Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 9, 2026

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo
06:43

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

Published on: November 8, 2018

11.1K

Development of an Integrated Deep Learning Approach for Detecting Fetal Brain Abnormalities at Routine Second

Ruben Ramirez Zegarra1,2, Alessandra Familiari3, Andrea Dall'Asta1

  • 1Department of Medicine and Surgery, Obstetrics and Gynaecology Unit, University of Parma, Parma, Italy.

Radiology. Artificial Intelligence
|April 8, 2026
PubMed

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Artificial Intelligence Dystocia Algorithm (AIDA) for Risk Stratification of Occiput Posterior Fetal Head Position.

Journal of imaging·2026
Same author

Intrapartum point-of-care ultrasound for assisting diagnosis of fetal head descending through buttonhole cervical tear.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2026
Same author

Evaluation of fetal anatomy in the first trimester on a national scale: screening and beyond.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2026
Same author

Comparing endometrial preparation protocols and clinical outcomes: lessons learned from 3507 vitrified-warmed euploid transfers.

Journal of assisted reproduction and genetics·2026
Same author

Exploring hemodynamic alterations in gastroschisis: insights into fetal growth restriction using prenatal MRI.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2026
Same author

The MRI two-perfusion IVIM model improves understanding of SARS-CoV-2 virus impact on placental tissue.

Magma (New York, N.Y.)·2026
Same journal

Externally Tested AI for Lung Nodule Classification: A Realistic Benchmark for an Emerging Screening Era.

Radiology. Artificial intelligence·2026
Same journal

Impact of Exposure Parameters on Deep Learning Models in Chest Radiography and Implications for Deployment.

Radiology. Artificial intelligence·2026
Same journal

Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation.

Radiology. Artificial intelligence·2026
Same journal

Benchmarking of AI and Radiologists for Indeterminate Lung Nodule Malignancy Risk Estimation on Screening CT: The LUNA25 Challenge.

Radiology. Artificial intelligence·2026
Same journal

When One Sequence Is Enough-And When It Isn't.

Radiology. Artificial intelligence·2026
Same journal

Cracking the Registration Conundrum in Breast MRI: Preserving the Tumor Signal to Reveal True Treatment Change.

Radiology. Artificial intelligence·2026
See all related articles
Summary
This summary is machine-generated.

A new deep learning pipeline accurately detects fetal brain abnormalities using second-trimester ultrasound images. This AI tool shows high diagnostic performance, aiding in early detection of congenital anomalies.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Fetal Medicine

Background:

  • Second-trimester ultrasound is crucial for fetal anomaly screening.
  • Accurate detection of fetal brain abnormalities remains challenging.
  • Deep learning (DL) offers potential for automated image analysis.

Purpose of the Study:

  • To develop and validate an anatomy-aware, two-stage, end-to-end deep learning (DL) pipeline.
  • To automate the detection of fetal brain abnormalities using standardized second-trimester ultrasound images.
  • To assess the diagnostic performance of the developed DL pipeline.

Main Methods:

  • Retrospective multicenter study with 319 fetal brain images (normal and abnormal).
  • Images acquired between 19+0 and 23+6 weeks of gestation from nine international centers.
Keywords:
Artificial IntelligenceFetal Brain MalformationFetal NeurologyMachine LearningNeural NetworksNeurosonographyYOLOv5

More Related Videos

Murine Fetal Echocardiography
08:04

Murine Fetal Echocardiography

Published on: February 15, 2013

18.3K
State of the Art Cranial Ultrasound Imaging in Neonates
10:02

State of the Art Cranial Ultrasound Imaging in Neonates

Published on: February 2, 2015

26.7K

Related Experiment Videos

Last Updated: Apr 9, 2026

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo
06:43

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

Published on: November 8, 2018

11.1K
Murine Fetal Echocardiography
08:04

Murine Fetal Echocardiography

Published on: February 15, 2013

18.3K
State of the Art Cranial Ultrasound Imaging in Neonates
10:02

State of the Art Cranial Ultrasound Imaging in Neonates

Published on: February 2, 2015

26.7K
  • Developed a two-stage DL pipeline: YOLOv5 object detection followed by Mini-ResNet/HexaNet classification.
  • Performance evaluated using mAP@0.5 for object detection and AUC, sensitivity, specificity, F1-score for classification.

    • Main Results:

    • Object detection model achieved a mean average precision (mAP@0.5) of 0.93.
    • Classification model demonstrated high performance with an area under the receiver operating characteristic curve (AUC) of 0.96.
    • Sensitivity was 87%, specificity 91%, and F1-score 0.84 for distinguishing normal from abnormal fetal brain images.

    Conclusions:

    • The developed anatomy-aware DL pipeline shows high diagnostic performance for fetal brain anomaly detection.
    • This automated approach can aid in routine second-trimester fetal ultrasound screening.
    • The findings support the utility of AI in improving the accuracy and efficiency of prenatal diagnosis.