Abstract
Accurate brain tumor segmentation plays a significant role in the area of radiotherapy diagnosis and in the proper treatment for brain tumor detection. Typically, the brain tumor has poor boundary and low contrast between normal and lesion soft tissues that makes segmentation of brain tumor in the CT images a challenging task. This paper presents a novel approach to brain image segmentation using pulse-coupled neural network (PCNN) and zero level set (ZL) with Sobolev gradient (SG) method. In this article, PCNN is designed to use as an edge mapper to provide a regional description for the ZL to segregate the CT images based on contour maps. The PCNN is used to estimate the exact threshold to obtain the prominent edges of the images. Resulting edges are utilized in the ZL to extract image contour from the source image. Due to the over-sensitivity of the ZL method on the initial contour, a level set with the SG has been equipped to overcome the limitation of the ZL method. The experimental results show satisfactory segmentation outcomes with excellent accuracy and acceleration in comparison with the state-of-the-art methods.
Similar content being viewed by others
References
Dora L, Agrawal S, Panda R, Abraham A (2017) State of the art methods for brain tissue segmentation: a review. IEEE Rev Bio Eng 10:235–249
Eklund A, Dufort P, Forsberg D, LaConte SM (2013) Medical image processing on the GPU-past, present and future. Med Image Anal 17(8):1073–1094
Hsieh J (2003) Computed tomography: principles, design, artifacts, and recent advances, vol 114. SPIE Press, Bellingham
Kak AC, Slaney M (2001) Principles of computerized tomographic imaging. Society for Industrial and Applied Mathematics, Philadelphia
Wang Z, Ma Y, Cheng F, Yang L (2010) Review of pulse-coupled neural networks. Image Vis Comput 28(1):5–13
Osher S, Sethian JA (1988) Fronts propagating with curvature-dependent speed: algorithms based on Hamilton–Jacobi formulations. J Comput Phys 79(1):12–49
Sui H, Peng F, Xu C, Sun K, Gong J (2012) GPU-accelerated MRF segmentation algorithm for SAR images. Comput Geosci 43:159–166
Sanders J, Kandrot E (2010) CUDA by example: an introduction to general-purpose GPU programming, portable documents. Addison-Wesley Professional, Boston
Shattuck DW, Sandor-Leahy SR, Schaper KA, Rottenberg DA, Leahy RM (2001) Magnetic resonance image tissue classification using a partial volume model. NeuroImage 13(5):856–876
Akgun D, Erdogmus P (2015) GPU accelerated training of image convolution filter weights using genetic algorithms. Appl Soft Comput 30:585–594
Brodtkorb AR, Hagen TR, Saetra ML (2013) Graphics processing unit (GPU) programming strategies and trends in GPU computing. J Parallel Distrib Comput 73(1):4–13
Kirk DB, Hwu WMW (2010) Programming massively parallel processors. Elsevier, Amsterdam
Massingill BL, Mattson TG, Sanders BA (2004) Patterns for parallel programming. The software patterns series. Addison-Wesley Professional, Boston
Vagli P, Turini F, Cerri F, Neri E (2008) Temporal bone. Image Process Radiol 12:137–149
Yoo TS (2004) Insight into images: principles and practice for segmentation, registration, and image analysis. AK Peters Ltd, Natick
Sonka M, Hlavac V, Boyle R (2014) Image processing, analysis, and machine vision. Cengage Learning, Stamford
Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Image Process 10(2):266–277
Neuberger JW (1997) Sobolev gradients and differential equations. Lecture notes in mathematics, vol 1670. Springer, Berlin
Khadidos A, Sanchez V, Li CT (2017) Weighted level set evolution based on local edge features for medical image segmentation. IEEE Trans Image Process 26(4):1979–1991
Pratondo A, Chui CK, Ong SH (2016) Robust edge-stop functions for edge-based active contour models in medical image segmentation. IEEE Signal Process Lett 23(2):220–226
Wei S, Qu H, Hou M (2011) Automatic image segmentation based on PCNN with adaptive threshold time constant. Neurocomputing 74:1485–1491
Xie W, Li Y, Ma Y (2015) PCNN-based level set method of automatic mammographic image segmentation. Opt Int J Light Electron Opt 127(4):1644–1650
Song E, Huang D, Hung C (2011) Semi-supervised multi-class adaboost by exploiting unlabeled data. Expert Syst Appl 38:6720–6726
Konstantinos K, Christian L, Virginia FJN et al (2017) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78
Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for scene segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495
Litjens G, Kooi T, Bejnordi BE (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
Zhang H, Wang S, Xu X, Chow T, Jonathan Wu QMJ (2018) Tree2Vector: learning a vectorial representation for tree-structured data. IEEE Trans Neural Netw Learn Syst 29(11):C1–5173
Smistad E, Falch TL, Bozorgi M et al (2015) Medical image segmentation on GPUs-A comprehensive review. Med Image Anal 20(1):1–18
Renka RJ (2010) Geometric curve modeling with Sobolev gradients. In: Neuberger JW (ed) Sobolev gradients and differential equations. Springer, Berlin, pp 199–208
Jaros M, Strakos P et al (2017) Implementation of K-means segmentation algorithm on Intel Xeon Phi and GPU: application in medical imaging. Adv Eng Softw 103:21–28
Renka RJ (2005) Sobolev gradient method for construction of elastic curves in regular surfaces. Nonlinear Anal Theory Methods Appl 63(5):e1789–e1796
Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22(1):61–79
Levine M, Nazif A (1985) Dynamic measurement of computer generated image segmentations. IEEE Trans Pattern Anal Mach Intell 7:155–164
Lin L, Yang W et al (2016) Inference with collaborative model for interactive tumor segmentation in medical image sequences. IEEE Trans Cybern 46(12):2796–2809
Liu B, Cheng HD, Huang J, Tian J, Tang X, Liu J (2010) Probability density difference-based active contour for ultrasound image segmentation. Pattern Recognit 43(6):2028–2042
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Biswas, B., Ghosh, S.K. & Ghosh, A. A novel CT image segmentation algorithm using PCNN and Sobolev gradient methods in GPU frameworks. Pattern Anal Applic 23, 837–854 (2020). https://doi.org/10.1007/s10044-019-00837-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-019-00837-9