Deep Sequence Learning for Accurate Gestational Age Estimation from a $\$$25 Doppler Device

TL;DR

This paper introduces a low-cost, smartphone-based Doppler method utilizing deep sequence learning to accurately estimate gestational age, potentially expanding access to fetal development assessment in resource-limited settings.

Contribution

It presents a novel low-cost Doppler device combined with a convolutional LSTM model for precise gestational age estimation from smartphone-collected data.

Findings

Mean absolute GA error of 0.71 months, outperforming previous methods.

Effective use of time-frequency features in Doppler signals.

Feasibility of smartphone-based fetal development assessment.

Abstract

Assessing fetal development is usually carried out by techniques such as ultrasound imaging, which is generally unavailable in rural areas due to the high cost, maintenance, skills and training needed to operate the devices effectively. In this work, we propose a low-cost one-dimensional Doppler-based method for estimating gestational age (GA). Doppler time series were collected from 401 pregnancies between 5 and 9 months GA using a smartphone. The proposed model for GA estimation is based on sequence learning by forming a temporally dependent model using a convolutional long-short-term memory network. Time-frequency features are extracted from Doppler signals and regularized before feeding to the network. The overall mean absolute GA error with respect to the last menstrual period was found to be 0.71 month, which outperforms all previous works.