Encrypted | Login
The DL-spectral CT Challenge has concluded. The Challenge provided an opportunity for investigators in deep-learning CT image reconstruction to compete with their colleagues on the accuracy of their methodology for solving the inverse problem associated with dual-energy kV-switching CT acquisition. The top five performing individuals and teams are:

Username Team Name Members Institutions(s) RMSE Score
GenweiMa GM_CNU Genwei Ma
Xing Zhao
Capital Normal University,
Beijing, China
Southern University of Science
and Technology,
Shenzhen, China
6.8 x 10^(-7)
Huxiaoyu090 iTORCH Xiaoyu Hu
Xun Jia
University of Texas Southwestern Medical Center, Dallas 6.21 x 10^(-6)

Hyeongseok Kim
Seungryong Cho

Korea Advanced Institute of Science & Technology, Daejon, South Korea 1.19 x 10^(-4)
Maria Medrano
Joseph A. O’Sullivan
Washington University,
St. Louis
2.52 x 10^(-4)
dhlee91   Donghyeon Lee Johns Hopkins University School
of Medicine, Baltimore
4.08 x 10^(-4)

For more information see the Challenge website which will remain open: https://dl-sparse-view-ct-challenge.eastus.cloudapp.azure.com/competitions/3

The validation phase, which included about 30 active participants, and the final test phase included 18 submissions. Each submission consisted of an algorithm report along with predictions on 100 images from spectral data. Final score was the mean root-mean-square-error (RMSE) calculated in comparison with the truth images. RMSE values for the top five appear in the table. For full ranking for validation and test phases, please see the ‘Results’ tab of the Challenge page.

A full Challenge report will be forthcoming at the end of August.