3D Heart Reconstruction from Sparse Pose-agnostic 2D Echocardiographic Slices

2025-07-03

AI Summary

Conventional 2D echocardiography suffers from sparse view sampling and unknown probe pose, leading to low accuracy in cardiac quantitative assessment—particularly for right ventricular (RV) volume—while 3D echocardiography is limited by low spatial resolution and heavy reliance on manual segmentation. Method: We propose a novel alternating optimization framework that jointly refines slice pose estimation and learns a 3D implicit neural representation of the heart anatomy. Integrating multi-view geometry, learnable shape priors, and implicit neural representations, the method enables end-to-end reconstruction of patient-specific 3D cardiac anatomy from only six standard clinical 2D echocardiographic views. Contribution/Results: To our knowledge, this is the first method enabling accurate RV volume estimation without any 3D scan acquisition. It achieves mean absolute volume errors of 1.98% for the left ventricle (LV) and 5.75% for the RV—substantially outperforming the conventional biplane method (20.24%)—thereby overcoming a fundamental limitation in current 2D echocardiographic quantification.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: State Estimation

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Echocardiography (echo) plays an indispensable role in the clinical practice of heart diseases. However, ultrasound imaging typically provides only two-dimensional (2D) cross-sectional images from a few specific views, making it challenging to interpret and inaccurate for estimation of clinical parameters like the volume of left ventricle (LV). 3D ultrasound imaging provides an alternative for 3D quantification, but is still limited by the low spatial and temporal resolution and the highly demanding manual delineation. To address these challenges, we propose an innovative framework for reconstructing personalized 3D heart anatomy from 2D echo slices that are frequently used in clinical practice. Specifically, a novel 3D reconstruction pipeline is designed, which alternatively optimizes between the 3D pose estimation of these 2D slices and the 3D integration of these slices using an implicit neural network, progressively transforming a prior 3D heart shape into a personalized 3D heart model. We validate the method with two datasets. When six planes are used, the reconstructed 3D heart can lead to a significant improvement for LV volume estimation over the bi-plane method (error in percent: 1.98% VS. 20.24%). In addition, the whole reconstruction framework makes even an important breakthrough that can estimate RV volume from 2D echo slices (with an error of 5.75% ). This study provides a new way for personalized 3D structure and function analysis from cardiac ultrasound and is of great potential in clinical practice.

Problem

• Reconstructs 3D heart anatomy from sparse 2D echo slices
• Improves accuracy of left ventricle volume estimation
• Enables right ventricle volume estimation from 2D slices

Innovation

• 3D reconstruction from 2D echo slices
• Pose estimation and 3D integration
• Implicit neural network optimization