Delayed Enhancement (DE) Cardiac Magnetic Resonance (CMR) allows practitioners to identify brosis in the myocardium. It is useful in the di erential diagnosis of Hypertrophic Cardiomyopathy (HCM), and its assessment is of importance in selecting the most ade- quate therapy for a patient. However, it has been stated in the literature that most clinical semiautomatic scar quanti cation methods present high intra- and interobserver variability in the case of HCM. Automatic methods relying on mixture model estimation of the myocardial inten- sity distribution are also subject to variability due to misalignments of the myocardial mask. In this paper, the CINE-CMR image information is incorporated to the estimation of the DE-CMR tissue distributions, without assuming perfect alignment between the two modalities nor the same label partitions in them. For this purpose, we propose an expec- tation maximization algorithm that estimates the DE-CMR distribution parameters, as well as the conditional probabilities of the DE-CMR la- bels with respect to the labels of CINE-CMR, with the latter being an input of the algorithm. Our results show that, compared to applying the original EM in the myocardium, the proposed algorithm is more accu- rate in estimating the myocardial tissue parameters and obtains higher loglikelihood of the scar voxels, as well as a higher Dice coe cient of the subsequent segmentations.
Excepté là où spécifié autrement, la license de ce document est décrite en tant que Attribution 4.0 International