Markerless Coil Classification and Localization in a Routine MRI Examination Setting using an RGB-D Camera

  • Janani G. Nadar
  • Xia Zhong
  • Andreas Maier
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


In a routine MRI scan, a radio-frequency (RF) coil must be selected and placed around the region of interest (ROI). This is a crucial step in the workflow as the accurate coil placement is paramount for obtaining high-quality images. However, in the existing workflow, the position of the coil placement on the patient is estimated empirically by the medical technical assistant (MTA). This routine coil placement process has two shortcomings. On the one hand, the expertise of MTA in coil placement, taking the anatomical difference between patients into account, have a huge impact on the accuracy of the coil placement, and subsequently the image quality. On the other hand, the risk of selecting and placing the incorrect coil should be also be acknowledged. To improve the current workflow and provide feedback ahead of the MRI scans, we use an RGB-D camera to acquire extra information. Using the depth images taken before and after placing the coil, we propose a novel method to classify the coil type and localize the coil position during the coil placement process such that the MTA can place the coil correctly and accurately. We trained and evaluated our method over 100 synthetic data sets. We used two types of coils and placed and deformed them differently according to the anatomical region. The evaluation shows that we can classify the coil type without any error, and localize the coil with a mean translational error of 7.1 cm and mean rotation angle error of 0.025 rad.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Singh V, Chang Y, Ma K, et al. Estimating a patient surface model for optimizing the medical scanning workflow. Proc MICCAI. 2014; p. 472–479.Google Scholar
  2. 2.
    Zhong X, Strobel N, Sanders JC, et al. Generation of Personalized Computational Phantoms Using Only Patient Metadata. Proc IEEE NSS/MIC. 2017.Google Scholar
  3. 3.
    Frohwein L, He M, Buther F, et al. Determination of position and shape of flexible mri surface coils using the Microsoft Kinect for attenuation correction in PET/MRI. Eur J Nucl Med Mol Imaging Physics. 2015;2(1):A79.Google Scholar
  4. 4.
    Bernardini F, Mittleman J, Rushmeier H, et al. The ball-pivoting algorithm for surface reconstruction. IEEE Trans Vis Comput Graphics. 1999;5(4):349–359.Google Scholar
  5. 5.
    Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vision. 2004;60(2):91–110.Google Scholar
  6. 6.
    Darom T, Keller Y. Scale-invariant features for 3-D mesh models. IEEE Trans Image Process. 2012;21(5):2758–2769.Google Scholar
  7. 7.
    Csurka G, Dance C, Fan L, et al. Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision at ECCV; 2004. p. 1–22.Google Scholar
  8. 8.
    Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273–297.Google Scholar
  9. 9.
    Fischler MA, Bolles RC. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM. 1981;24(6):381–395.Google Scholar
  10. 10.
    Kabsch W. A solution for the best rotation to relate two sets of vectors. Acta Crystallogr A. 1976;32(5):922–923.Google Scholar

Copyright information

© Springer-Verlag GmbH Deutschland 2018

Authors and Affiliations

  1. 1.Pattern Recognition Lab, Department of Computer ScienceFriedrich-Alexander-Universität Erlangen-NürnbergErlangenDeutschland
  2. 2.Erlangen Graduate School in Advanced Optical Technologies(SAOT)ErlangenDeutschland

Personalised recommendations