Dr. McMillan presented at the Practical Big Data Workshop at the University of Michigan in Ann Arbor on May 18th. The title of Dr. McMillan’s talk was “Can Machines be Trusted? Robustification of Deep Learning for Medical Imaging.” This work highlighted some of the work the MIMRTL group is doing towards the development of robust …
MIMRTL research was presented at the 2023 Midwest Machine Learning Symposium (https://midwest-ml.org/2023). Contributions included poster presentations on CT synthesis from MR images (On The Effect of Training Database Size For MR-based Synthetic CT Generation In The Head by S. Iman Zare Estakhraji; Weijie Chen; Ali Pirasteh; Tyler Bradshaw; Alan McMillan) and convex optimization strategies to …
Congratulations to MIMRTL graduate students Sabeeka Khan (LinkedIn: https://www.linkedin.com/in/sabeeka-khan/) and Nikhil Nagam (LinkedIn: https://www.linkedin.com/in/nikhil-nigam-31131b12a/). Both recently graduated with Masters’ degrees in the Department of Electrical and Computer Engineering. We look forward to seeing the great things that you accomplish. Congrats to Sabeeka and Nikhil!
Congratulations to Weijie Chen on a successful preliminary examination! Weijie’s PhD thesis work in the MIMRTL group will develop efficient ensemble methods applied to medical imaging. His hypothesis is that such models will yield not only better performance for segmentation and synthesis applications, but also enable assessment of model uncertainty. The ability to assess a …
MIMRTL researchers and collaborators, led by S. Iman Zare Estakhraji, PhD recently published a paper that explored the use of unsupervised and supervised training methods to generate synthetic computed tomography (sCT) images from magnetic resonance (MR) images. The study employed a cycleGAN method with unpaired data sets for unsupervised training and several supervised models that …