Title: Volume-based analysis of 6-month infant brain MRI for autism biomarker identification and early diagnosis Autism spectrum disorder (ASD) is a complex developmental disability, characterized by deficits in social interaction, language skills, repetitive stereotyped behaviors, and restricted interests. Based on a new government survey, it shows 1 in 45 children (ages 3 to 17) are diagnosed with ASD, a significant increase from Centers for Disease Control and Prevention's previously estimated prevalence of 1 in 68 from 2011-2013. Volume-based analysis of neuroimaging data is playing an increasingly critical role in adult autism studies, and has revealed widespread structural and functional abnormalities. However, existing volume-based analysis tools developed for adult brains are ill-suited for infant studies, due to great challenges in brain tissue segmentation and ROI labeling, caused by the extremely low tissue contrast. To become an independent investigator on infant neuroimaging research, the candidate proposes in this K01 application to receive training in clinical phenomenology and child developmental cognitive neuroscience of children with ASD, developmental neurobiology and neurodevelopmental disorders, and biostatistics. These training activities will greatly augment the candidate's background in ASD, infant neuroimaging mapping and establish a solid foundation for his long-term goal of being a leading researcher on developing imaging-based early biological markers for autism. In the research plan, the candidate will create a unique suite of infant-specific, volume-based neuroimaging analysis tools that enable accurate characterization of early brain development in autistic infants, as well as improved capabilities in early identification of biomarkers and early diagnosis of at-risk infants. Specifically, a new method for unified skull stripping and tissue segmentation will be developed (Aim 1). Also, a new atlas-guided multi-channel forest learning will be proposed for ROI labeling (Aim 2). With the accurate tissue segmentation and ROI labeling, ROI-based volume measurements will be performed and used to identify early indicators or biomarker of risk for autism (Aim 3). Finally, early diagnosis of infants will be performed (Aim 4). Results from this research will help identify early biomarkers of risk for autism and also design targeted preemptive intervention strategies. All created tools and atlases will be integrated and released freely to the public, such as through NITRC (www.nitrc.org).

Public Health Relevance

This project aims to create a unique suite of infant-specific, volume-based neuroimaging analysis tools for accurate characterization of early brain development in both typically developing infants and the autistic infants. In particular, we will develop novel methods for accurate skull stripping, tissue segmentation and region of interest (ROI) labeling. Then, we will perform volume-based analysis on 6-month-old infants with autism and further identify the related imaging biomarkers. Finally, we will perform early diagnosis on infant subjects.

Agency
National Institute of Health (NIH)
Institute
National Institute of Mental Health (NIMH)
Type
Research Scientist Development Award - Research & Training (K01)
Project #
5K01MH109773-04
Application #
9829113
Study Section
Special Emphasis Panel (ZRG1)
Program Officer
Bechtholt, Anita J
Project Start
2017-01-15
Project End
2020-12-31
Budget Start
2020-01-01
Budget End
2020-12-31
Support Year
4
Fiscal Year
2020
Total Cost
Indirect Cost
Name
University of North Carolina Chapel Hill
Department
Biochemistry
Type
Schools of Medicine
DUNS #
608195277
City
Chapel Hill
State
NC
Country
United States
Zip Code
27599
Xia, Jing; Zhang, Caiming; Wang, Fan et al. (2018) A COMPUTATIONAL METHOD FOR LONGITUDINAL MAPPING OF ORIENTATION-SPECIFIC EXPANSION OF CORTICAL SURFACE AREA IN INFANTS. Proc IEEE Int Symp Biomed Imaging 2018:683-686
Li, Guannan; Liu, Mingxia; Sun, Quansen et al. (2018) Early Diagnosis of Autism Disease by Multi-channel CNNs. Mach Learn Med Imaging 11046:303-309
Meng, Yu; Li, Gang; Wang, Li et al. (2018) Discovering cortical sulcal folding patterns in neonates using large-scale dataset. Hum Brain Mapp :
Wu, Zhengwang; Li, Gang; Wang, Li et al. (2018) CONSTRUCTION OF SPATIOTEMPORAL NEONATAL CORTICAL SURFACE ATLASES USING A LARGE-SCALE DATASET. Proc IEEE Int Symp Biomed Imaging 2018:1056-1059
Wang, Fan; Lian, Chunfeng; Xia, Jing et al. (2018) CONSTRUCTION OF SPATIOTEMPORAL INFANT CORTICAL SURFACE ATLAS OF RHESUS MACAQUE. Proc IEEE Int Symp Biomed Imaging 2018:704-707
Nie, Dong; Wang, Li; Adeli, Ehsan et al. (2018) 3-D Fully Convolutional Networks for Multimodal Isointense Infant Brain Image Segmentation. IEEE Trans Cybern :
Xia, Jing; Wang, Fan; Meng, Yu et al. (2018) A computational method for longitudinal mapping of orientation-specific expansion of cortical surface in infants. Med Image Anal 49:46-59
Chen, Jiawei; Zhang, Han; Nie, Dong et al. (2018) Automatic Accurate Infant Cerebellar Tissue Segmentation with Densely Connected Convolutional Network. Mach Learn Med Imaging 11046:233-240
Jha, Shaili C; Xia, Kai; Schmitt, James Eric et al. (2018) Genetic influences on neonatal cortical thickness and surface area. Hum Brain Mapp 39:4998-5013
Wang, Li; Li, Gang; Adeli, Ehsan et al. (2018) Anatomy-guided joint tissue segmentation and topological correction for 6-month infant brain MRI with risk of autism. Hum Brain Mapp 39:2609-2623

Showing the most recent 10 out of 15 publications