FetalNet: Multi-task Deep Learning Framework for Fetal Ultrasound Biometric Measurements

TL;DR

FetalNet is an innovative multi-task deep learning framework that analyzes fetal ultrasound videos to accurately localize, classify, and measure fetal body parts, improving over existing methods by incorporating spatio-temporal features and attention mechanisms.

Contribution

The paper introduces FetalNet, a novel end-to-end multi-task neural network with attention and stacked modules for comprehensive fetal ultrasound video analysis, addressing limitations of single-image methods.

Findings

FetalNet outperforms existing methods in classification accuracy.

FetalNet achieves superior segmentation performance.

The model effectively localizes scan planes in ultrasound videos.

Abstract

In this paper, we propose an end-to-end multi-task neural network called FetalNet with an attention mechanism and stacked module for spatio-temporal fetal ultrasound scan video analysis. Fetal biometric measurement is a standard examination during pregnancy used for the fetus growth monitoring and estimation of gestational age and fetal weight. The main goal in fetal ultrasound scan video analysis is to find proper standard planes to measure the fetal head, abdomen and femur. Due to natural high speckle noise and shadows in ultrasound data, medical expertise and sonographic experience are required to find the appropriate acquisition plane and perform accurate measurements of the fetus. In addition, existing computer-aided methods for fetal US biometric measurement address only one single image frame without considering temporal features. To address these shortcomings, we propose an end-to-end multi-task neural network for spatio-temporal ultrasound scan video analysis to simultaneously localize, classify and measure the fetal body parts. We propose a new encoder-decoder segmentation architecture that incorporates a classification branch. Additionally, we employ an attention mechanism with a stacked module to learn salient maps to suppress irrelevant US regions and efficient scan plane localization. We trained on the fetal ultrasound video comes from routine examinations of 700 different patients. Our method called FetalNet outperforms existing state-of-the-art methods in both classification and segmentation in fetal ultrasound video recordings.