Biomedical Engineering

Group Members

Ding Ning, Ph.D. (In progress)

Research Assistant

Ph.D. (ongoing), University of Canterbury, New Zealand

Master of Applied Data Science, University of Canterbury, New Zealand

Master of Science degree Applied Mathematics,  Northeastern University, USA

ding.n@camcid.org

 

Lijin Zhou, BS, MEng.

Research Assistant

Master of Engineering Artificial Intelligence, Stevens Institute of Technology, USA

lijin.z@camcid.org

 

Research Coordinator

Elisa Hampson

admin@camcid.org

Research Focus

 

The mission of the Biomedical Engineering group is to develop and find effective computational techniques for the analysis of medical images and signal processing. The group focuses on pursuing research, including:

 

  • Development of machine learning algorithms for medical image analysis and image interpretation.
  • Biomedical Computing.
  • Biomedical Instrumentation
  • Bioimaging

 

We have a strong interest in the application of medical imaging and computing technology to improve the diagnosis of diseases.

 

Projects

 

Deep learning-based image segmentation of scar tissue from late Gadolinium enhancement 3D cardiovascular Magnetic Resonance Imaging (MRI)

 

Machine learning and Artificial Intelligence (AI) are rapidly gaining importance in the field of medical imaging. Our aim is to apply machine learning and deep learning in cardiac Magnetic Resonance Imaging (MRI) to assist in improving quality, image analysis, and AI-based interpretation of the disease. Deep learning may allow us to automatically analyze diseased tissue in cardiac MR images. Our research also includes developing AI-based algorithms to improve cardiac image quality and assist in disease diagnoses.

 

Machine Learning-based image reconstruction methods for cardiovascular imaging

 

We are exploring different machine learning-based approaches in image reconstruction of MRI and echocardiography images. We are working on comparing different machine learning algorithms for a better understanding of cardiac pathology.

 

Implication and challenges of AI in diagnostic imaging

 

We are involved in literature reviews on AI implications and challenges in diagnostic imaging (Ultrasound, Computed Tomography, Positron Emission Tomography, and MRI). We are particularly interested in the workflow, data management, and ethical challenges of applying AI in clinics and hospitals.