Context sensitive cardiac x-ray imaging: a machine vision approach to x-ray dose control

Article English OPEN
Kengyelics, SM ; Gislason-Lee, AJ ; Keeble, C ; Magee, DR ; Davies, AG (2015)
  • Publisher: Society of Photo-optical Instrumentation Engineers (SPIE)

Modern cardiac x-ray imaging systems regulate their radiation output based on the thickness of the patient to maintain an acceptable signal at the input of the x-ray detector. This approach does not account for the context of the examination or the content of the image displayed. We have developed a machine vision algorithm that detects iodine-filled blood vessels and fits an idealized vessel model with the key parameters of contrast, diameter, and linear attenuation coefficient. The spatio-temporal distribution of the linear attenuation coefficient samples, when appropriately arranged, can be described by a simple linear relationship, despite the complexity of scene information. The algorithm was tested on static anthropomorphic chest phantom images under different radiographic factors and 60 dynamic clinical image sequences. It was found to be robust and sensitive to changes in vessel contrast resulting from variations in system parameters. The machine vision algorithm has the potential of extracting real-time context sensitive information that may be used for augmenting existing dose control strategies.
  • References (9)

    1 World Health Organisation, “The top 10 causes of death, Factsheet no 310.” http://www. (2014). Accessed 17th June 2014.

    2 P. Ludman, National Audit of Percutaneous Coronary Interventional Procedures Public Report, British Cardiovascular Intervention Society (2011).

    3 E. Grech, “Percutaneous coronary intervention. I. History and development,” Brit. Med. J. 326, 1080-1082 (2003).

    4 E. Grech, “Percutaneous coronary intervention. II. The procedure,” Brit. Med. J. 326, 1137- 1140 (2003).

    5 M. J. Eisenberg, J. Afilalo, P. R. Lawler, M. Abrahamowicz, H. Richard, and L. Pilote, “Cancer risk related to low-dose ionizing radiation from cardiac imaging in patients after acute myocardial infarction,” CMAJ 183(4), 430-436 (2011).

    6 D. Z˘ ontar, D. Kuhelj, D. S˘krk, and U. Zdes˘ar, “Patient peak skin doses from cardiac interventional procedures,” Radiat. Prot. Dosim. 139, 162-165 (2010).

    7 A. J. Gislason-Lee, A. R. Cowen, and A. G. Davies, “Dose optimization in cardiac x-ray imaging,” Med. Phys. 40, 091911-1-11 (2013).

    8 MATLAB, Version (R2014a), The MathWorks Inc., Natick, Massachusetts (2014).

    9 A. Frangi, W. Niessen, K. Vincken, and M. Viergever, “Multiscale vessel enhancement filtering,” in Medical Image Computing and Computer-Assisted Interventation MICCAI98, W. Wells, A. Colchester, and S. Delp, Eds., Lecture Notes in Computer Science 1496, 130-137, Springer Berlin Heidelberg (1998).

  • Metrics
    No metrics available
Share - Bookmark