EnLVAM: Enhanced Left Ventricle Linear Measurements Utilizing Anatomical Motion Mode

TL;DR

This paper introduces EnLVAM, a framework that improves left ventricle measurements in echocardiography by enforcing anatomical constraints and using real-time AMM images, reducing errors and simplifying clinical workflow.

Contribution

The novel framework enhances LV measurement accuracy by integrating anatomical motion mode images and straight-line constraints, addressing misalignment issues in deep learning methods.

Findings

Improved measurement accuracy over standard B-mode methods

Framework generalizes across different network architectures

Semi-automatic design with minimal user interaction

Abstract

Linear measurements of the left ventricle (LV) in the Parasternal Long Axis (PLAX) view using B-mode echocardiography are crucial for cardiac assessment. These involve placing 4-6 landmarks along a virtual scanline (SL) perpendicular to the LV axis near the mitral valve tips. Manual placement is time-consuming and error-prone, while existing deep learning methods often misalign landmarks, causing inaccurate measurements. We propose a novel framework that enhances LV measurement accuracy by enforcing straight-line constraints. A landmark detector is trained on Anatomical M-Mode (AMM) images, computed in real time from B-mode videos, then transformed back to B-mode space. This approach addresses misalignment and reduces measurement errors. Experiments show improved accuracy over standard B-mode methods, and the framework generalizes well across network architectures. Our semi-automatic design includes a human-in-the-loop step where the user only places the SL, simplifying interaction while preserving alignment flexibility and clinical relevance.