RUMI PARSE RISE Optimizing Stroke Treatment CDSC


Many of us go online to get information about our medical conditions. But do you really understand the data in your medical record? The Retrieving Understandable Medical Information (RUMI) project aims to provide tailored, context-sensitive information to patients.


With the increasing amount of data in the electronic health record, new methods are required to help expedite a healthcare provider's understanding of a patient's medical history. The PARSE project explores the use of topic models for summarizing large, unstructured data collections to support PCPs.


Are you an undergraduate interested in biomedical informatics? The MII Research in Informatics Summer Experience (MII RISE) is an opportunity for undergraduates to work with our faculty to gain experience in research and biomedical informatics.

Optimizing Stroke Treatment

Annually, it is estimated that more than 795,000 Americans experience a stroke. The severity of neurological damage due to an acute stroke is mitigated by the early restoration of blood flow to the affected area. In this project, new probabilistic modeling methods are being developed to optimally select treatments.


The Center for Domain-Specific Computing (CDSC) is an NSF-InTrans award, focusing on next-generation hardware and software acceleration of algorithms in the biomedical sciences. CDSC is a collaboration between UCLA, Rice University, Oregon Health Sciences University, and Intel Research.

Research News

Paper published in IEEE Trans on Medical Imaging
02 October 2018

The journal IEEE Trans on Medical Imaging has published "Path R-CNN for Prostate Cancer Diagnosis and Gleason Grading of Histological Images," by MII student Wenyuan Li. Co-authors of this article include MII student Jiayun Li, Karthik V. Sarma, King Chung Ho, Shiwen Shen, MII faculty member Corey Arnold, and collaborators Beatrice S Knudsen and Arkadiusz Gertych.

PLOS One publishes article on
03 May 2018

An article on has been published in the journal PLOS One. Authors include MII members Nicholas J. Matiasz, Justin Wood, William Speier, and William Hsu, who collaborate on this project with Alcino J. Silva and Wei Wang. ResearchMaps is a web app designed to help scientists evaluate evidence and plan their next experiment. The app is open-source and free for academic and non-profit use.

Best student paper award at AMIA 2017
01 December 2017

MII student Johnny Ho received the best student paper award (Martin Epstein Award) at AMIA 2017 for his paper, "Classifying Acute Ischemic Stroke Onset Time using Deep Imaging Features." MII student Jiayun Li was also nominated as a finalist in the Student Paper Competition for her paper, "A Multi-scale U-Net for Semantic Segmentation of Histological Images from Radical Prostatectomies."

Paper published in Frontiers in Neuroinformatics
13 February 2017

The journal Frontiers in Neuroinformatics has published "Computer-Aided Experiment Planning toward Causal Discovery in Neuroscience," by MII student Nicholas J. Matiasz. Co-authors of this article include MII student Justin Wood, MII faculty member William Hsu, and collaborators Wei Wang and Alcino J. Silva.

more research news>