Accurate cardiac left ventricle (LV) quantification is among the most clinically important and most frequently demanded tasks for identification and diagnosis of cardiac diseases and is of great interest in the research community of medical image analysis. The LVQuan18 challenge will
- focus on full quantification of LV, i.e., all clinical significant LV indices regarding to the anatomical structure of LV are investigated in addition to the frequently studied LV volume;
- provide a unified platform for participants around the world to develop effective solutions for LV full quantification;
- benchmark all submitted solutions for the task of LV quantification and advance the state-of-art performance for computer-aided cardiac image quantification.
Paper submission： https://ocs.springer.com/ocs/home/STACOM2018
Challenge papers： https://link.springer.com/book/10.1007/978-3-030-12029-0
The Final Rankings
|Jiahui Li, Zhiqiang Hu||Left Ventricle Full Quantification Using Deep Layer Aggregation Based Multitask Relationship Learning||1||1||1||2||1|
|Eric Kerfoot, James Clough, Ilkay Oksuz, Jack Lee, Andrew P. King, Julia A. Schnabel||Left-Ventricle Quantification Using Residual U-Net||1||3||4||3||2|
|Fumin Guo, Matthew Ng, Graham Wright||Cardiac MRI Left Ventricle Segmentation and Quantification: A Framework Combining U-Net and Continuous Max-Flow||3||5||6||7||3|
|Hao Xu, Jurgen E. Schneider, Vicente Grau||Calculation of Anatomical and Functional Metrics Using Deep Learning in Cardiac MRI: Comparison Between Direct and Segmentation-Based Estimation||7||4||6||4||3|
- Training/Validation data release: 26 NOV, 2017
- Test data release: 17 June 2018
- Abstract registration: 17 June 2018
- Test results submission: 22 June 2018, 23:59 CDT
- Test performance feedback: 25 June 2018
- Paper submission deadline: 28 June 2018 (June 27, 2018 23:59 CDT)
- Workshop paper notification: 23 July 2018
- Camera ready version submission: 30 July 2018
- Challenge day: 16 Septermber 2018 (in conjunction with STACOM 2018)
- Multiple awards will be selected according to the ranking list of all participants.
- Selected challenge papers will be published with the STACOM proceedings in Lecture Notes in Computer Science, Springer.
- A potential publication in MedIA or IEEE TMI which summarizes the benchmarked algorithms will be completed and all participants share the credit.
For any questions about the challenge, feel free to contact.