NSF CAREER: Systematic Mitigation of Deep Learning Adversaries in Medical Imaging

With the enormous amounts of data being acquired by large-scale healthcare systems, computational data analysis has become an essential component in healthcare applications to process and extract information. Deep learning, a sub-category of artificial intelligence (AI), has established itself as a paradigm-shifting technology for data analytics due to its powerful ability to extract high-level data representations.

Intelligent Fusion of MRI and ultrasound images for prostate cancer intervention
Recent clinical studies show that multi-parametric magnetic resonance imaging (mpMRI) can help identify clinically significant prostate cancer prior to biopsy.
Temporal Enhanced Ultrasound based Prostate Cancer Detection
Temporal Enhanced Ultrasound (TeUS), comprising a time series of ultrasound images, has been reported as an alternative non-invasive tissue characterization technique.
Deep learning based Low-dose CT image denoising
This project develops a generative adversarial network with the Wasserstein distance (WGAN) as the discrepancy measure between distributions and a perceptual loss that computes the difference between images in an established feature space.
Deep Compressive Fluorescence Lifetime Image Reconstruction
Compressive Macroscopic Fluorescence Lifetime Imaging (MFLI) is a novel technical implementation that allows multiple molecular interactions in macroscopic scale to be modeled.