NCT05790473: AIRFRAME

Artificial Intelligence Algorithm for the Screening of Abnormal Fetal Brain Findings at First Trimester Ultrasound Scan

Status unknown Last updated 22 March 2024

What this trial tests

trial testing Artificial Intelligence in Fetal Anomaly in 10,000 participants. Status unknown.

Timeline

1 May 2023

Primary endpoint
1 May 2024

1 May 2025

Quick facts

Lead sponsor	Fondazione Policlinico Universitario Agostino Gemelli IRCCS
Status	Status unknown
Study type	OBSERVATIONAL
Enrollment	10,000
Start date	1 May 2023
Primary completion	1 May 2024
Estimated completion	1 May 2025
Sites	1 location across Italy

Drugs / interventions tested

• Artificial Intelligence

Conditions studied

• Fetal Anomaly — all drugs for Fetal Anomaly →
• Brain Malformation — all drugs for Brain Malformation →

Sponsor

Fondazione Policlinico Universitario Agostino Gemelli IRCCS

Who can join

Adults 18 to 45, female only, with Fetal Anomaly or Brain Malformation. Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

Visualization of the posterior fossa brain spaces, their spatial relationship and measurements can be obtained in the midsagittal view of fetal head, the same used for NT measurement (9), and plays an important role in the early diagnosis of neural tube defects, such as open spinal dysraphism (5), and posterior fossa anomalies, such as DWM or BPC (7). However, assessment of the fetal posterior fossa in the first trimester is still challenging due to several limitations including involuntary movements of the fetus and small size of the brain structures, causing difficulties for examination and misdiagnosis. Moreover, it is also operator-dependent for the acquirement of high-quality ultrasound images, standard measurements, and precise diagnosis.

The use of new technologies to improve the acquisition of images, to help automatically perform measurements, or aid in the diagnosis of fetal abnormalities, may be of great importance for the optimal assessment of the fetal brain, particularly in the first trimester (10). Artificial intelligence (AI) is described as the ability of a computer program to perform processes associated with human intelligence, such as learning, thinking and problem-solving. Deep Learning (DL), a subset of Machine Learning (ML), is a branch of AI, defined by the ability to learn features automatically from data without human intervention. In DL, the input and output are connected by multiple layers loosely modeled on the neural pathways of the human brain. In the image recognition field, one of the most promising type of DL networks is represented by convolutional neural networks (CNN). These are designed to extract highly representative image features in a fully automated way, which makes them applicable to diagnostic decision-making.

According to these observations, we propose a research project aimed to develop an ultrasound-based AI-algorithm, which is capable to assess the fetal posterior fossa structures during the first trimester ultrasound scan and discriminate between normal and abnormal findings through a fully automatic data processing.

Publications & conference data

No peer-reviewed publications indexed yet for this trial.