Original Raters

These are raters who participated in the original STACOM 2011 workshop. The first consensus was established based on these raters.

Contour-constrained optical flow tracking (AO)

This method involves manual drawing at the first frame before automatically tracks contour in the subsequent frames by minimizing energy functionals, which consist of optical flow and contour properties constraints.

Submitted by the Nile University, Cairo, Egypt.

Ahmed S. Fahmy, Ahmed O. Al-Agamy, and Ayman Khalifa, "Myocardial Segmentation Using Contour-Constrained Optical Flow Tracking", STACOM 2011, LNCS 7085, pp 120-128, Springer, 2012.

Manually guide-point modeling assisted fitting of cardiac model (AU)

This is an expert-guided segmentation method where a finite element model of the LV was fitted interactively throughout the cardiac frames.

Submitted by the University of Auckland, New Zealand.

Bo Li, Yingmin Liu, Christopher J. Occleshaw, Brett R. Cowan, and Alistair A. Young, "In-line Automated Tracking for Ventricular Function With Magnetic Resonance Imaging", JACC: Cardiovascular Imaging, 3:8, pp 860-866, 2010.

Block matching algorithm (DS)

This method involves manual drawing at the first frame and the subsequent myocardial contours were detected by using the block-matching technique.

Submitted by Diagnostic Inc.

S. Ourselin, A. Roche, S. Prima, and N. Ayache, "Block Matching: A General Framework to Improve Robustness of Rigid Registration of Medical Images", MICCAI 2000, LNCS 1935, pp 557-566, Springer, 2000.


Layered spatio-temporal forests algorithm (INR)

This segmentation algorithm was based on two layers of spatio-temporal decision forests with almost no assumptions on the data nor explicitly specifying the segmentation rules. 4D spatio-temporal features to classification with decision forests were introduced in the first layer for context aware MR intensity standardization and image alignment. The second layer was then used for the final image segmentation. This is a fully automated segmentation algorithm without any user intervention.

Submitted by INRIA, France.

Ján Margeta, Ezequiel Geremia, Antonio Criminisi, and Nicholas Ayache, "Layered Spatio-temporal Forests for Left Ventricle Segmentation from 4D Cardiac MRI Data", STACOM 2011, LNCS 7085, pp 109-119, Springer, 2011.


Deformable registration method (SCR)

This fully automated algorithm registered and segmented cardiac MR images based on inverse consistency of deformable registration to register all frames to the first frame. The segmentation was applied to any frame and propagated to any other frames in the sequence through forward and backward deformation fields.

Submitted by Siemens Corporation Research group.

Marie-Pierre Jolly, Christoph Guetter, Xiaoguang Lu, Hui Xue, and Jens Guehring, "Automatic Segmentation of the Myocardium in Cine MR Images Using Deformable Registration", STACOM 2011, LNCS 7085, pp 98-108, 2011.

New Submissions

Raters who have submitted and provided us their algorithm description.

A fully Convolutional Neural Network (VT)

This method was based on a 15 layers of Convolutional Neural Network (CNN) for segmentation.  The network was trained for a pixel-wise labelling. Code is available from a github page.

Submitted by the Booz Allen Hamilton, USA.

Phi Vu Tran, "A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI", arXiv:1604.00494 [cs.CV], 2017.

Convolutional neural network regression (TLK)

This method was based on Convolutional Neural Network (CNN) regression by utilising the radial distance of the LV walls to segment the myocardium. Two CNNs were used: 1) a network to detect the centre of the ventricular cavity point, and 2) a network to determine the radial distances from the centre point.

Submitted by the University of Malaya, Malaysia.

Li Kuo Tan, Yih Miin Liew, EinlyLim, and Robert A. McLaughlin, "Convolutional neural network regression for short-axis left ventricle segmentation in cardiac cine MR sequences", Medical Image Analysis, 39, pp 78-86, 2017.

Histogram of Oriented Gradients (SG)

This fully automated segmentation algorithm was based on the global control of a statistical deformable model with local control assumption of the material properties of non-rigid objects. The initial 3D model was estimated using a Histogram of Oriented Gradients. Non-rigid motion was reconstructed using a variational method.

Submitted by the University of California in Los Angeles, USA.

Sharath K Gopal, "Unified Deterministic/Statistical Deformable Models for Cardiac Image Analysis", PhD Thesis Dissertation, UCLA, 2016.

Registered Raters

Participants who are still working on developing the segmentation algorithms and yet to submit their segmentation results.

Name Institution Submission status
Huafei Hu University of Sheffield, UK submitted
Tan Li Kuo University of Malaya, Kuala Lumpur submitted
Phi Vu Tran Booz Allen Hamilton, USA submitted (2 versions)
Sharath Gopal University of California, Los Angeles, USA submitted
Oliver Moolan-Feroze Bristol University, UK submitted
Mahendra Khened Indian Institute of Technology, Madras, India submitted (3 versions)
Kumaradevan Punithakumar University of Alberta, Canada not yet
Mahapatra Dwarikanath ETH Zurich, Switzerland not yet
Angélica Atehortúa Universidad Nacional, Bogota, Colombia not yet
Mahdi Hajiaghayi University of California, Irvine, USA unreachable
Bogdan Budescu Transilvania University, Brasov, Romania not yet
Zhijie Wang Western University, Ontario, Canada not yet
Xiahai Zhuang Shanghai Advanced Research Institute, China not yet
Yang Yu Rutgers University, USA not yet
Moslem Avendi UC Irvine, USA not yet
Lichao Wang TU Munich, German not yet
Cristian Linte Rochester Institute of Technology, USA not yet
Wenjun Tan Northeastern University, China not yet
Martin Rajchi Imperial College London, UK not yet
Wendeson da Silva Oliveira Federal University of Pernambuco, Brazil not yet
Joyce Teixeira Federal University of Pernambuco, Brazil not yet
Piere-Marc Jodoin University of Sherbrooke, Canada not yet
Gongning Luo Harbin Institute of Technology, China not yet
Yurun Ma Lanzhou University, China not yet
Maimoona Khan National University of Sciences and Technology, Pakistan not yet
Yang Xulei Institute of High Performance Computing, A*STAR, Singapore not yet
Heran Yang Xi'an Jiaotong University, China not yet
Gustavo Canavaci Barizon University of Säo Paolo, Brazil not yet
Ariel Hernán Curiale Universidad Nacional de Cuyo, Argentina not yet
Fan Yang Guizhou Medical University, China not yet
Brian Rice NeoSoft Medical, USA not yet
Hassan Mohy-ud-Din Yale University, USA not yet
Liset Romaguera Universidad Federal Do Amazonas, Brazil not yet
Aliasghar Mortazi University of Central Florida, USA not yet
Nasrin Bastani Isfahan University of Medical Science, Iran not yet
Shehzaad Dhuliawala University of Massachusetts, USA September 2017
Mobarakol Islam National University of Singapore February 2017
Mo Yuanhan Imperial College London, UK End of 2017
Awais Muhammad Lodhi University of Central Punjab, Pakistan Nov 2017
Lv Xuyang Northeastern University, China Aug 2017
Manuel Morales MIT, USA Sep 2017
Defeng Chen Capital Normal University, China Sep 2017
Mohit Pandey Cornell University, USA July 2018
Xiaoming Liu Wuhan University of Science and Technology, China -
Xuan Yang Shenzhen University, China May 2018
Heming Yao University of Michigan, USA Nov 2018
Xinyi Li Leiden University Medical Center, the Netherlands Feb 2018
Bradley Kenstler University of San Fransisco, USA Sep 2017
Rhodri Davies Barts Heart Centre, UK Dec 2017
Antong Chen Merc & Co. Inc., USA Dec 2018
Yongkui Xiang Shenzhen University, China -
Agisilaos Chartsias University of Edinburgh, UK 2018
Sina Masoud-Ansari University of Auckland, NZ July 2018
Christian Payer Graz University of Technology, Graz, Austria Feb 2018
William Edward Hahn Florida Atlantic University, USA Dec 2017
Ilkyu Lee Seoul National University, Korea 18 Nov 2017
Shengjie Wu Beijing Jiaotong University, Beijing, China  15 Dec 2017
Jesus R. Garcia  Universidad Nacional de San Luis, Argentina  01 March 2018