|Paper, Diagram, and Code Submission||June 23|
|Notification of Acceptance||August 18|
|Poster Submission||September 7|
|Presentations and Winner Announcement||Previously: September 8
Updated: September 10 & 11
Participation at IEEE IUS 2020
(updated September 1, 2020)
All accepted participants are required to prepare a 3-minute poster for presentation during the CUBDL summary event at IEEE IUS 2020
on September 8th. These posters will remain visible during the 3-hour CUBDL summary event, as well as during the entire symposium. The top 4-8 finishers will have the option to give oral presentations about their network architectures during the CUBDL summary event on September 8th.
The CUBDL summary event at IEEE IUS 2020, was originally scheduled for September 8th. However, as IUS is now virtual, we have modified the schedule for the challenge participants as follows:
- CUBDL Poster Session, Thursday, September 10, 4:15 – 6:15am PDT: each challenge participant will be available to provide an overview of their submissions.
- CUBDL Live Session, Friday, September 11, 9:45-10:15am PDT: the organizers will provide a brief overview of the challenge for the IUS community, the results of all participants will be compared, two of the top participants will give oral presentations about their networks, and the cash prize winners will be announced. The session will end with live Q&A.
Pending the receipt of a sufficient number of high-quality submissions, the organizers will aim to submit a multi-author journal paper describing top results. All co-authors of the winning methods will be included as authors of this journal paper. Top-performing participants included in this associated journal paper will be required to share submitted files. We intend to release all unrestricted test data with the publication of this report in order to provide a useful reference and benchmark dataset for future follow-on work.
Updated July 5, 2021: Our multi-author journal paper describing top results was accepted for publication! D. Hyun, A. Wiacek, S. Goudarzi, S. Rothlübbers, A. Asif, K. Eickel, Y. C. Eldar, J. Huang, M. Mischi, H. Rivaz, D. Sinden, R.J.G. van Sloun, H. Strohm, M. A. L. Bell, Deep Learning for Ultrasound Image Formation: CUBDL Evaluation Framework & Open Datasets, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control (accepted July 1, 2021) [pdf]