arterial input and corrected for rate pressure product. Patients in both groups were divided into subgroups of LVEF ≤35% and LVEF >35%. Differences in MPRi between the subgroups were examined. MPRi was moderately correlated with LVEF in patients with NIC (r = 0.53, p = 0.03), whereas the correlation in patients with IC was lower (r = 0.32, p = 0.22). Average LVEF in NIC and IC was 34% ± 8% and 35% ± 8%, respectively (p = 0.63). MPRi was not significantly different in IC compared with NIC (1.17 [0.88 to 1.61] vs 1.23 [1.07 to 1.66], p = 0.41), including the subgroups of LVEF (IC: 1.20 ± 0.56 vs NIC: 1.15 ± 0.24, p = 0.75 for LVEF ≤35% and IC: 1.35 ± 0.44 vs NIC: 1.58 ± 0.50, p = 0.19 for LVEF >35%). However, MPRi was significantly lower in patients with LVEF ≤35% compared with those with LVEF>35% (1.17 ± 0.40 vs 1.47 ± 0.47, p = 0.01). Similar difference between LVEF groups was noted in the patients with NIC (1.15 ± 0.24 vs 1.58 ± 0.50, p = 0.006) but not in the patients with IC (1.20 ± 0.56 vs 1.35 ± 0.44, p = 0.42). MPRi can be abnormal in the presence of left ventricular dysfunction with nonischemic etiology. This is a potential pitfall to consider when using this approach to detect ischemia because of epicardial coronary disease using myocardial perfusion imaging.

Assessment of right ventricular size and function from cardiovascular magnetic resonance images using artificial intelligence.

BACKGROUND: Theoretically, artificial intelligence can provide an accurate automatic solution to measure right ventricular (RV) ejection fraction (RVEF) from cardiovascular magnetic resonance (CMR) images, despite the complex RV geometry. However, in our recent study, commercially available deep learning (DL) algorithms for RVEF quantification performed poorly in some patients. The current study was designed to test the hypothesis that quantification of RV function could be improved in these patients by using more diverse CMR datasets in addition to domain-specific quantitative performance evaluation metrics during the cross-validation phase of DL algorithm development. METHODS: We identified 100 patients from our prior study who had the largest differences between manually measured and automated RVEF values. Automated RVEF measurements were performed using the original version of the algorithm (DL1), an updated version (DL2) developed from a dataset that included a wider range of RV pathology and validated using multiple domain-specific quantitative performance evaluation metrics, and conventional methodology performed by a core laboratory (CORE). Each of the DL-RVEF approaches was compared against CORE-RVEF reference values using linear regression and Bland-Altman analyses. Additionally, RVEF values were classified into 3 categories: ≤ 35%, 35-50%, and ≥ 50%. Agreement between RVEF classifications made by the DL approaches and the CORE measurements was tested. RESULTS: CORE-RVEF and DL-RVEFs were obtained in all patients (feasibility of 100%). DL2-RVEF correlated with CORE-RVEF better than DL1-RVEF (r = 0.87 vs. r = 0.42), with narrower limits of agreement. As a result, DL2 algorithm also showed increasing accuracy from 0.53 to 0.80 for categorizing RV function. CONCLUSIONS: The use of a new DL algorithm cross-validated on a dataset with a wide range of RV pathology using multiple domain-specific metrics resulted in a considerable improvement in the accuracy of automated RVEF measurements. This improvement was demonstrated in patients whose images were the most challenging and resulted in the largest RVEF errors. These findings underscore the critical importance of this strategy in the development of DL approaches for automated CMR measurements.

AI Based CMR Assessment of Biventricular Function: Clinical Significance of Intervendor Variability and Measurement Errors.

OBJECTIVES: The aim of this study was to determine whether left ventricular ejection fraction (LVEF) and right ventricular ejection fraction (RVEF) and left ventricular mass (LVM) measurements made using 3 fully automated deep learning (DL) algorithms are accurate and interchangeable and can be used to classify ventricular function and risk-stratify patients as accurately as an expert. BACKGROUND: Artificial intelligence is increasingly used to assess cardiac function and LVM from cardiac magnetic resonance images. METHODS: Two hundred patients were identified from a registry of individuals who underwent vasodilator stress cardiac magnetic resonance. LVEF, LVM, and RVEF were determined using 3 fully automated commercial DL algorithms and by a clinical expert (CLIN) using conventional methodology. Additionally, LVEF values were classified according to clinically important ranges: <35%, 35% to 50%, and ≥50%. Both ejection fraction values and classifications made by the DL ejection fraction approaches were compared against CLIN ejection fraction reference. Receiver-operating characteristic curve analysis was performed to evaluate the ability of CLIN and each of the DL classifications to predict major adverse cardiovascular events. RESULTS: Excellent correlations were seen for each DL-LVEF compared with CLIN-LVEF (r = 0.83-0.93). Good correlations were present between DL-LVM and CLIN-LVM (r = 0.75-0.85). Modest correlations were observed between DL-RVEF and CLIN-RVEF (r = 0.59-0.68). A >10% error between CLIN and DL ejection fraction was present in 5% to 18% of cases for the left ventricle and 23% to 43% for the right ventricle. LVEF classification agreed with CLIN-LVEF classification in 86%, 80%, and 85% cases for the 3 DL-LVEF approaches. There were no differences among the 4 approaches in associations with major adverse cardiovascular events for LVEF, LVM, and RVEF. CONCLUSIONS: This study revealed good agreement between automated and expert-derived LVEF and similarly strong associations with outcomes, compared with an expert. However, the ability of these automated measurements to accurately classify left ventricular function for treatment decision remains limited. DL-LVM showed good agreement with CLIN-LVM. DL-RVEF approaches need further refinements.