Cover Image

Crowdtruth validation: a new paradigm for validating algorithms that rely on image correspondences

Feature tracking and 3D surface reconstruction are key enabling techniques to computer-assisted minimally invasive surgery. One of the major bottlenecks related to training and validation of new algorithms is the lack of large amounts of annotated images that fully capture the wide range of anatomic...

Full description

Saved in:
Bibliographic Details
Main Authors: Maier-Hein, Lena (Author) , Kondermann, Daniel (Author) , Roß, Tobias (Author) , Mersmann, Sven (Author) , Heim, Eric (Author) , Bodenstedt, Sebastian (Author) , Kenngott, Hannes Götz (Author) , Sancez Bach, Alexandro (Author) , Wagner, Martin (Author) , Preukschas, Anas (Author) , Wekerle, Anna-Laura (Author) , Helfert, Stefanie (Author) , März, Keno (Author) , Mehrabi, Arianeb (Author) , Speidel, Stefanie (Author) , Stock, Christian (Author)
Format: Article (Journal)
Language:English
Published: 18 April 2015
In: International journal of computer assisted radiology and surgery
Year: 2015, Volume: 10, Issue: 8, Pages: 1201-1212
ISSN:1861-6429
DOI:10.1007/s11548-015-1168-3
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1007/s11548-015-1168-3
Get full text
Author Notes:Lena Maier-Hein, Daniel Kondermann, Tobias Roß, Sven Mersmann, Eric Heim, Sebastian Bodenstedt, Hannes Götz Kenngott, Alexandro Sanchez, Martin Wagner, Anas Preukschas, Anna-Laura Wekerle, Stefanie Helfert, Keno März, Arianeb Mehrabi, Stefanie Speidel, Christian Stock
Description
Summary:Feature tracking and 3D surface reconstruction are key enabling techniques to computer-assisted minimally invasive surgery. One of the major bottlenecks related to training and validation of new algorithms is the lack of large amounts of annotated images that fully capture the wide range of anatomical/scene variance in clinical practice. To address this issue, we propose a novel approach to obtaining large numbers of high-quality reference image annotations at low cost in an extremely short period of time.
Item Description:Gesehen am 05.06.2020
Physical Description:Online Resource
ISSN:1861-6429
DOI:10.1007/s11548-015-1168-3

Similar Items