This interview is with Cancer Informatics editorial board member Dr Bradley J Erickson. Cancer Informatics is an open access journal published by Libertas Academica.

Editor in Chief Dr James Willey has recently issued a call for papers.

What is the primary focus of your research?

Computer analysis of brain tumor images. This includes both evaluation of new image types for information content, development of new 'features' that can be extracted from the images, machine learning methods for finding combinations of features that reflect response to therapies or prognosis, and impact of display methods for human interpretation of images.

What are the most exciting developments arising from current research in your area?

New machine learning methods allow computers to find aspects of images that correlate with some desired measure (such as response or survival). These can be much more complex relationships than are humanly perceptible, and can also include non-image information.

Who are your main collaborators? Please describe your work with them.

This research lies at the junction between clinical and technological. As such, I collaborate with clinicians who refer and evaluate patients, and do a wonderful job of developing and evaluating new agents. On the technology side, we have a nice relationship with IBM Research as well as internal researchers who are developing new computer methods.

How did you come to be working in your research area?

As a neuro-radiologist I am most interested in diseases of the brain, and cancer is a disease that lends itself to image processing and informatics tools. Therefore, it was a very natural thing to work in this arena.

What do you think about the development of open access publishing? Have you published in an open access journal? What motivated you to do so?

The key idea behind publishing is to have readers. Open access maximizes the number of readers who will read articles if they are of interest. I think it is a refreshing alternative to traditional publication models, and it has pushed many good changes into the traditional publishers. I suspect that just as software will have both open source and traditional models competing, there will be both open access and traditional publication models for many years. Having a choice in publication models is a great thing for authors.

What articles and/or books have you published recently?

Chapters in Practical Imaging Informatics

NLP of brain tumor radiology reports

Open Source Software in Imaging Informatics