A Fast Approach to Automatic Detection of Brain Lesions

  • Subhranil Koley
  • Chandan Chakraborty
  • Caterina Mainero
  • Bruce Fischl
  • Iman AganjEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10154)


Template matching is a popular approach to computer-aided detection of brain lesions from magnetic resonance (MR) images. The outcomes are often sufficient for localizing lesions and assisting clinicians in diagnosis. However, processing large MR volumes with three-dimensional (3D) templates is demanding in terms of computational resources, hence the importance of the reduction of computational complexity of template matching, particularly in situations in which time is crucial (e.g. emergent stroke). In view of this, we make use of 3D Gaussian templates with varying radii and propose a new method to compute the normalized cross-correlation coefficient as a similarity metric between the MR volume and the template to detect brain lesions. Contrary to the conventional fast Fourier transform (FFT) based approach, whose runtime grows as \( O\left( {N\,\log N} \right) \) with the number of voxels, the proposed method computes the cross-correlation in \( O\left( N \right) \). We show through our experiments that the proposed method outperforms the FFT approach in terms of computational time, and retains comparable accuracy.


Fast Fourier Transform Template Match Lesion Detection Multiple Sclerosis Lesion Fast Fourier Transform Method 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



Support for this research was provided in part by the National Institute of Diabetes and Digestive and Kidney Diseases (K01DK101631, R21DK108277), the National Institute for Biomedical Imaging and Bioengineering (P41EB015896, R01EB006758, R21EB018907, R01EB019956), the National Institute on Aging (5R01AG008122, R01AG016495), the National Institute for Neurological Disorders and Stroke (R01NS0525851, R21NS072652, R01NS070963, R01NS083534, 5U01NS086625), the National Institutes of Health (NIH) Blueprint for Neuroscience Research (5U01-MH093765; part of the multi-institutional Human Connectome Project), and was made possible by the resources provided by the NIH Shared Instrumentation Grants (S10RR023401, S10RR019307, and S10RR023043). Additionally, SK was supported by a Fulbright-Nehru Doctoral Research Fellowship (Award no: 2098/DR/2015-2016), and CC was supported by the DAE-Young Scientist Research Award Scheme (2013/36/38-BRNS/2350, dt.25-11-2013) by Board of Research in Nuclear Sciences (BRNS), Dept. of Atomic Energy, Govt. of India. BF has a financial interest in CorticoMetrics, a company whose medical pursuits focus on brain imaging and measurement technologies. BF’s interests were reviewed and are managed by Massachusetts General Hospital and Partners HealthCare in accordance with their conflict of interest policies.


  1. 1.
    Tourassi, G.D., Vargas-Voracek, R., Catarious, D.M., Floyd, C.E.: Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information. Med. Phys. 30, 2123–2130 (2003)CrossRefGoogle Scholar
  2. 2.
    Lochanambal, K.P., Karnan, M., Sivakumar, R.: Identifying masses in mammograms using template matching. In: Proceedings of the Second International Conference on Communication Software and Networks (ICCSN 2010), pp. 339–342 (2010)Google Scholar
  3. 3.
    Osman, O., Ozekes, S., Ucan, O.N.: Lung nodule diagnosis using 3D template matching. Comput. Biol. Med. 37, 1167–1172 (2007)CrossRefGoogle Scholar
  4. 4.
    Moltz, J.H., Schwier, M., Peitgen, H.-O.: A general framework for automatic detection of matching lesions in follow-up CT. In: Proceedings of the IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2009), pp. 843–846 (2009)Google Scholar
  5. 5.
    Wang, P., DeNunzio, A., Okunieff, P., O’Dell, W.G.: Lung metastases detection in CT images using 3D template matching. Med. Phys. 34, 915–922 (2007)CrossRefGoogle Scholar
  6. 6.
    Warfield, S.K., Kaus, M., Jolesz, F.A., Kikinis, R.: Adaptive, template moderated, spatially varying statistical classification. Med. Image Anal. 4, 43–55 (2000)CrossRefGoogle Scholar
  7. 7.
    Ambrosini, R.D., Wang, P., O’Dell, W.G.: Computer-aided detection of metastatic brain tumors using automated three-dimensional template matching. J. Magn. Reson. Imaging 31, 85–93 (2010)CrossRefGoogle Scholar
  8. 8.
    Farjam, R., Parmar, H.A., Noll, D.C., Tsien, C.I., Cao, Y.: An approach for computer-aided detection of brain metastases in post-Gd T1-W MRI. Magn. Reson. Imaging 30, 824–836 (2012)CrossRefGoogle Scholar
  9. 9.
    Yang, S., Nam, Y., Kim, M.-O., Kim, E.Y., Park, J., Kim, D.-H.: Computer-aided detection of metastatic brain tumors using magnetic resonance black-blood imaging. Invest. Radiol. 48, 113–119 (2013)CrossRefGoogle Scholar
  10. 10.
    Wang, X.-F., Gong, J., Bu, R.-R., Nie, S.-D.: A 3D adaptive template matching algorithm for brain tumor detection. In: Ma, S., Jia, L., Li, X., Wang, L., Zhou, H., Sun, X. (eds.) LSMS/ICSEE 2014. CCIS, vol. 461, pp. 50–61. Springer, Heidelberg (2014). doi: 10.1007/978-3-662-45283-7_6 Google Scholar
  11. 11.
    Muñoz, A., Ertlé, R., Unser, M.: Continuous wavelet transform with arbitrary scales and O(N) complexity. Sig. Process. 82, 749–757 (2002)CrossRefzbMATHGoogle Scholar
  12. 12.
    Kogan, S.: A note on definite integrals involving trigonometric functions (1999).
  13. 13.
    Cooley, J.W., Tukey, J.W.: An algorithm for the machine calculation of complex fourier series. Math. Comput. 19, 297–301 (1965)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Subhranil Koley
    • 1
    • 2
  • Chandan Chakraborty
    • 2
  • Caterina Mainero
    • 1
    • 3
  • Bruce Fischl
    • 1
    • 3
    • 4
  • Iman Aganj
    • 1
    • 3
    Email author
  1. 1.Athinoula A. Martinos Center for Biomedical Imaging, Radiology DepartmentMassachusetts General HospitalCharlestownUSA
  2. 2.School of Medical Science and TechnologyIndian Institute of Technology KharagpurKharagpurIndia
  3. 3.Radiology DepartmentHarvard Medical SchoolBostonUSA
  4. 4.Computer Science and Artificial Intelligence LaboratoryMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations