Detection and characteristics of microvascular obstruction in reperfused acute myocardial infarction using an optimized protocol for contrast-enhanced cardiovascular magnetic resonance imaging

Abstract

Several cardiovascular magnetic resonance imaging (CMR) techniques are used to detect microvascular obstruction (MVO) after acute myocardial infarction (AMI). To determine the prevalence of MVO and gain more insight into the dynamic changes in appearance of MVO, we studied 84 consecutive patients with a reperfused AMI on average 5 and 104 days after admission, using an optimised single breath-hold 3D inversion recovery gradient echo pulse sequence (IR-GRE) protocol. Early MVO (2 min post-contrast) was detected in 53 patients (63%) and late MVO (10 min post-contrast) in 45 patients (54%; p = 0.008). The extent of MVO decreased from early to late imaging (4.3±3.2% vs. 1.8±1.8%, p<0.001) and showed a heterogeneous pattern. At baseline, patients without MVO (early and late) had a higher left ventricular ejection fraction (LVEF) than patients with persistent late MVO (56±7% vs. 48±7%, p<0.001) and LVEF was intermediate in patients with early MVO but late MVO disappearance (54±6%). During follow-up, LVEF improved in all three subgroups but remained intermediate in patients with late MVO disappearance. This optimised single breath-hold 3D IR-GRE technique for imaging MVO early and late after contrast administration is fast, accurate and allows detection of patients with intermediate remodelling at follow-up.

Fig. 1

Look–Locker images (left panel) in a patient with regions of interest (ROIs) drawn in only one phase (right panel, enlarged from left panel). Left panel 39 phases of a single slice Look–Locker sequence in one of the eight patients. Right panel phase 20 is enlarged to demonstrate the different ROIs that were drawn in all phases: subendocardial hypoenhanced region (MVO) (dotted line), region directly adjacent to the hypoenhanced region (infarcted myocardium) (solid black line), region of noninfarcted (normal) myocardium (dotted-dashed line)

Fig. 2

Signal intensity curves obtained from the Look–Locker sequence (a) and merit function of contrast and SNR. The MR-derived quantity was normalized to the maximum value (b). a Signal intensity (SI) curves in the region of microvascular obstruction (MVO), infarcted and noninfarcted myocardium obtained from Look–Locker inversion recovery images in a representative patient. Maximum contrast (i.e. SI difference) between MVO and infarcted myocardium would be obtained at an inversion time of approximately 340 ms. b Combining optimised contrast and overall signal, the merit function provides a much less broader optimum at an inversion time of 465 ms for this case than for the contrast between MVO and infarcted area. Note the broad maximum in b and the relatively low signal at 340 ms (i.e. maximal SI difference in this case) in a

Fig. 3

Early (left panel) and late CE-CMR images (right panel) in one of the patients. Two sets of four contiguous short axis slices at midlevel of the LV in a patient 5 days after reperfused acute anteroseptal wall myocardial infarction. Left panel 2 min after contrast injection: the blood pool (*) and myocardium show increased signal intensity (arrow), except for a central dark anteroseptal rim (arrowhead; early MVO). Right panel late hyper- and hypoenhancement: 10 min after contrast injection, signal from noninfarcted myocardium is “nulled” (black arrow) and the infarcted myocardium is hyperenhanced (white arrow). A dark central rim is observed within the bright area (late MVO; arrowhead)

Fig. 4

Correlation between early and late MVO. A good correlation was found between the extent of early and persistent late MVO. The average extent of early MVO was larger than that of persistent late MVO (r = 0.78, p < 0.001). The dotted line represents the line of identity and emphasises the inequality of the measures

Fig. 5

Change in the extent of MVO. In all patients, the extent of early MVO decreased significantly but showed a heterogeneous pattern (MVO persistence (x····x)). In eight patients early MVO disappeared during late CE-CMR (). These patients had a significantly smaller extent of early MVO than the patients with persistence of MVO (0.8% ± 0.4% vs. 5 ± 3.1%, p < 0.001)