Synthetic generation of myocardial blood-oxygen-level-dependent MRI time series via structural sparse decomposition modeling

Dictionary-Driven Ischemia Detection From Cardiac Phase-Resolved Myocardial BOLD MRI at Rest

Cardiac Phase-resolved Blood-Oxygen-Level Dependent (CP-BOLD) MRI provides a unique opportunity to image an ongoing ischemia at rest. However, it requires post-processing to evaluate the extent of ischemia. To address this, here we propose an unsupervised ischemia detection (UID) method which relies on the inherent spatio-temporal correlation between oxygenation and wall motion to formalize a joint learning and detection problem based on dictionary decomposition. Considering input data of a single subject, it treats ischemia as an anomaly and iteratively learns dictionaries to represent only normal observations (corresponding to myocardial territories remote to ischemia). Anomaly detection is based on a modified version of One-class Support Vector Machines (OCSVM) to regulate directly the margins by incorporating the dictionary-based representation errors. A measure of ischemic extent (IE) is estimated, reflecting the relative portion of the myocardium affected by ischemia. For visualization purposes an ischemia likelihood map is created by estimating posterior probabilities from the OCSVM outputs, thus obtaining how likely the classification is correct. UID is evaluated on synthetic data and in a 2D CP-BOLD data set from a canine experimental model emulating acute coronary syndromes. Comparing early ischemic territories identified with UID against infarct territories (after several hours of ischemia), we find that IE, as measured by UID, is highly correlated (Pearson's r=0.84) with respect to infarct size. When advances in automated registration and segmentation of CP-BOLD images and full coverage 3D acquisitions become available, we hope that this method can enable pixel-level assessment of ischemia with this truly non-invasive imaging technique.

Impaired Myocardial Oxygenation Response to Stress in Patients With Chronic Kidney Disease

BACKGROUND

Coronary artery disease and left ventricular hypertrophy are prevalent in the chronic kidney disease (CKD) and renal transplant (RT) population. Advances in cardiovascular magnetic resonance (CMR) with blood oxygen level-dependent (BOLD) technique provides capability to assess myocardial oxygenation as a measure of ischemia. We hypothesized that the myocardial oxygenation response to stress would be impaired in CKD and RT patients.

METHODS AND RESULTS

Fifty-three subjects (23 subjects with CKD, 10 RT recipients, 10 hypertensive (HT) controls, and 10 normal controls without known coronary artery disease) underwent CMR scanning. All groups had cine and BOLD CMR at 3 T. The RT and HT groups also had late gadolinium CMR to assess infarction/replacement fibrosis. The CKD group underwent 2-dimensional echocardiography strain to assess fibrosis. Myocardial oxygenation was measured at rest and under stress with adenosine (140 μg/kg per minute) using BOLD signal intensity. A total of 2898 myocardial segments (1200 segments in CKD patients, 552 segments in RT, 480 segments in HT, and 666 segments in normal controls) were compared using linear mixed modeling. Diabetes mellitus (P=0.47) and hypertension (P=0.57) were similar between CKD, RT, and HT groups. The mean BOLD signal intensity change was significantly lower in the CKD and RT groups compared to HT controls and normal controls (-0.89±10.63% in CKD versus 5.66±7.87% in RT versus 15.54±9.58% in HT controls versus 16.19±11.11% in normal controls, P<0.0001). BOLD signal intensity change was associated with estimated glomerular filtration rate (β=0.16, 95% CI=0.10 to 0.22, P<0.0001). Left ventricular mass index and left ventricular septal wall diameter were similar between the CKD predialysis, RT, and HT groups. None of the CKD patients had impaired global longitudinal strain and none of the RT group had late gadolinium hyperenhancement.

CONCLUSIONS

Myocardial oxygenation response to stress is impaired in CKD patients and RT recipients without known coronary artery disease, and unlikely to be solely accounted for by the presence of diabetes mellitus, left ventricular hypertrophy, or myocardial scarring. The impaired myocardial oxygenation in CKD patients may be associated with declining renal function. Noncontrast BOLD CMR is a promising tool for detecting myocardial ischemia in the CKD population.