Skip to main content

Mingxia Liu

Mingxia Liu, PhD, is a UNC Lineberger Comprehensive Cancer Center member with research interests in developing advanced machine learning and deep learning methods to improve breast cancer diagnosis, prognosis, and treatment response prediction through medical image analysis and multimodal data integration.

PhD
Associate Professor, Radiology
UNC-Chapel Hill
Breast Cancer Research Research Program

Area of Interest

My primary research interest lies in applying advanced machine learning and deep learning techniques to breast cancer medical imaging and multimodal data integration. I focus on developing innovative AI algorithms that improve early detection, precise diagnosis, and prognosis prediction by analyzing diverse imaging modalities such as mammography, MRI, ultrasound, and pathology images.

A key aspect of my work is harmonizing multi-site and multi-modality data—including imaging, genomic, and clinical datasets—to overcome variability across scanners, protocols, and populations. I am particularly interested in designing methods that capture tumor heterogeneity and dynamic progression patterns through multi-template learning and longitudinal modeling, even in the presence of incomplete or missing data.

Additionally, I develop domain adaptation and transfer learning approaches to facilitate robust cross-site data harmonization, enabling scalable and generalizable clinical AI tools. Ultimately, my goal is to translate cutting-edge computational techniques into actionable insights that enhance personalized breast cancer treatment and improve patient outcomes.

Find publications on PubMed

Awards and Honors

  • Outstanding Area Chair Award, The 26th International Conference on Medical Image Computing and Computer Assisted Intervention, Vancouver, Canada, 2023
  • Best Paper Award, “Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework,” The 14th International Workshop on Machine Learning in Medical Imaging, Vancouver, Canada, 2023.
  • Best Paper Award, “Fast Image-Level MRI Harmonization via Spectrum Analysis,” The 13th International Workshop on Machine Learning in Medical Imaging, Singapore, 2022
  • Best Paper Award, “Triplet Graph Convolutional Network for Multi-scale Analysis of Brain Functional Connectivity Using Functional MRI,” International Workshop on Graph Learning in Medical Imaging, Shenzhen, China, 2019
  • Best Performance Award (#1 Ranked), “Classification of Normal versus Malignant Cells in B-ALL White Blood Cancer Microscopic Images” Challenge, IEEE International Symposium on Biomedical Imaging, Venice, Italy, 2019
  • Young Scientist Award Nomination, “Diagnosis of Alzheimer’s Disease Using View-aligned Hypergraph Learning with Incomplete Multi-modality Data,” The 20th International Conference on Medical Image Computing and Computer Assisted Intervention, Athens, 2016
Headshot of Mingxia Liu.