Take 10 with... Martin Urschler
Dr Martin Urschler gives us 10 minutes of his time to discuss his research in medical image analysis and computer-aided diagnostic procedures.
1. Describe your research topic to us in 10 words or less.
Aiding experts in analysing and interpreting medical imaging data.
2. Now explain it in everyday terms!
Medical imaging devices like computed tomography (CT) or Magnetic Resonance Imaging (MRI) scanners have had tremendous impact on medicine in the last decades, since they let experts non-invasively look inside the human body to study anatomical structures and diagnose diseases. However, the number of images generated from such devices is huge, and assisting medical experts in the analysis and interpretation of this data is beneficial to improving effectiveness and lowering costs of imaging-based diagnostic procedures.
My main research interest is in medical image analysis and computer vision, where we apply approaches from mathematical optimisation and signal processing as well as statistical machine learning to semi- or fully-automatically derive information from two- and three-dimensional imaging data. This can be used to study various organs and their function in the body, like in the case of my more specific research interests, the lung, the heart, or the spinal vertebrae.
3. What are some of the day-to-day research activities you carry out?
My research involves a variety of tasks, so I can never complain of being bored by it! Activities involve programming software frameworks to support algorithm development, looking for publicly available datasets or novel algorithms that have been published, reviewing the work of colleagues, and reading parts of the rapidly increasing body of research papers in this area. And at the end of the day, all of that is of course accompanied by working with students, who help me to better navigate this area of research I am invested in.
4. What do you enjoy most about your research?
Identifying and attempting to solve challenging problems is a great driver of my research work, but more importantly I enjoy working with research students. I observe, and try to guide their growth and development on their journey to become independent researchers themselves.
5. Tell us something that has surprised you in the course of your research.
A surprising fact I have learned over my research career is that a lot of good collaborations or even research ideas and papers start out when a number of colleagues - some of whom may already know each other and others newly met - go out for a drink or some food at a conference or some other event. Talking about work is mixed with private anecdotes and for some reason this process seems to result in unleashing creativity!
6. How have you approached any challenges you’ve faced in your research?
A key challenge in my inter-disciplinary research is to facilitate an environment where experts from different areas can talk with each other in a way that is understandable for all participants. While this may sound trivial, I have often experienced situations where the definition of some key terminology was different in disciplines, and after months of discussing research details, confusion about this general terminology led to different interpretations of where we were going. What I learned from these incidents is that patience and striving for clarity are valuable traits to nurture!
7. What questions have emerged as a result?
In research, there is a constant stream of questions that emerge through interactions within and between the disciplines. A specific example of a research question that came out of our careful discussions between medical image analysis and legal medicine experts was to study the feasibility of estimating age of children and adolescents solely from MRI data of the growing bones and developing teeth. This ultimately led to a research project that has funded a core part of my group for several years in Austria.
8. What kind of impact do you hope your research will have?
My hope is that my research career will lead to at least one procedure in the space of medical imaging-based processes or diagnostics that has sustainable impact on the health and wellbeing of a group of people.
9. When collaborating across the faculty or University, or outside the University, who do you work with and how does it benefit your research?
My collaborators are in medical imaging departments, such as radiologists and radiology technicians, but also clinicians and medical doctors. I have connections with groups in my hometown Graz in Austria, but am also slowly building up connections in Auckland and New Zealand. Scientific collaborators are mostly spread around Europe, and some of them are former colleagues of mine from Graz University of Technology. A large variety of collaborators is a good way to ensure one does not get stuck in research dead ends, by providing valuable critical feedback on ideas.
10. What one piece of advice would you give your younger, less experienced research self?
Do not waste so much time wondering about whether things might fail, or if research ideas may not work out. Failure is a large part of research, and success is often the exception. By putting the focus on trying something without being anxious to fail in it, a much more nutritious environment for success can be laid out. And growing older, I think this strategy is not only applicable to research...