publication . Other literature type . Article . 2013

GPU accelerated segmentation and centerline extraction of tubular structures from medical images.

Anne C. Elster; Frank Lindseth; Frank Lindseth; Erik Smistad;
Restricted
  • Published: 01 Nov 2013
  • Publisher: Springer Science and Business Media LLC
Abstract
To create a fast and generic method with sufficient quality for extracting tubular structures such as blood vessels and airways from different modalities (CT, MR and US) and organs (brain, lungs and liver) by utilizing the computational power of graphic processing units (GPUs).    A cropping algorithm is used to remove unnecessary data from the datasets on the GPU. A model-based tube detection filter combined with a new parallel centerline extraction algorithm and a parallelized region growing segmentation algorithm is used to extract the tubular structures completely on the GPU. Accuracy of the proposed GPU method and centerline algorithm is compared with the r...
Read more
doi: 10.1007/s11548-013-0956-x
Subjects
ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputingMethodologies_COMPUTERGRAPHICS
free text keywords: Surgery, Health Informatics, Radiology Nuclear Medicine and imaging, General Medicine, Extraction methods, Tree traversal, Segmentation, Computer vision, Computer science, Detection filter, Doppler ultrasound, Region growing segmentation, Artificial intelligence, business.industry, business, Skeletonization, Extraction algorithm
Download fromView all 2 versions
International Journal of Computer Assisted Radiology and Surgery
Article
Provider: Microsoft Academic Graph
International Journal of Computer Assisted Radiology and Surgery
Article . 2013
Provider: Crossref
http://dx.doi.org/10.1007/s115...
Other literature type . 2013
Provider: Datacite
Springer Science and Business Media LLC
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue