Leonardo inspace 3d

The MICCAI 2020 CADA challenge provided 109 cases. Image data of patients with cerebral aneurysms without vasospasm were collected for the purpose of assisting diagnosis and treatment [32 (link)]. The image data were acquired utilizing the digital subtraction AXIOM Artis C-arm system. Post-processing was performed using LEONARDO InSpace 3D (Siemens, Forchheim, Germany). After implementation of the contrast agent, a reconstruction of a volume of interest was selected by a neurosurgeon. The reconstructed images generally consist of 220 contiguous slices. The imaging parameters were as follows: in-plane size of $256\times 256$ ; iso-voxel size of 0.5 mm. Patients were of different ages and genders, making the samples diverse.

The challenge for aneurysm rupture risk estimation is task 3 in cerebral aneurysm detection and analysis (CADA) challenge. The challenge organizers provided 110 datasets with 128 annotated aneurysms. The image data of patients were acquired utilizing the digital subtraction AXIOM Artis C-arm system by a rotational acquisition time of 5 s with 126 frames. Postprocessing was performed using LEONARDO InSpace 3D (Siemens, Forchheim, Germany). All segmentation masks provided by a skilled annotator were checked by an experienced neurosurgeon later. Figure 1 shows the example of the two types of segmentation masks (stereolithography files and image files) for the same aneurysm. In addition, the rupture state and rupture information of each aneurysm are provided. After removing 3 cases with missing information, the remaining 125 cases are included for model training and validation.