Adrian Vasile Dalca

Postdoctoral Fellow

A.A. Martinos Center for Biomedical Imaging
Massachusetts General Hospital, Harvard Medical School

Computer Science and Artificial Intelligence Lab
EECS, Massachusetts Institute of Technology

32 Vassar St, 32-D474, Cambridge, MA, 02139. 
adalca at mit dot edu

I am a postdoctoral fellow at MGH, Harvard medical School, working with Mert Sabuncu. Until recently, I was a graduate student at Medical Vision Group, CSAIL, EECS MIT, advised by Polina Golland. I am interested in models for medical image analysis and characterizing genetic effects on imaging phenotypes. I have been lucky to work with wonderful collaborators.

I serve on the MICCAI Society Student Board, and participate in the MIT-MGH SITECOR program, which allows engineers to observe surgical procedures in an effort to improve O.R. technologies. I also have a side passion for computational photography and vision.

My wife, Monica, is a graduate student at MIT in the Biology department doing exciting research on cancer biology.

Check out our IPMI 2017 paper, which won the best Poster Award!
Register images with our patch based method (Best Paper Award at PatchMI 2016)! paper | code
My PhD Thesis is up.
Predict entire MRIs using genetics! Short video | paper | web | news
New website for the Boston Timescape Project

Current Main Projects

Predictive Modeling of Imaging and Genetics

I'm interested in the prediction of an entire medical image (e.g. MRI) given a subject's genotype and environmental factors. Towards this end, we are currently developing predictive mathematical models, the first of which will be presented at MICCAI 2015 in Munich.

A Computational Model for Stroke

Stroke is one of the top causes of death and debilitating injury. We are developing models for extracting important phenotypes from medical stroke imaging to aid in prediction, risk assesment and genetic exploration. Stroke is also a main applications of our imaging genetics models mentioned above.

tipiX - Rapid Visualization of Large Image Collections

tipiX is a new approach for fast and effective visualization of large image collections. This applies to both natural images as well as medical volumes in population studies. The key insight is to collapse inherently high-dimensional imaging data onto an interactive two-dimensional canvas native to a computer screen in a way that enables intuitive browsing of the image data. Several examples will get you started in various domains. The code is available on github.

  • A.V. Dalca, R. Sridharan, N.S. Rost, P. Golland. tipiX: Rapid Visualization of Large Image Collections In MICCAI-IMIC Interactive Medical Image Computing Workshop, 2014.
    Best paper award for impact and usability.
    Finalist CSAIL Amazing Research Highlight Competition.

Current Side Projects

Boston Timescape Project

Since 2010, I've taken pictures of the Boston Skyline from a high vantage point. The more than one million images have been captured with different high resolution cameras (SLRs, GoPros, P&S, cell phone cameras). Some pictures are singletons (just one picture was taken for, say, that week or that day) whereas others are part of series or timelapses (and vary from 1/second to 1/minute, etc). I'm happy to share this data and am currently setting up a repository for it . There are several cool projects that could be done. Go to the project homepage to explore samples from the data with tipiX, and get more information!

Original design: MiniFolio