Learning deep architectures for the interpretation of first-trimester fetal echocardiography (LIFE) - a study protocol for developing an automated intelligent decision support system for early fetal echocardiography

Abstract

Background: Congenital Heart Disease represents the most frequent fetal malformation. The lack of prenatal identification of congenital heart defects can have adverse consequences for the neonate, while a correct prenatal diagnosis of specific cardiac anomalies improves neonatal care neurologic and surgery outcomes. Sonographers perform prenatal diagnosis manually during the first or second-trimester scan, but the reported detection rates are low. This project's primary objective is to develop an Intelligent Decision Support System that uses two-dimensional video files of cardiac sweeps obtained during the standard first-trimester fetal echocardiography (FE) to signal the presence/absence of previously learned key features.

Methods: The cross-sectional study will be divided into a training part of the machine learning approaches and the testing phase on previously unseen frames and eventually on actual video scans. Pregnant women in their 12-13 + 6 weeks of gestation admitted for routine first-trimester anomaly scan will be consecutively included in a two-year study, depending on the availability of the experienced sonographers in early fetal cardiac imaging involved in this research. The Data Science / IT department (DSIT) will process the key planes identified by the sonographers in the two- dimensional heart cine loop sweeps: four-chamber view, left and right ventricular outflow tracts, three vessels, and trachea view. The frames will be grouped into the classes representing the plane views, and then different state-of-the- art deep-learning (DL) pre-trained algorithms will be tested on the data set. The sonographers will validate all the intermediary findings at the frame level and the meaningfulness of the video labeling.

Discussion: FE is feasible and efficient during the first trimester. Still, the continuous training process is impaired by the lack of specialists or their limited availability. Therefore, in our study design, the sonographer benefits from a second opinion provided by the developed software, which may be very helpful, especially if a more experienced colleague is unavailable. In addition, the software may be implemented on the ultrasound device so that the process could take place during the live examination.

Trial registration: The study is registered under the name "Learning deep architectures for the Interpretation of Fetal Echocardiography (LIFE)", project number 408PED/2020, project code PN-III-P2-2.1-PED-2019.

Trial registration: ClinicalTrials.gov , unique identifying number NCT05090306, date of registration 30.10.2020.

Keywords: Artificial intelligence; Decision support systems; Echocardiography; Fetal cardiology.

Fig. 1

Examples of the four key-planes visualized during the first-trimester fetal heart sweep in apical view (A-D) and lateral view (E-H). From top to bottom (each on one row): the parallel atrioventricular flows in four-chamber view plane (A,E), the aortic flow in left ventricle outflow tract view (B,F), the X-sign – crossing of the arterial arches (C,G), and the V-sign, in the three-vessel plane (D,H)

Fig. 2

Workflow overview of the entire protocol. US videos are separated into frames, from which human experts assign the key planes to the four different categories. Data are anonymized, non-important frames are added as a distinct category of images, the model is trained on the obtained image data set and will then classify frames in new US videos and generate reports

Fig. 3

Examples in which background is removed from the initial image (A), intermediary images are obtained for one side (B-F), and either both views are kept (G), or the Doppler color side is used alone (H)