Nurture Map Lab Emory University School of Medicine

Maternal–infant imaging · AI · Neurodevelopment

Tracing the pathways from maternal health to the next generation’s developing brain.

We develop AI and quantitative MRI methods to map how maternal health shapes placental function, fetal physiology, brain development, and early neurobehavior.

Explore our research Collaborate with us

The Nurture Map

生生之谓易《周易·系辞上传》Life is a continuous process of becoming.

  1. 01

    Maternal context

    Metabolic, inflammatory, environmental, and psychosocial health in pregnancy.

  2. Illustration of the placenta and its vessels

    02

    Placenta

    Structure, perfusion, oxygenation, exchange, and molecular signaling.

  3. Illustration of the fetal heart and circulation

    03

    Fetal circulation

    Blood flow, cardiovascular adaptation, and oxygen delivery.

  4. Illustration of the developing brain

    04

    Developing brain

    Structure, tissue maturation, connectivity, and regional growth.

  5. 05

    Early neurobehavior

    Regulation, attention, and social communication in infancy.

K99/R00

NIH Pathway to Independence Award, NICHD

2 R01s

As principal investigator, among 4 active NIH awards

30+

Peer-reviewed publications in imaging, AI, and mental health

Research

Three programs, one pathway.

We combine imaging, machine learning, multi-omics, and longitudinal behavior to build measurable phenotypes and find modifiable pathways for earlier intervention.

01 · Methods

AI for perinatal imaging phenotypes

Learning methods for fetal, placental, newborn, and infant MRI that handle motion, changing anatomy, scanner differences, and limited labels.

How can we recover reliable phenotypes from moving, rapidly changing anatomy?

02 · Mechanisms

Placental and fetal-circulatory pathways

How maternal metabolism, inflammation, stress, medications, and environment shape placental function, fetal hemodynamics, and oxygen delivery.

Where along the maternal–placental–fetal pathway does risk emerge?

03 · Outcomes

From perinatal phenotypes to neurobehavioral risk

Linking imaging phenotypes with regulation, attention, social communication, NICU course, and early psychopathology risk.

Which perinatal phenotypes signal later risk or resilience?

Active NIH support

For families · Now recruiting in Atlanta

Join the MOON Study

We follow families from pregnancy through baby’s first year to learn how a mother’s health, the placenta, and early brain development are connected.

Learn about joining

Contacting us doesn’t enroll you, and taking part is always voluntary.

Also recruiting, in Durham, NC: the MOMMA Study at Duke University

People

Our team

An interdisciplinary team spanning machine learning, MRI, and maternal–infant health, working with clinical partners across Atlanta and beyond.

Principal investigator

Yun Wang, Ph.D.

Tenure-track Assistant Professor of Biomedical Informatics, Emory University School of Medicine

Secondary appointments in Gynecology & Obstetrics and Radiology & Imaging Sciences · NIH K99/R00 Pathway to Independence awardee · Standing member, NIH NICHD study section

Full profile yun.wang2@emory.edu

Ruiying Liu, Ph.D.

Postdoctoral Fellow

Segmentation, motion correction, foundation models

Award · ASPNR Erin & Darren Schwartz Research Scientist Travel Grant, 2026

First author · NeuroLangSeg, MIDL 2026

Clinical & research partners

  • Children’s Healthcare of AtlantaPediatric radiology
  • Duke UniversityMOMMA Study
  • Western UniversityPlacental MRI
  • NIH ARISEN NetworkU54 research network

Methods & software

Tools built for moving, growing anatomy.

Platform · 2022

FINNEAS

Privacy-preserving, cloud-based infant MRI analysis that needs no programming.

Platform

CVPR 2024

MAPSeg

Unified domain adaptation for heterogeneous 3D medical image segmentation.

Paper Code

MIDL 2026

NeuroLangSeg

Language-guided subcortical segmentation with anatomical–linguistic validation.

Paper Code

MIDL 2026

Fetal MRI super-resolution

Orientation-aware diffusion models that recover 3T-like detail from routine 1.5T scans.

Paper

MICCAI PIPPI 2025

Placental MRI phenotyping

Contrast-invariant self-supervised segmentation for reproducible placental measurement.

Paper

IEEE TMI 2022

PTNet3D

A 3D transformer for high-resolution longitudinal infant brain MRI synthesis.

Paper Code

Publications

Selected work

Lab members in bold

  1. 2026
    NeuroLangSeg: Language-Guided Subcortical Segmentation with Pseudo-Supervision and Anatomical–Linguistic Validation

    Liu, R., Liu, J., Zhang, X., Huang, C., & Wang, Y. · Medical Imaging with Deep Learning

  2. 2026
    Orientation-Aware Diffusion Super-Resolution for 3T-Like Fetal MRI from Routine 1.5T Scans

    Zhong, X., Liu, R., Lin, G., Huang, C., Goldman-Yassen, A., Mehollin-Ray, A., & Wang, Y. · Medical Imaging with Deep Learning

  3. 2026
    A Two-Stage Multi-Modal MRI Framework for Lifespan Brain Age Prediction

    Zhang, D., Liu, R., & Wang, Y. · Medical Imaging with Deep Learning

  4. 2025
    Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI

    Zhong, X., Liu, R., Nichols, E. S., Zhang, X., Laine, A. F., Duerden, E. G., & Wang, Y. · MICCAI PIPPI

  5. 2025
    Prediction of Mental Health Risk in Adolescents

    Hill, E. D., Kashyap, P., Raffanello, E., Wang, Y., Moffitt, T. E., Caspi, A., Engelhard, M., & Posner, J. · Nature Medicine

  6. 2024
    MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling

    Zhang, X., Wu, Y., Angelini, E., Li, A., Guo, J., Rasmussen, J. M., O’Connor, T. G., Wadhwa, P. D., Jackowski, A. P., Li, H., Posner, J., Laine, A. F., & Wang, Y. · CVPR

Full list on ORCID →

News

Recently