Our travel grant and EDD challenge winner!!! 

Adrian Krenzer is with the Department of Artificial Intelligence and Knowledge Systems in Germany (http://www.is.informatik.uni-wuerzburg.de/startseite/) and he has won the Endoscopic Disease Detection Challenge 2020 (EDD2020), hosted by Dr. Sharib Ali. The EDD2020 will be held in conjunction with the IEEE International Symbiosis of Biomedical Imaging 2020 (ISBI 2020). As MedIAN likes to support early career researchers and extend their network they sponsored a full travel grant for his participation in the ISBI2020. Adrian Krenzer is a PhD student at Julius-Maximilians-University, Würzburg, Germany. Previously he obtained his M.Sc. in Business Information Systems and a B.Sc. in Business Information Systems. His research interests include deep learning, machine learning, computer vision, object detection and medical image processing. His PhD thesis is concerned with the automatic classification and documentation of polyps in colonoscopies. His project is a joint effort of the University Hospital of Würzburg’s gastroenterological department and the Artificial Intelligence and Knowledge Systems chair. 

 We wanted to know more about how he felt about the challenge he'd just participated in and how he felt about the online workshop and the winning the travel grant. 

1)   What do you think about EDD2020 challenge?

The common endoscopic computer vision research is mostly focused on the detection of a singular disease like, e.g. polyps. I like the approach of the EDD2020 because it extends this detection task by providing data for different diseases in various organs. Therefore, allowing to see a bigger picture and supporting the medical domain more efficiently. 

 2) What was exciting about participating in the online challenge of EDD2020?

Competition is always exiting especially when it is in your field of interest. As my PhD focuses on poly detection it was thrilling to get to know the different researches and seeing their progress as well as my own. It also allows me to grow my network and getting to know the community of people interested in this domain. 

3) What did you learn and what opportunities did it give you?

The EDD2020 really thought me a lot. Frist of all I enjoyed working with my new and amazing team members Amar Hekalo and Prof. Frank Puppe. Since my previous research was focused on polyp detection only, I liked the challenge of classifying different diseases as well. Which also handed me the opportunity to focus more on disease classification in the future. Second the MedIAN gave me the financial freedom to participate in the entire EDD2020 conference which would not have been possible otherwise. 

4) How do you feel regarding winning this challenge?

I feel accomplished and I am very grateful to have the support of my great colleges at Würzburg University Amar Hekalo and Prof. Frank Puppe without whom could not have made it. Especially the great work of Amar Hekalo in the segmentation task of the challenge helped a lot and I appreciate the supervision and support of Prof. Frank Puppe during the challenge and the writing process of the paper.  

 5) What do you think AI challenges like this can do to transform health care and help you understand the challenges and how can this be used for care pathways in the future?

Challenges are very important as in the domain of deep learning they mostly involve the publication of free open source data. Therefore, challenges may become benchmarks for further research in their domain, this happened for example with the Endoscopic Vision challenge 2015 (https://polyp.grand-challenge.org/). In addition, a challenge like the EDD2020 can set groundwork for further research. Challenges can therefore have immense contribution to the community and in further research for the real applications in clinics. Also, medical doctors will see the increasing performance in such challenges, and it may be more likely for them to try such systems in their own care. 

I am very grateful that my participation to the entire ISBI 2020 conference were financially supported by NIHR BRC Oxford. The challenge was a unique and enriching experience. The organizing committee was very engaging, cooperative and knowledgeable in this domain. By providing these extensive datasets, a competition leaderboard, and exhaustive support, they created an ideal environment for its participants to learn, connect, and contribute to the advancement of automated disease detection in endoscopy. I wish this challenge and the upcoming workshop every success. Once again, thank you very much for the organization and the travel grant support.