Structure learning in random fields for heart motion abnormality detection

TLDR

Coronary heart disease diagnosis relies on assessing regional heart wall motion in left‑ventricle ultrasound, yet expert interpretation is challenging and intra‑observer variability is high, underscoring the need to model interactions among heart regions. The study aims to jointly learn the structure and parameters of conditional random fields for detecting heart motion abnormalities. This is achieved by formulating the learning as a convex optimization problem with block‑L1 regularization, employing an efficient projection method to obtain the globally optimal penalized maximum‑likelihood solution, and validating the approach through extensive numerical experiments and real‑world echocardiogram data.

Abstract

Coronary Heart Disease can be diagnosed by assessing the regional motion of the heart walls in ultrasound images of the left ventricle. Even for experts, ultrasound images are difficult to interpret leading to high intra-observer variability. Previous work indicates that in order to approach this problem, the interactions between the different heart regions and their overall influence on the clinical condition of the heart need to be considered. To do this, we propose a method for jointly learning the structure and parameters of conditional random fields, formulating these tasks as a convex optimization problem. We consider block-L1 regularization for each set of features associated with an edge, and formalize an efficient projection method to find the globally optimal penalized maximum likelihood solution. We perform extensive numerical experiments comparing the presented method with related methods that approach the structure learning problem differently. We verify the robustness of our method on echocardiograms collected in routine clinical practice at one hospital.