3D-IRCADb (3D Image Reconstruction for Comparison of Algorithm Database) is a database includes several sets of anonymized medical images of patients and the manual segmentation of the various structures of interest performed by clinical experts. The 3D medical images and masks of the segmented structures of interest are available as DICOM files. The representation of segmented zones is also provided as surface meshes in VTK format. This database will soon be completed with new cases.
The objective of this database is to compare segmentation algorithms mesh generation algorithms and breathing simulation algorithms. Moreover, the database can be used within the framework of anatomical education or medical simulation.
In the future, this database will be completed by many other cases. Moreover, the automated segmentation of structures of interest will also be added so as to offer an efficient tool to the scientific community for the comparison of algorithms.
The content of 3D-IRCADb is subject to a CC Attribution-Non commercial-No Derivative Works 3.0 licence. If you use this database with your segmentation or mesh algorithm, do not hesitate to contact us and to send us your results with the authorization of publication on our website. This way, a specific CC licence can be created with the references in link with your work and your results will be added with a free access on the 3D-IRCADb database.
This first database (3D-IRCADb-01) is composed of the CT-scans of 10 women and 10 men with hepatic tumours in 75% of cases. Where appropriate, the Couninaud segment number corresponding to the location of tumours is also provided.
This second database (3D-IRCADb-02) is composed of 2 anonymized CT-scans. The first one has been realized during the arterial phase in inhaled position, whereas the second one has been realized during the portal phase in exhaled position. The patient has a hepatic focal nodular hyperplasia in segment VII according to Couinaud’s description.