A guide to events on our campuses.

Assembly Series

A tradition of convening thought leaders since 1953

McKelvey School of Engineering

ESE Dissertation Proposal Jiaming Liu

Monday, August 15 | 3:00 PM - 5:00 PM

Preston M. Green Hall, Rodin Auditorium, Room 0120
135 N Skinker Blvd, St. Louis, MO 63112, USA

Fast and robust recovery of image from deluge of incomplete and noisy date is now within reach for many important biomedical applications. Success in such recovery tasks requires accurate and scalable algorithms that can leverage the knowledge of physics as well as strong statistical priors. For example, in the compressed sensing magnetic resonance imaging (CS-MRI), the physics model is used to ensure the reliability, while the sparse natural of medical images is used as prior to accelerate the data acquisition. Recently, deep learning methods have shown state-of-the-art results in a number of biomedical imaging tasks. Although powerful, the corresponding methods are often heuristic and fragile to outliers. In fact, there is still a lack of a robust and interpretable deep-learning-based framework that comes with provable theoretical guarantees.

My research aims to bridge this gap by building a unified framework that is rapid, scalable to largescale data, and comes with provable guarantees. To achieve the goal, I utilize “artifacts removing” as a mechanism to incorporate the prior knowledge into the recovery problem but keeping the prior explicitly decoupled from the data acquisition model.  Hence, by using “learned artifacts remover”, my methodology can fully leverage the rich prior information in the training data, while having the physics model to accommodate outliers. We demonstrate the performance of our algorithms by validating their performance on various imaging applications and providing rigorous theoretical analysis.

In addition, this dissertation evaluates and outlines future work to explore three specific topics: (a) efficient deep learning for data-intensive biological imaging; (b) deep probabilistic priors for inverse imaging; (c) theoretical foundations for deep learning priors, all of which are centered on developing new algorithms and mathematical tools for advanced computational imaging applications.

Event Type



McKelvey School of Engineering


Science & Technology

Electrical & Systems Engineering
Speaker Information

Jiaming Liu
PhD Candidate
Washington University in St. Louis 

Google Calendar iCal Outlook