I'm a data scientist in the Imaging Research Center, Department of Radiology at Cincinnati Children's. My research area focuses on artificial intelligence (AI) technologies in medical imaging. I have applied my expertise to various disease conditions, including neurodevelopment deficits in newborn infants, attention deficit hyperactivity disorder (ADHD), autism spectrum disorder and liver diseases.
During my education to obtain my PhD, I had a chance to work as a part-time research assistant in the Department of Radiology at Cincinnati Children's. As I learned more about medical images, I realized that it would be more meaningful to apply my computer science expertise to the healthcare field. This decision led to my career in medical imaging. My goal is to facilitate the clinical translation of AI technologies to improve the healthcare quality and safety of pediatric patients nationally and globally.
I develop advanced machine learning and deep learning approaches for medical images to aid radiologists and pediatricians in various clinical applications. I also created a novel transfer learning approach for deep learning models to understand human brain networks better. I proposed the first deep learning model to stratify the severity of liver stiffening using T2-weighted abdominal magnetic resonance images (MRI).
Specifically, my research experience includes image reconstruction and denoising, image segmentation, image biomarker identification, image-based disease diagnosis, prognosis and clinical outcome predictions.
I have been a researcher for over 15 years and began my career at Cincinnati Children's in 2013. I am honored to have received the Walter E. Berdon Award for best clinical research paper from the Pediatric Radiology journal (2021). Our team's deep learning study on ADHD was the featured publication by the Radiological Society of North America (2019).
When I'm not working, I enjoy reading.
BS: Electrical Engineering, Northeastern University, Liaoning, China, 2004.
MS: Electrical Engineering, Northeastern University, Liaoning, China, 2007.
PhD: Computer Science and Engineering, University of Cincinnati, OH, 2013.
Post-Doc: Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, 2016.
Liver diseases; neonatology
Machine learning; deep learning; medical image analysis
Diffuse excessive high signal intensity in the preterm brain on advanced MRI represents widespread neuropathology. NeuroImage. 2022; 264.
A novel Ontology-guided Attribute Partitioning ensemble learning model for early prediction of cognitive deficits using quantitative Structural MRI in very preterm infants. NeuroImage. 2022; 260.
A self-training deep neural network for early prediction of cognitive deficits in very preterm infants using brain functional connectome data. Pediatric Radiology. 2022; 52:2227-2240.
A multi-head self-attention deep learning approach for detection and recommendation of neuromagnetic high frequency oscillations in epilepsy. Frontiers in Neuroinformatics. 2022; 16.
ConCeptCNN: A novel multi-filter convolutional neural network for the prediction of neurodevelopmental disorders using brain connectome. Medical Physics. 2022; 49:3171-3184.
Multi-Contrast MRI Image Synthesis Using Switchable Cycle-Consistent Generative Adversarial Networks. Diagnostics. 2022; 12.
Transformer-Based High-Frequency Oscillation Signal Detection on Magnetoencephalography From Epileptic Patients. Frontiers in Molecular Biosciences. 2022; 9.
Integrated analysis of lncRNA, miRNA and mRNA profiles reveals potential lncRNA functions during early HIV infection. Journal of Translational Medicine. 2021; 19.
Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants. Frontiers in Neuroscience. 2021; 15.
Early micro- and macrostructure of sensorimotor tracts and development of cerebral palsy in high risk infants. Human Brain Mapping. 2021; 42:4708-4721.