Developing and Testing AI Models for Fetal Biometry and Amniotic Volume Assessment in Fetal Ultrasound Scans.

NCT05059093 | Completed

• 1 other identifier: U1111-1268-5186
• Study Type: observational
• Target: 122
• Locations: 1 country
• Sites: 6

Brief Summary

Routine fetal ultrasound scan during the second trimester of the pregnancy is a low-cost, noninvasive screening modality that has been proven to lower fetal mortality by up to 20%. One of the critical elements of this exam is the measurement of fetal biometric parameters, which are the head circumference (HC), biparietal diameter (BPD), abdominal circumference (AC), and femur length (FL) measured on biometry standard planes. Those standard planes are taken according to quality standards first described by Salomon et al. and used as the guidelines of the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG). The biometric parameters extracted from them are essential to diagnose fetal growth restriction (FGR), the world's first cause of perinatal fetal mortality. Such measurements and image quality assessment are time-consuming tasks that are prone to inter and intraobserver variability depending on the level of skill of the sonographer or the physician performing the exam. Amniotic fluid (AF) volume assessment is also an essential step in routine screening scans allowing the diagnosis of oligo or hydramnios, both associated with increased fetal mortality rates. The AF is measured by two main "semi-quantitative" techniques: Amniotic Fluid Index (AFI) and the single deepest pocket (SDP). The latter is more specific as it lowers the overdiagnosis of oligo-amnios without any impact on mortality or morbidity and is easier to perform for the sonographer (only one measurement versus four in the case of the AFI technique). However, AF assessment remains a time-consuming and poorly reproducible task. Attempts to automate such biometric measurements and AF volume assessment have been made using Artificial Intelligence (AI) and deep learning (DL) tools. Studies showed excellent results "in silico," reaching up to 98 %, 95%, 93 % dice score coefficients for HC, AC, and FL measurements and 89 % DSC for AFI measurements. However, they were all conducted retrospectively without validation on prospectively acquired images. Reviews and experts have stressed the need for quality peer-reviewed prospective studies to assess AI tools' performance with real-world data. Their performance is expected to be worse and to reflect better their use in the clinical workflow. This study aims to develop DL models to automate HC, BPD, AC, and FL measurements and AF volume assessment from retrospectively acquired data and test their performances to those of clinicians and experts on prospective real-world fetal US scans.

Conditions

Small for Gestational Age Infant; Fetal Growth Restriction; Oligohydramnios; Polyhydramnios

Keywords

Deep Learning; Artificial Intelligence; Fetal Ultrasound; Fetal Biometry; Amniotic Fluid Volume Measurement

Outcome Measures

Primary Outcomes (1)

• Overall accuracy for the biometric parameters measurement and amniotic fluid volume assessment

  Mean Absolute Error between the model's HC, BPD, AC, FL, and SDP measurements (in mm), the RT clinician's, and the panel's

  up to 20 weeks

Secondary Outcomes (3)

• Image quality

  Up to 20 weeks

• Small-for-Gestational-Age fetus detection accuracy, sensitivity and specificity

  Up to 20 weeks

• Oligohydramnios and polyhydramnios detection accuracy, sensitivity, and specificity

  Up to 20 weeks

Interventions

Classification and segmentation deep learning models DIAGNOSTIC_TEST

Models that will be trained on retrospectively acquired data and run on the prospectively acquired data to extract biometric parameters and amniotic volume estimation.

Eligibility Criteria

• Age: 18 Years+
• Sex: female
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Pregnant women from 18 years onwards scheduled for a routine fetal ultrasound scan

You may qualify if:

• Single or multiple viable pregnancies with a gestational age of 14 weeks or more as dated on a first trimester US scan with the crown-rump length (CRL) measurement or grossly estimated from the last menstrual period (LMP).
• Routine programmed US scan.
• Patient's consent is obtained.
• Patient over 18 years old.

You may not qualify if:

• Emergency indication for the fetal ultrasound
• Major morphological malformations that do not allow proper measurement of the cranium, abdominal or lower limb, for example, anencephaly, omphalocele, lower limb phocomelia.
• Fetal death.

Sponsors & Collaborators

• Deepecho: lead
• Centre Hospitalier Universitaire Ibn Rochd: collaborator
• Hassan II University: collaborator
• Mohammed VI University Hospital: collaborator
• Mohammed V Souissi University: collaborator

Study Sites (6)

Centre de Radiologie Abou Madi

Casablanca, 20100, Morocco

Location

Centre Hospitalier Cheikh Khalifa

Casablanca, 20100, Morocco

Location

Centre Hospitalier Universitaire Ibn Rochd

Casablanca, 20100, Morocco

Location

Mohamed VI University International Hospital

Casablanca, 27182, Morocco

Location

Centre Hospitalier Universitaire Hassan II Fes

Fes, Morocco

Location

Centre Hospitalier Universitaire Mohammed VI Oujda

Oujda, Morocco

Location

Related Publications (15)

• Grytten J, Skau I, Sorensen R, Eskild A. Does the Use of Diagnostic Technology Reduce Fetal Mortality? Health Serv Res. 2018 Dec;53(6):4437-4459. doi: 10.1111/1475-6773.12721. Epub 2018 Jan 19.

  PMID: 29349772 BACKGROUND

• Salomon LJ, Alfirevic Z, Berghella V, Bilardo C, Hernandez-Andrade E, Johnsen SL, Kalache K, Leung KY, Malinger G, Munoz H, Prefumo F, Toi A, Lee W; ISUOG Clinical Standards Committee. Practice guidelines for performance of the routine mid-trimester fetal ultrasound scan. Ultrasound Obstet Gynecol. 2011 Jan;37(1):116-26. doi: 10.1002/uog.8831. No abstract available.

  PMID: 20842655 BACKGROUND

• Gaudineau A. [Prevalence, risk factors, maternal and fetal morbidity and mortality of intrauterine growth restriction and small-for-gestational age]. J Gynecol Obstet Biol Reprod (Paris). 2013 Dec;42(8):895-910. doi: 10.1016/j.jgyn.2013.09.013. Epub 2013 Nov 9. French.

  PMID: 24216305 BACKGROUND

• Sarris I, Ioannou C, Chamberlain P, Ohuma E, Roseman F, Hoch L, Altman DG, Papageorghiou AT; International Fetal and Newborn Growth Consortium for the 21st Century (INTERGROWTH-21st). Intra- and interobserver variability in fetal ultrasound measurements. Ultrasound Obstet Gynecol. 2012 Mar;39(3):266-73. doi: 10.1002/uog.10082.

  PMID: 22535628 BACKGROUND

• Tashfeen K, Hamdi IM. Polyhydramnios as a predictor of adverse pregnancy outcomes. Sultan Qaboos Univ Med J. 2013 Feb;13(1):57-62. doi: 10.12816/0003196. Epub 2013 Feb 27.

  PMID: 23573383 BACKGROUND

• Morris RK, Meller CH, Tamblyn J, Malin GM, Riley RD, Kilby MD, Robson SC, Khan KS. Association and prediction of amniotic fluid measurements for adverse pregnancy outcome: systematic review and meta-analysis. BJOG. 2014 May;121(6):686-99. doi: 10.1111/1471-0528.12589. Epub 2014 Feb 7.

  PMID: 24738894 BACKGROUND

• Kehl S, Schelkle A, Thomas A, Puhl A, Meqdad K, Tuschy B, Berlit S, Weiss C, Bayer C, Heimrich J, Dammer U, Raabe E, Winkler M, Faschingbauer F, Beckmann MW, Sutterlin M. Single deepest vertical pocket or amniotic fluid index as evaluation test for predicting adverse pregnancy outcome (SAFE trial): a multicenter, open-label, randomized controlled trial. Ultrasound Obstet Gynecol. 2016 Jun;47(6):674-9. doi: 10.1002/uog.14924.

  PMID: 26094600 BACKGROUND

• Sande JA, Ioannou C, Sarris I, Ohuma EO, Papageorghiou AT. Reproducibility of measuring amniotic fluid index and single deepest vertical pool throughout gestation. Prenat Diagn. 2015 May;35(5):434-9. doi: 10.1002/pd.4504. Epub 2015 Mar 28.

  PMID: 25297394 BACKGROUND

• Li Y, Zhang Z, Dai C, Dong Q, Badrigilan S. Accuracy of deep learning for automated detection of pneumonia using chest X-Ray images: A systematic review and meta-analysis. Comput Biol Med. 2020 Aug;123:103898. doi: 10.1016/j.compbiomed.2020.103898. Epub 2020 Jul 14.

  PMID: 32768045 BACKGROUND

• Dhar R, Falcone GJ, Chen Y, Hamzehloo A, Kirsch EP, Noche RB, Roth K, Acosta J, Ruiz A, Phuah CL, Woo D, Gill TM, Sheth KN, Lee JM. Deep Learning for Automated Measurement of Hemorrhage and Perihematomal Edema in Supratentorial Intracerebral Hemorrhage. Stroke. 2020 Feb;51(2):648-651. doi: 10.1161/STROKEAHA.119.027657. Epub 2019 Dec 6.

  PMID: 31805845 BACKGROUND

• Sekhar A, Biswas S, Hazra R, Sunaniya AK, Mukherjee A, Yang L. Brain Tumor Classification Using Fine-Tuned GoogLeNet Features and Machine Learning Algorithms: IoMT Enabled CAD System. IEEE J Biomed Health Inform. 2022 Mar;26(3):983-991. doi: 10.1109/JBHI.2021.3100758. Epub 2022 Mar 7.

  PMID: 34324425 BACKGROUND

• Kim HP, Lee SM, Kwon JY, Park Y, Kim KC, Seo JK. Automatic evaluation of fetal head biometry from ultrasound images using machine learning. Physiol Meas. 2019 Jul 1;40(6):065009. doi: 10.1088/1361-6579/ab21ac.

  PMID: 31091515 BACKGROUND

• Sobhaninia Z, Rafiei S, Emami A, Karimi N, Najarian K, Samavi S, Reza Soroushmehr SM. Fetal Ultrasound Image Segmentation for Measuring Biometric Parameters Using Multi-Task Deep Learning. Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:6545-6548. doi: 10.1109/EMBC.2019.8856981.

  PMID: 31947341 BACKGROUND

• Cho HC, Sun S, Min Hyun C, Kwon JY, Kim B, Park Y, Seo JK. Automated ultrasound assessment of amniotic fluid index using deep learning. Med Image Anal. 2021 Apr;69:101951. doi: 10.1016/j.media.2020.101951. Epub 2021 Jan 7.

  PMID: 33515982 BACKGROUND

• Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019 Oct 29;17(1):195. doi: 10.1186/s12916-019-1426-2.

  PMID: 31665002 BACKGROUND

Related Links

• Ultrasound assessment of fetal biometry and growth ISUOG Guidelines

MeSH Terms

Conditions

Fetal Growth Retardation; Oligohydramnios; Polyhydramnios

Condition Hierarchy (Ancestors)

Fetal Diseases; Pregnancy Complications; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Growth Disorders; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Saad Slimani, M.D.

  Centre Hospitalier Universitaire Ibn Rochd de Casablanca

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 7, 2021
• First Posted: September 28, 2021
• Study Start: October 25, 2021
• Primary Completion: April 1, 2022
• Study Completion: April 1, 2022
• Last Updated: July 27, 2022

Record last verified: 2022-07

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, CSR
• Time Frame: Immediately the following publication, 12 months following article publication
• Access Criteria: Review purposes only. Proposal should be directed to saad.slimani@deepecho.io. To gain access, data requestors will need to sign a data access agreement.

Locations

MO (6)