Brain abnormality detection using template matching
-
G.B. Praveen
,
Anita Agrawal
Abstract
Magnetic resonance imaging (MRI) is a widely used imaging modality to evaluate brain disorders. MRI generates huge volumes of data, which consist of a sequence of scans taken at different instances of time. As the presence of brain disorders has to be evaluated on all magnetic resonance (MR) sequences, manual brain disorder detection becomes a tedious process and is prone to inter- and intra-rater errors. A technique for detecting abnormalities in brain MRI using template matching is proposed. Bias filed correction is performed on volumetric scans using N4ITK filter, followed by volumetric registration. Normalized cross-correlation template matching is used for image registration taking into account, the rotation and scaling operations. A template of abnormality is selected which is then matched in the volumetric scans, if found, the corresponding image is retrieved. Post-processing of the retrieved images is performed by the thresholding operation; the coordinates and area of the abnormality are reported. The experiments are carried out on the glioma dataset obtained from Brain Tumor Segmentation Challenge 2013 database (BRATS 2013). Glioma dataset consisted of MR scans of 30 real glioma patients and 50 simulated glioma patients. NVIDIA Compute Unified Device Architecture framework is employed in this paper, and it is found that the detection speed using graphics processing unit is almost four times faster than using only central processing unit. The average Dice and Jaccard coefficients for a wide range of trials are found to be 0.91 and 0.83, respectively.
Acknowledgments
Authors would like to thank Dr. Ponraj Sundaram (Professor and Head of Department, Department of Neurosurgery, Goa Medical College, Goa, India), Dr. Sanjay Sardesai (Associate Professor, Department of Radiodiagnosis, Goa Medical College, Goa, India), Dr. Ankush Jajodia (Junior Resident, Radiodiagnosis, Goa Medical College, Goa, India), Dr. Subhash Jakhar (Senior Resident, Neurosurgery, Goa Medical College, Goa, India), for rendering their invaluable help in understanding the physiology of brain concepts related to analysis of MR images. Brain tumor image data used in this work were obtained from the NCI-MICCAI 2013 Challenge on Multimodal Brain Tumor Segmentation (http://martinos.org/qtim/miccai2013/index.html) organized by K. Farahani, M. Reyes, B. Menze, E. Gerstner, J. Kirby, and J. Kalpathy-Cramer. The challenge database contains fully anonymized images from the following institutions: ETH Zurich, University of Bern, University of Debrecen, and University of Utah and publicly available images from the Cancer Imaging Archive (TCIA).
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Research funding: None declared.
Employment or leadership: None declared.
Honorarium: None declared.
Competing interests: The funding organization(s) played no role in the study design; in the collection, analysis, and interpretation of data; in the writing of the report; or in the decision to submit the report for publication.
References
[1] About brain tumors: a primer for patients and caregivers. Chicago, IL: American Brain Tumor Association, 2012.Suche in Google Scholar
[2] Lee JH. Meningiomas: diagnosis, treatment, and outcome. 2008.Suche in Google Scholar
[3] Mamelak AN, Jacoby DB. Targeted delivery of antitumoral therapy to glioma and other malignancies with synthetic chlorotoxin (tm-601). Expert Opin Drug Delivery 2007;4:175–86.10.1517/17425247.4.2.175Suche in Google Scholar
[4] Harris GJ, Barta PE, Peng LW, Lee S, Brettschneider PD, Shah A, et al. MR volume segmentation of gray matter and white matter using manual thresholding: dependence on image brightness. Am J Neuroradiol 1994;15:225–30.Suche in Google Scholar
[5] Suzuki H, Toriwaki J-I. Automatic segmentation of head MRI images by knowledge guided thresholding. Comput MedImaging Graphics 1991;15:233–40.10.1016/0895-6111(91)90081-6Suche in Google Scholar
[6] Adams R, Bischof L. Seeded region growing. IEEE Transpattern Anal Machine Intelligence 1994;6:641–7.10.1109/34.295913Suche in Google Scholar
[7] Mittelhaeusser G, Kruggel F. Fast segmentation of brain magnetic resonance tomograms. Computer Vision, Virtual Reality and Robotics in Medicine, pp. 237–41. Springer, 1995.10.1007/978-3-540-49197-2_27Suche in Google Scholar
[8] Wong K-P. Medical image segmentation: methods and applications in functional imaging. In Handbook of Biomedical Image Analysis, pp. 111–82. Boston, MA: Springer, 2005.10.1007/0-306-48606-7_3Suche in Google Scholar
[9] Dam E, Loog M, Letteboer M. Integrating automatic and interactive brain tumor segmentation. In Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference, vol. 3, pp. 790–3. IEEE, 2004.10.1109/ICPR.2004.1334647Suche in Google Scholar
[10] Bezdek JC. Pattern recognition with fuzzy objective function algorithms. New York, USA: Springer Sci Business Media, 2013.Suche in Google Scholar
[11] Bishop CM. Pattern recognition. Machine Learning 2006;128:1–58.Suche in Google Scholar
[12] Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation. J Elect Imaging 2004;13:146–68.10.1117/1.1631315Suche in Google Scholar
[13] Otsu N. A threshold selection method from gray-level histograms. Automatica 1975;11:23–7.10.1109/TSMC.1979.4310076Suche in Google Scholar
[14] Tsai D-M, Chen Y-H. A fast histogram-clustering approach for multi-level thresholding. Pattern Recogn Lett 1992;13:245–52.10.1016/0167-8655(92)90075-BSuche in Google Scholar
[15] Tsai W-H. Moment-preserving thresolding: a new approach. Comput Vision, Graphics Image Process 1985;29:377–93.10.1016/0734-189X(85)90133-1Suche in Google Scholar
[16] Yen J-C, Chang F-J, Chang S. A new criterion for automatic multilevel thresholding. IEEE Trans Image Process 1995;4:370–8.10.1109/83.366472Suche in Google Scholar
[17] Wang S, Haralick RM. Automatic multithreshold selection. ComputVision Graphics Image Process 1984;25:46–67.10.1016/0734-189X(84)90048-3Suche in Google Scholar
[18] Jain R, Kasturi R, Schunck BG. Machine vision, Vol. 5, McGraw-Hill: New York, 1995.Suche in Google Scholar
[19] Sonka M, Hlavac V, Boyle R. Image processing, analysis, and machine vision. Cengage Learning, 2014.Suche in Google Scholar
[20] Mary Synthuja Jain Preetha M, Padma Suresh L, Bosco J. Image segmentation using seeded region growing. In Computing, Electronics and Electrical Technologies (ICCEET), 2012, International Conference, pp. 576–83. Poland: IEEE, 2012.10.1109/ICCEET.2012.6203897Suche in Google Scholar
[21] Clarke LP, Velthuizen RP, Phuphanich S, Schellenberg JD, Arrington JA, Silbiger MM. MRI: stability of three supervised segmentation techniques. Magn Reson Imaging 1993;11:95–106.10.1016/0730-725X(93)90417-CSuche in Google Scholar
[22] Havaei M, Jodoin P-M, Larochelle H. Efficient interactive brain tumor segmentation as within-brain knn classification. In Pattern Recognition (ICPR), 2014 22nd International Conference, pp. 556–61. Stockholm, Sweden: IEEE, 2014.10.1109/ICPR.2014.106Suche in Google Scholar
[23] Tu JV. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 1996;49:1225–31.10.1016/S0895-4356(96)00002-9Suche in Google Scholar
[24] Clarke LP. MR image segmentation using MLM and artificial neural nets. MedPhys 1991;8:673.Suche in Google Scholar
[25] Ozkan M, Dawant BM, Maciunas RJ. Neural-network-based segmentation of multi-modal medical images: a comparative and prospective study. IEEE Trans MedImaging 993;12:534–44.10.1109/42.241881Suche in Google Scholar PubMed
[26] Huang G-B, Zhu Q-Y, Siew CK. Real-time learning capability of neural networks. IEEE Trans Neural Networks 2006;17:863–78.10.1109/TNN.2006.875974Suche in Google Scholar PubMed
[27] Martn-Landrove M, Villalta R. Brain tumor image segmentation using neural networks. In Proceedings of International Society of Magnetic Resonance in Medicine, p. 14, 2006.Suche in Google Scholar
[28] Sauwen N, Acou M, Van Cauter S, Sima DM, Veraart J, Maes F, et al. Comparison of unsupervised classification methods for brain tumor segmentation using multi-parametric MRI. NeuroImage: Clin 2016;12:753–64.10.1016/j.nicl.2016.09.021Suche in Google Scholar PubMed PubMed Central
[29] Sammouda R, Niki N, Nishitani H. Neural networks based segmentation of magnetic resonance images. In Nuclear Science Symposium and Medical Imaging Conference, 1994, IEEE Conference Record, Vol 4, pp. 1827–31. New York: IEEE, 1994.Suche in Google Scholar
[30] Yeh J-Y, Fu JC. A hierarchical genetic algorithm for segmentation of multi-spectral human-brain MRI. Expert Syst Appl 2008;34:1285–95.10.1016/j.eswa.2006.12.012Suche in Google Scholar
[31] Praveen GB, Anita A. Hybrid approach for brain tumor detection and classification in magnetic resonance images. In Communication, Control and Intelligent Systems (CCIS), 2015, pp. 162–6. Mathura, India: IEEE, 2015.10.1109/CCIntelS.2015.7437900Suche in Google Scholar
[32] Praveen GB, Anita A. Multi stage classification and segmentation of brain tumor. In Computing for Sustainable Global Development (INDIACom), 2016, 3rd International Conference, pp. 1628–32. IEEE, 2016.Suche in Google Scholar
[33] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436.10.1038/nature14539Suche in Google Scholar PubMed
[34] Solanes A, Igual L, Radua J. Detection of midline brain abnormalities using convolutional neural networks. 2018.10.1007/978-3-030-11723-8_15Suche in Google Scholar
[35] Rezaei M, Yang H, Meinel C. Brain abnormality detection by deep convolutional neural network. arXiv preprint arXiv:1708.05206, 2017.Suche in Google Scholar
[36] Pan Y, Huang W, Lin Z, Zhu W, Zhou J, Wong J, et al. Brain tumor grading based on neural networks and convolutional neural networks. In Engineering in Medicine and Biology Society (EMBC), 2015, 37th Annual International Conference of the IEEE, pp. 699–702, IEEE, 2015.10.1109/EMBC.2015.7318458Suche in Google Scholar PubMed
[37] Rao V, Sarabi MS, Jaiswal A. Brain tumor segmentation with deep learning. MICCAI Multimodal Brain Tumor Segmentation Challenge (BraTS). 2015;56–9.Suche in Google Scholar
[38] Zhao X, Wu Y, Song G, Li Z, Fan Y, Zhang Y. Brain tumor segmentation using a fully convolutional neural network with conditional random fields. In International Workshop on Brain Lesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pp. 75–87. Cham, Switzerland: Springer, 2016.10.1007/978-3-319-55524-9_8Suche in Google Scholar
[39] Nie D, Zhang H, Adeli E, Liu L, Shen D. 3d deep learning for multi-modal imaging-guided survival time prediction of brain tumor patients. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 212–20. Cham, Switzerland: Springer, 2016.10.1007/978-3-319-46723-8_25Suche in Google Scholar PubMed PubMed Central
[40] Chen L, Bentley P, Rueckert D. Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks. NeuroImage Clin 2017;15:633–43.10.1016/j.nicl.2017.06.016Suche in Google Scholar PubMed PubMed Central
[41] Kamnitsas K, Ledig C, Newcombe VF, Simpson JP, Kane AD, Menon DK, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. MedImage Anal 2017;36:61–78.10.1016/j.media.2016.10.004Suche in Google Scholar PubMed
[42] Maier O, Schröder C, Forkert ND, Martinetz T, Handels H. Classifiers for ischemic stroke lesion segmentation: a comparison study. PLoS One 2015;10:1–18.10.1371/journal.pone.0145118Suche in Google Scholar PubMed PubMed Central
[43] Praveen GB, Agrawal A, Sundaram P, Sardesai S. Ischemic stroke lesion segmentation using stacked sparse autoencoder. Comput Biol Med 2018 8;99:38–52. DOI: 10.1016/j.compbiomed.2018.05.027.Suche in Google Scholar PubMed
[44] Musoko V, Procházka A. Non-linear median filtering of biomedical images. Institute of Chemical Technology, Department of Computing and Control Engineering, 2009.Suche in Google Scholar
[45] De Boor C. On calculating with b-splines. J Approx Theor 1972;6:50–62.10.1016/0021-9045(72)90080-9Suche in Google Scholar
[46] Tustison NJ, Avants BB, Cook PA, Zheng Y, Egan A, Yushkevich PA, et al. N4itk: improved n3 bias correction. IEEE TransMed Imaging 2010;29:1310–20.10.1109/TMI.2010.2046908Suche in Google Scholar PubMed PubMed Central
[47] Tustison N, Wintermark M, Durst C, Avants B, et al. Ants and arboles. In MICCAI BraTS Workshop, pp. 47–50. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
[48] Cordier N, Menze B, Delingette H, Ayache N. Patch-based segmentation of brain tissues. In MICCAI challenge on multimodal brain tumor segmentation, pp. 6–17. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
[49] Buendia P, Taylor T, Ryan M, John N. A grouping artificial immune network for segmentation of tumor images. In MICCAI challenge on multimodal brain tumor segmentation, pp. 1–5. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
[50] Doyle S, Vasseur F, Dojat M, Forbes F. Fully automatic brain tumor segmentation from multiple MR sequences using hidden Markov fields and variational EM. In MICCAI challenge on multimodal brain tumor segmentation, pp. 18–22. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
[51] Zhao L, Sarikaya D, Corso JJ. Automatic brain tumor segmentation with MRF on supervoxels. In MICCAI challenge on multimodal brain tumor segmentation, pp. 51–4. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
[52] Meier R, Bauer S, Slotboom J, Wiest R, Reyes M. A hybrid model for multimodal brain tumor segmentation. In MICCAI challenge on multimodal brain tumor segmentation, pp. 31–7. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
[53] Guo X, Schwartz L, Zhao B. Semi-automatic segmentation of multimodal brain tumor using active contours. In MICCAI challenge on multimodal brain tumor segmentation, pp. 27–30. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
[54] Pereira S, Festa J, Mariz JA, Sousa N, Silva CA. Automatic brain tissue segmentation of multi-sequence MR images using random decision forests. In MICCAI challenge on multimodal brain segmentation, pp. 23–6. Nagoya, Japan: IEEE, 2013.10.54294/azta8gSuche in Google Scholar
[55] Gupta M, Prabhakar Rao BV, Rajagopalan V, Das A, Kesavadas C. Volumetric segmentation of brain tumor based on intensity features of multimodality magnetic resonance imaging. In Computer, Communication and Control (IC4), 2015 International Conference, pp. 1–6. Indore, India: IEEE, 2015.10.1109/IC4.2015.7375550Suche in Google Scholar
[56] Tang H, Lu H, Liu W, Tao X. Tumor segmentation from single contrast MR images of human brain. In Biomedical Imaging (ISBI), 2015 IEEE 12th International Symposium, pp. 46–9. IEEE, 2015.10.1109/ISBI.2015.7163813Suche in Google Scholar
[57] Reza S, Iftekharuddin KM. Multi-class abnormal brain tissue segmentation using texture. In MICCAI challenge on multimodal brain segmentation, pp. 38–42. Nagoya, Japan: IEEE, 2013.Suche in Google Scholar
©2018 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Research Articles
- Brain abnormality detection using template matching
- Offset compensated baseline restoration and computationally efficient hybrid interpolation for the brain PET
- The similarity of selected statins – a comparative analysis
- Cell proliferation induced by modified cationic dextran
- An empirical wavelet transform based approach for multivariate data processing application to cardiovascular physiological signals
Artikel in diesem Heft
- Research Articles
- Brain abnormality detection using template matching
- Offset compensated baseline restoration and computationally efficient hybrid interpolation for the brain PET
- The similarity of selected statins – a comparative analysis
- Cell proliferation induced by modified cationic dextran
- An empirical wavelet transform based approach for multivariate data processing application to cardiovascular physiological signals
