Datasets

General description

The training dataset is composed of 450 patients as follows:

  • 366 patients with good/medium image quality;
  • 84 patients with poor image quality;
  • 222 patients with an ejection fraction lower that 45%;
  • 87 patients with an ejection fraction higher that 55%.

For all these data, the corresponding manual references given by one cardiologist expert along with additional information (diastolic-systolic phase instants) are provided.

This work has published to IEEE TMI journal. You must cite this paper for any use of the CAMUS database

  • S. Leclerc, E. Smistad, J. Pedrosa, A. Ostvik, et al.
    "Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography" in IEEE Transactions on Medical Imaging, vol. 38, no. 9, pp. 2198-2210, Sept. 2019.

    doi: 10.1109/TMI.2019.2900516