Attention-guided deep learning for gestational age prediction using fetal brain MRI

Liyue Shen; Jimmy Zheng; Edward H Lee; Katie Shpanskaya; Emily S McKenna; Mahesh G Atluri; Dinko Plasto; Courtney Mitchell; Lillian M Lai; Carolina V Guimaraes; Hisham Dahmoush; Jane Chueh; Safwan S Halabi; John M Pauly; Lei Xing; Quin Lu; Ozgur Oztekin; Beth M Kline-Fath; Kristen W Yeom

doi:10.1038/s41598-022-05468-5

Back

Attention-guided deep learning for gestational age prediction using fetal brain MRI

Journal article

Open access

Peer reviewed

Attention-guided deep learning for gestational age prediction using fetal brain MRI

Liyue Shen, Jimmy Zheng, Edward H Lee, Katie Shpanskaya, Emily S McKenna, Mahesh G Atluri, Dinko Plasto, Courtney Mitchell, Lillian M Lai, Carolina V Guimaraes, …

Scientific reports, Vol.12(1), pp.1408-1408

01/26/2022

DOI: 10.1038/s41598-022-05468-5

PMCID: PMC8791965

PMID: 35082346

Files and links (1)

url

https://doi.org/10.1038/s41598-022-05468-5View

Published (Version of record) Open Access

Abstract

Magnetic resonance imaging offers unrivaled visualization of the fetal brain, forming the basis for establishing age-specific morphologic milestones. However, gauging age-appropriate neural development remains a difficult task due to the constantly changing appearance of the fetal brain, variable image quality, and frequent motion artifacts. Here we present an end-to-end, attention-guided deep learning model that predicts gestational age with R score of 0.945, mean absolute error of 6.7 days, and concordance correlation coefficient of 0.970. The convolutional neural network was trained on a heterogeneous dataset of 741 developmentally normal fetal brain images ranging from 19 to 39 weeks in gestational age. We also demonstrate model performance and generalizability using independent datasets from four academic institutions across the U.S. and Turkey with R scores of 0.81-0.90 after minimal fine-tuning. The proposed regression algorithm provides an automated machine-enabled tool with the potential to better characterize in utero neurodevelopment and guide real-time gestational age estimation after the first trimester.

Artifacts

Brain - diagnostic imaging

Brain - growth & development

Datasets as Topic

Deep Learning

Female

Fetus

Gestational Age

Humans

Image Processing, Computer-Assisted - statistics & numerical data

Magnetic Resonance Imaging - methods

Magnetic Resonance Imaging - standards

Neuroimaging - methods

Neuroimaging - standards

Pregnancy

Pregnancy Trimesters - physiology

Turkey

United States

Details

Title: Subtitle: Attention-guided deep learning for gestational age prediction using fetal brain MRI
Creators: Liyue Shen - Stanford University
Jimmy Zheng - Stanford University
Edward H Lee - Stanford University
Katie Shpanskaya - Lucile Packard Children's Hospital
Emily S McKenna - Lucile Packard Children's Hospital
Mahesh G Atluri - Lucile Packard Children's Hospital
Dinko Plasto - St. Joseph's Hospital and Medical Center
Courtney Mitchell - St. Joseph's Hospital and Medical Center
Lillian M Lai - Children's Hospital of Los Angeles
Carolina V Guimaraes - Lucile Packard Children's Hospital
Hisham Dahmoush - Lucile Packard Children's Hospital
Jane Chueh - Lucile Packard Children's Hospital
Safwan S Halabi - Lucile Packard Children's Hospital
John M Pauly - Stanford University
Lei Xing - Stanford University
Quin Lu - Philips Healthcare North America, Gainesville, USA.
Ozgur Oztekin - Korean Council for University Education
Beth M Kline-Fath - Cincinnati Children's Hospital Medical Center
Kristen W Yeom - Lucile Packard Children's Hospital
Resource Type: Journal article
Publication Details: Scientific reports, Vol.12(1), pp.1408-1408
DOI: 10.1038/s41598-022-05468-5
PMID: 35082346
PMCID: PMC8791965
NLM abbreviation: Sci Rep
ISSN: 2045-2322
eISSN: 2045-2322
Language: English
Date published: 01/26/2022
Academic Unit: Radiology
Record Identifier: 9984318781102771

Metrics

40 Record Views

31 Times Cited - Web of Science

See more details