The DEPOLL dataset for evaluating registration accuracy in AR-guided surgery
DePoLL (the Deformable Porcine Laparoscopic Liver) dataset was created to quantitatively evaluate registration accuracy for AR-guided liver surgery using a pre-operative CT model.
One reference configuration with a pre-operative CT (without insufflation) is given. Two reference 3D models are provided (one with the lobes of the liver segmented and one without). There are 13 infra-operative configurations to test the registration. In all these configurations, metal markers (clips on the surface, and spheres inside the lobes) are present and localized using intra-operative CT.
This work was performed in collaboration with the EnCoV research group.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
For reference, please cite our publication below. For any further information, please contact us.
Modrzejewski, R., Collins, T., Seeliger, B. et al. An in vivo porcine dataset and evaluation methodology to measure soft-body laparoscopic liver registration accuracy with an extended algorithm that handles collisions. Int J CARS 14, 1237–1245 (2019). https://doi.org/10.1007/s11548-019-02001-4
Composition of the dataset
The reference configuration
- The pre-operative CT
- The proposed models to register (with and without segmented lobes)
- The marker positions
The intra-operative configurations (1/2/3/4/5/6/7/8/9/10/11/12/13)
- The intra-operative CTs
- The exploration videos
- The target surfaces (extracted from CT and reconstructed from the video)
- The markers positions
- The markers association with the reference image
The association script
- An application script in matlab for marker association