Probability Neural Network Classification Model of Brain Tissue Pathologies using High Frequency Techniques
[1]
S. S. Shanbhag , Electronics and Communication Engineering, Gogte Institute of Technology, Belgaum, India.
[2]
G. R. Udupi , Electronics and Communication Engineering, Gogte Institute of Technology, Belgaum, India.
[3]
K. M. Patil , Indian Institute of Technology (Madras), Belgaum, India.
[4]
K. Ranganath , RAGAVS, Diagnostics and Research Center Pvt. Ltd., Bangalore, India.
The conventional method of analysing the brain tissue pathologies on Diffusion Weighted-Magnetic Resonance (DW-MR) images is by human inspection. Such operator-assisted classification techniques are not viable for large amounts of medical data and are generally non-reproducible. The use of neural networks shows a great potential in this area to carry out fast, accurate and automatic data classification. In the present study, Probability Neural Network (PNN) architecture was employed to develop an automated classification model based on the quantified signal intensity variations on DW-MR images, derived from the subjects with brain pathologies, using High Frequency Power (HFP) parameter. The PNN models were designed to provide important reference in judging the timing and developmental stages of the subjects with cerebral infarction and Intracerebral Haemorrhage (ICH), and help in carrying out the differential diagnosis of the subjects with brain tumors, namely, glioma and meningioma. The PNN models were able to accurately (100%) categorize ICH subjects into their respective stages, and presented an overall efficiency of 96.67% in classifying the infarct subjects. Also the model was able to clearly differentiate (100%) between the subjects with glioma and meningioma. Consequently, the PNN models developed in the present work were helpful in providing valuable information about the brain tissue pathologies, which could speed up the diagnosis and execution of treatment. Further, it could help in providing timely and appropriate treatment to the subjects with these brain pathologies, to protect them from additional damage to their brain tissues.
Cerebral Infarction, Diffusion Weighted Images, Glioma, Intracerebral Haemorrhage, Magnetic Resonance Imaging, Meningioma, Probability Neural Network, Signal Intensity
[1]
M. V. Kumar and S. Kulkarni, “Tumors classification using PNN methods,” International Journal of Soft Computing and Engineering, November 2012, 2(5), pp. 266-268.
[2]
K. Z. Mao, K. C. Tan, W. Ser, “Probabilistic neural network structure determination for pattern classification,” IEEE Transactions on Neural Networks, July 2000, 11(4), pp. 1009-1016.
[3]
D. F. Specht, “Probabilistic neural networks,” Neural Networks, 1990, 3, pp. 109-118.
[4]
C. Kramer, B. Mckay, J. Belina, “Probabilistic neural network array architecture for ECG classification,” Proceedings of Annual International Conference of IEEE Engineering in Medicine and Biology Society, 1995, 17, pp. 807-808.
[5]
M. T. Musavi, K. H. Chan, D. M. Hummels, K. Kalantri, “On the generalization ability of neural network classifier,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(6), pp. 659-663.
[6]
I. M. M. El Emary and S. Ramakrishnan, “On the application of various probabilistic neural networks in solving different pattern classification problems,” World Applied Sciences Journal, 2008, 4 (6), pp. 772-780.
[7]
J. M. Shen, X. W. Xia, W. G. Kang, J. J. Yuan, L. Sheng, “The use of MRI apparent diffusion coefficient (ADC) in monitoring the development of brain infarction”, BMC Medical Imaging, 2011, 11(2).
[8]
W. G. Bradley Jr., “MR appearance of hemorrhage in the brain,” Radiology, October 1993, 189(1), pp. 15-26.
[9]
R. Rajeshkannan, S. Moorthy, K. P. Sreekumar, R. Rupa, N. K. Prabhu, “Clinical applications of diffusion weighted MR imaging: A review,” Indian Journal of Radiology and Imaging, 2006, 16(4), pp. 705-710.
[10]
D. Le Bihan, Temperature imaging by NMR. In: Le Bihan, ed. “Diffusion and perfusion magnetic resonance: Applications to functional MRI”, New York: Raven, 1995, pp. 181-187.
[11]
J. H. Burdette, P. E. Ricci, N. Petitti, A. D. Elster, “Cerebral infarction: Time course of signal intensity changes on diffusion weighted images,” American Journal of Roentgenology, September 1998, 171(3), pp. 791-795.
[12]
J. D. Eastwooda, S. T. Engelterd, J. F. MacFall, D. M. Delongc, J. M. Provenzalea, “Quantitative assessment of the time course of infarct signal intensity on diffusion-weighted images,” American Journal of Neuroradiology, April 2003, 24(4), pp. 680-687.
[13]
K. Kang, D. G. Na, J. W. Ryoo, H. S. Byun, H. G. Roh, Y. S. Pyeun, “Diffusion-weighted MR imaging of intracerebral haemorrhage,” Korean Journal of Radiology, October-December 2001, 2(4), pp. 183-191.
[14]
S. E. Maier, Y. Sun, R. V. Mulkern, “Diffusion imaging of brain tumors,” NMR in Biomedicine, August 2010, 23(7), pp. 849-864.
[15]
Gonzalez R. C., Wintz P., Image transforms in ‘Digital Image Processing’, 2nd edition, 1987, Addison-Wesley, U.S.A.
[16]
K. G. Prabhu, K. M. Patil, S. Srinivasan, “Diabetic feet at risk: A new method of analysis of walking foot pressure images at different levels of neuropathy for early detection of plantar ulcers”, Medical and Biological Engineering and Computing, 2001, 39, pp. 288-293.
[17]
S. S. Shanbhag, G. R. Udupi, K. M. Patil, K. Ranganath, “Analysis of cerebral infarct signal intensity on diffusion-weighted MR images using frequency domain techniques,” American Journal of Biomedical Engineering, 2012, 2(3), pp. 124-130.
[18]
S. S. Shanbhag, G. R. Udupi, K. M. Patil, K. Ranganath, “A new method of analysing the intracerebral haemorrhage signal intensity on brain MRI images using frequency domain techniques,” Journal of Biomedical Science and Engineering, 2013, 6, pp. 56-64.
[19]
S. S. Shanbhag, G. R. Udupi, K. M. Patil, K. Ranganath, “A new method of analysis of brain MRI images for quantitative grading of brain tissue pathology,” Proceedings of the 2011 International Conference on Biomedical Engineering and Technology, Malaysia, 4-5 June 2011, pp. 35-39.
[20]
S. Haykin, “Neural networks: A comprehensive foundation,” 1994, MacMillan College Publishing Co., New York.
[21]
MATLAB User’s Guide, “The Math Works” Inc., 1998, Natick, MA 01760-2098.
[22]
P. D. Wasserman, “Advanced methods in neural computing,” Van Nostrand Reinhold, 1993, New York, pp. 35-55.
[23]
A. M. Molinaro, R. Simon, R. M. Pfeiffer, “Prediction error estimation: a comparison of resampling methods,” Bioinformatics, 2005, 21(15), pp. 3301-3307.
