Atrial fibrosis quantification based on maximum likelihood estimator of multivariate images

TL;DR

This paper introduces a fully-automated method for quantifying atrial fibrosis using multivariate MRI images, employing a joint distribution model and maximum likelihood estimation to improve segmentation accuracy and account for misregistration.

Contribution

The novel approach combines multivariate mixture modeling with MLE and transformation embedding for improved atrial fibrosis quantification from cardiac MRI images.

Findings

Achieved accuracy of 0.809 and Dice score of 0.556 in clinical data

Statistically better performance than conventional algorithms (p<0.03)

Effective correction of misregistration through embedded transformations

Abstract

We present a fully-automated segmentation and quantification of the left atrial (LA) fibrosis and scars combining two cardiac MRIs, one is the target late gadolinium-enhanced (LGE) image, and the other is an anatomical MRI from the same acquisition session. We formulate the joint distribution of images using a multivariate mixture model (MvMM), and employ the maximum likelihood estimator (MLE) for texture classification of the images simultaneously. The MvMM can also embed transformations assigned to the images to correct the misregistration. The iterated conditional mode algorithm is adopted for optimization. This method first extracts the anatomical shape of the LA, and then estimates a prior probability map. It projects the resulting segmentation onto the LA surface, for quantification and analysis of scarring. We applied the proposed method to 36 clinical data sets and obtained promising results (Accuracy: $0.809\pm .150$, Dice: $0.556\pm.187$). We compared the method with the conventional algorithms and showed an evidently and statistically better performance ($p<0.03$).