EMIDEC
automatic Evaluation of Myocardial Infarction from Delayed-Enhancement Cardiac MRI

The EMIDEC challenge abstract

Keywords: MRI, heart, myocardial infarction, segmentation, classification, delayed-enhancement

One crucial parameter to evaluate the state of the heart after myocardial infarction (MI) is the viability of the myocardial segment, i.e. if the segment recovers its functionality upon revascularization. MRI performed several minutes after the injection of a contrast agent (delayed enhancement-MRI or DE-MRI) is a method of choice to evaluate the extent of MI, and by extension, to assess viable tissues after an injury (in conjunction with the thickening of the muscle evaluated from cine-MRI).

The two main objectives of the EMIDEC challenge are first to classify normal and pathological cases from the clinical information with or without DE-MRI, and secondly to automatically detect the different relevant areas (the myocardial contours, the infarcted area and the permanent microvascular obstruction area (no-reflow area)) from a series of short-axis DE-MRI covering the left ventricle. The segmentation allows us to make a quantification of the MI, in absolute value (mm3) or percentage of the myocardium.

The database consists of 150 exams (all from different patients) divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are provided to distinguish normal and pathological cases. The training set (100 cases) will be available mid-April.

To participate to the challenge and get access to the datasets, each participant should create an account . Once registered, the participant could access to the datasets of the challenge through its personal account.

The Segmentation contest will take place in September 2020, before the conference, and the global ranking will be based on geometrical and clinical metrics currently used in medical practices.

The Classification contest will happen during the MICCAI conference in October 2020, and the global ranking will correspond to the classification accuracy.

Moreover, the participants will also be requested to submit a paper following the MICCAI format that describe the methodology. The submitted papers will be accepted after a deep proofreading.

The EMIDEC challenge: Two goals

Task 1: Segmentation contest of the myocardium for all the DE-MRI exams, and the myocardial infarction and no-reflow areas on exams classified as pathologic ones. Contest done before the conference.

Task 2: Classification contest of the exams in normal or pathological one, according to the clinical data with or without the DE-MRI exams (two sub-challenges, the first one from only the clinical informations, and the second one considering the clinical informations and the DE-MRI). Contest done online and on-site

Important dates

Task 1: Segmentation contest

Releases:

  • Mid-April : Release of the training cases.
  • September, 1 and for 2 weeks: Release of the testing dataset

Registration and challenge:

  • Mid-April : Start of the registration process.
  • August, 31: End of registration.
  • September, 15: End of the challenge (deadline for the submission of the papers).
  • During the conference: Results of the challenge.

Task 2: Classification contest

Releases:

  • Mid-April : Release of the training cases.
  • Online and on-site challenge (release of the testing cases during the conference).

Registration and challenge:

  • Mid-April : Start of the registration process.
  • August, 31: End of registration.
  • September, 15: Submission of the papers.
  • Online and on-site challenge.

Organising Team

Primary contact person

Alain Lalande,
ImVia Laboratory and University Hospital of Dijon, Dijon, FR

Other members of the team

Fabrice Meriaudeau, ImVia Laboratory, Dijon, FR
Dominique Ginhac, ImVia Laboratory, Dijon, FR
Abdul Qayyum, ImVia Laboratory, Dijon, FR
Khawla Brahim, ImVia Laboratory, Dijon, FR
Thibaut Pommier, University Hospital of Dijon, Dijon, FR
Raphaƫl Couturier, Femto-St laboratory, Belfort, FR
Michel Salomon, Femto-St laboratory, Belfort, FR
Gilles Perrot, Femto-St laboratory, Belfort, FR
Zhihao Chen, Femto-St laboratory, Belfort, FR