Welcome to the Cardiac MRI Reconstruction Challenge (CMRxRecon)!  
The CMRxRecon Challenge is a part of the 26th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2023, which will be held from October 8th to 12th 2023 in Vancouver Convention Centre Canada.


This challenge aims to establish a platform for fast CMR image reconstruction and provide a benchmark dataset that enables the broad research community to promote advances in this area of research.


Cardiac magnetic resonance imaging (CMR) has become an important imaging modality for diagnosing cardiac diseases due to its superior soft tissue contrast and non-invasiveness. However, an inherent drawback of MRI is that the imaging speed is particularly slow, which will cause discomfort to patients and intr​oduce motion artifacts into images. CMR image reconstruction from highly under-sampled k-space (raw data) has become a hot topic in recent years. 
So far, a large number of AI-based image reconstruction algorithms have shown the potential to improve imaging performance through increasing the data under-sampling factor. However, the field of CMR reconstruction still lacks public, standardized, and high-quality datasets. To date, NYU Langone Health has released 'fastMRI' dataset, containing multi-channel knee and brain MRI raw data. However, these images are inadequate for 3D+1D (time domain) applications in cardiac imaging. The goal of establishing the 'CMRxRecon' dataset is to provide a platform that enables the broad research community to participate in this important work.  

Challenge tasks

The ‘CMRxRecon’ challenge includes two independent tasks. Each team can choose to participate one of them or both: 
1) Accelerated cine reconstruction
The aim of task 1 is to accelerate cine  imaging by rawdata under-sampling and address the image degradation due to motions caused by voluntary breath-holds or cardiac arrhythmia. The final goal will be real-time cine imaging. 

Task 1. Accelerated Cine Reconstruction

2) Accelerated T1/T2 mapping
The aim of task 2 is to improve the T1 and T2 mapping estimation accuracy by rawdata under-sampling and address the image degradation due to motions and under-sampled reconstructions. 

Task 2. Accelerated T1/T2 Mapping


We will provide monetary awards for the  top 3 winners of each task. The prize pool is exclusively sponsored by Siemens. 

Task 1. Accelerated cine construction

Task Winner Monetary Awards Certificate Oral Presentation Summary Paper Involved
Task 1 Top 1 $1,000
Task 1 Top 2 $500
Task 1 Top 3 $300

Task 2. Accelerated T1/T2 mapping

Task Winner Monetary Awards Certificate Oral Presentation Summary Paper Involved
Task 2 Top 1 $1,000
Task 2 Top 2 $500
Task 2 Top 3 $300

Study Cohort

A total of 300 healthy volunteers from a single center were included in this study. 
The released dataset includes 120 training data, 60 validation data and 120 test data.
Training data including fully sampled k-space data, auto-calibration lines (ACS, 24 lines) and reconstructed images in MATLAB .mat format will be provided.
Validation data include under-sampled k-space data with acceleration factors of 4, 8 and 10, sampling mask, and auto-calibration lines (ACS, 24 lines) will be provided. We will withhold the ground truth images of the validation set.
Test data include under-sampled k-space data with acceleration factors of 4, 8 and 10, sampling mask, auto-calibration lines (ACS, 24 lines) and reconstructed images. The test data will not be available to the participants.

CMR acquisition design

Scanner: Siemens 3T MRI scanner (MAGNETOM Vida).

Image acquisition: We followed the recommendations of CMR imaging reported in the previous publication (doi: 10.1007/s43657-02100018x, 10.1007/s43657-021-00018-x[w.c.y.1]  ).  
1) Cine: The ‘TrueFISP’ readout was used for CINE acquisition. The collected images include short-axis (SA), two-chamber (2CH), three-chamber (3CH) and four-chamber(4CH) long-axis (LA) views. Typically 5~10 slices were acquired for  SA cine, while a single slice was acquired for the other views. The cardiac cycle was segmented into 12–25 phases with a temporal resolution 50 ms. For this challenge, we provided raw k-space data of both SA (multi-slices) and LA (multi-views).  
2) Mapping: T1 mapping was conducted using a modified look-locker inversion recovery (MOLLI) sequence, which acquired nine images with different T1 weightings (using the 4-(1)-3-(1)-2 scheme). T1 mapping was performed in SA view only. Signals were collected at the end of the diastole with ECG triggering. T2 mapping was performed using T2-prepared (T2prep)-FLASH sequence with three T2 weightings in SA view, with identical geometrical parameters as used in T1 mapping. 

Pre-processing:  The raw k-space data exported from the scanner will be pre-processed and transformed to .mat format (MATLAB). The data were compressed to 10 virtual coils (Zhang et. al MRM 2013;69(2):571-82.) for standardization and to save storages. The image quality is highly consistent before and after coil compression. The partial Fourier data were filled up using POCS algorithm (provided by michael.voelker@mr-bavaria.de). We will provide a README file that describes the content of the data and how to use it. 

Manually segmentation

Representative Images with Manually Annotations

Manual segmentations of myocardium and chambers were performed by an experienced radiologist (with more than 5 years of cardiac imaging experience) using ITK-SNAP (version 3.8.0). The segmentation labels and the corresponding images were stored in NIFTI format, maintaining the original image coordinates.
For the LAX cine images, four cardiac chambers have been labeled as follows:
a) Left atrium - label 1;
b) Right atrium - label 2;
c) Left ventricle - label 3;
d) Right ventricle - label 4.
For the SAX cine images, we performed the following labeling:
a) Left ventricle - label 1;
b) Left ventricular myocardium - label 2;
c) Right ventricle - label 3.
The annotations of both T1 mapping and T2 mapping were the same as SAX cine.

Principal of participation

Note: Participants are not required to upload the complete training code. But teams willing to upload the original training code will be automatically entered into the code-sharing pool.


The schedule of the challenge is as follows. All deadlines are Pacific Standard Time (PST +0:00).

01 - May website opens for registration
10 - May release training and validation data
20 - May release demo code for PI reconstruction
30 - May submission system opens for validation
14 - July deadline for STACOM placeholder paper submission 
15 - July submission system opens for test set
14 - Aug deadline for STACOM paper submission
15 - Sep registration and docker submission deadline
12 - Oct release final results