Predicting Pulmonary Hypertension in Newborns: A Multi-view VAE Approach

TL;DR

This paper introduces a multi-view VAE model that enhances the accuracy and robustness of pulmonary hypertension detection in newborns using echocardiographic videos, addressing limitations of previous single-view approaches.

Contribution

The study presents a novel multi-view VAE framework for neonatal PH prediction, improving generalization and feature extraction over existing single-view models.

Findings

Improved classification accuracy over baseline models

Enhanced generalization to diverse echocardiographic views

Robust feature representations for neonatal PH detection

Abstract

Pulmonary hypertension (PH) in newborns is a critical condition characterized by elevated pressure in the pulmonary arteries, leading to right ventricular strain and heart failure. While right heart catheterization (RHC) is the diagnostic gold standard, echocardiography is preferred due to its non-invasive nature, safety, and accessibility. However, its accuracy highly depends on the operator, making PH assessment subjective. While automated detection methods have been explored, most models focus on adults and rely on single-view echocardiographic frames, limiting their performance in diagnosing PH in newborns. While multi-view echocardiography has shown promise in improving PH assessment, existing models struggle with generalizability. In this work, we employ a multi-view variational autoencoder (VAE) for PH prediction using echocardiographic videos. By leveraging the VAE framework, our model captures complex latent representations, improving feature extraction and robustness. We compare its performance against single-view and supervised learning approaches. Our results show improved generalization and classification accuracy, highlighting the effectiveness of multi-view learning for robust PH assessment in newborns.