Multiview and Multiclass Image Segmentation using Deep Learning in Fetal Echocardiography

TL;DR

This paper introduces a deep learning framework for comprehensive fetal heart structure segmentation in ultrasound images, improving prenatal CHD detection by handling multiple views and missing structures.

Contribution

It presents a novel multi-view, multi-structure segmentation method using an enhanced V-Net that is robust to missing labels and applicable to various fetal echocardiogram views.

Findings

Achieved an average Dice score of 79% across 14 structures.

Enhanced V-Net with spatial dropout, group normalization, and deep supervision.

Framework effectively handles missing labels and abnormalities in fetal echocardiograms.

Abstract

Congenital heart disease (CHD) is the most common congenital abnormality associated with birth defects in the United States. Despite training efforts and substantial advancement in ultrasound technology over the past years, CHD remains an abnormality that is frequently missed during prenatal ultrasonography. Therefore, computer-aided detection of CHD can play a critical role in prenatal care by improving screening and diagnosis. Since many CHDs involve structural abnormalities, automatic segmentation of anatomical structures is an important step in the analysis of fetal echocardiograms. While existing methods mainly focus on the four-chamber view with a small number of structures, here we present a more comprehensive deep learning segmentation framework covering 14 anatomical structures in both three-vessel trachea and four-chamber views. Specifically, our framework enhances the V-Net with spatial dropout, group normalization, and deep supervision to train a segmentation model that can be applied on both views regardless of abnormalities. By identifying the pitfall of using the Dice loss when some labels are unavailable in some images, this framework integrates information from multiple views and is robust to missing structures due to anatomical anomalies, achieving an average Dice score of 79%.