Application of Artificial Neural Network to Live Predict Brain Lesions like Multiple Sclerosis, Glioma, Glioblastoma and Metastases and Superiority of Refractive Index Over other Parameters

  • Tapan Krishna Biswas Researcher Department of Instrumentation and Electronics Engineering, JADAVPUR UNIVERSITY KOLKATA,INDIA
  • Anindya Ganguly College of Health and Human Sciences, Charles Darwin University, Australia
  • Rajib Bandopadhyay Department of Instrumentation and Electronics Engineering, Jadavpur University, India
  • Ajoy Kr. Dutta Department of Production Engineering, Jadavpur University, India
Keywords: Artificial Neural Network (ANN), Magnetic Resonance Imaging (MRI), Metabolites of MR Spectroscopy, Refractive Index (RI), Independent Numeric and dependent Variable, Prediction

Abstract

Artificial Neural Network  an extremely authoritative method of Supervised Machine Learning was applied to detect the different pathological lesions in the brain, like multiple sclerosis MS,  glioma of different grades and metastasis. Structural changes in the brain lesions may be noticed in MR images. MR spectroscopic graph may be informative to some extent but is not so easy to diagnose the disease accurately always. Use of ANN helps identifying the condition in doubtful cases. ANN train different data collected from various patients such as – Refractive Index, T2 relaxation values, Apparent Diffusion Coefficient (ADC), Creatine (CR), Choline (CHO), NAA (N-Acetyl Aspartate), ratio of CR/NAA, LIP/LAC (Lipid/lactate), MI ( Myoinositol), CHO/CR and T2 value in the periphery of lesion. Prediction by ANN after training the data, shows high accuracy in diagnosis. RI was found to be unique and most accurate amongst these parameters.

Author Biography

Tapan Krishna Biswas, Researcher Department of Instrumentation and Electronics Engineering, JADAVPUR UNIVERSITY KOLKATA,INDIA

 RESEARCHER 

DEPARTMENT OF INSTRUMENTATION AND ELECTRONICS ENGINEERING

JADAVPUR UNIVERSITY

KOLKATA

 

References

(1) Taghpour Zahir SH, Rezaei sadrabadi Dehghani F, Evaluation of Diagnostic Value of CT Scan and MRI in Brain Tumors and Comparison with Biopsy, Iranian Journal of Pediatric Hematology Oncology 2011 ;1.

(4):121-125

(2) Hagen T, Nieder C, Moringlane JR. Feiden W,Konig J, Correlation of preoperative neuroradiologic with postoperative histological diagnosis in pathological intracranial process. Der Radiologe, Nov 1995; 35(11):808-15

(3) Horská Alena and Barker Peter B., Imaging of Brain Tumors: MR Spectroscopy and Metabolic Imaging, Neuroimaging Clin N Am. 2010 ; 20(3): 293–310.

(4) Jansen JF, Backes WH, Nicolay K, Kooi ME. 1H MR spectroscopy of the brain: absolute quantification of metabolites.Radiology2006; 240 (2): 318–32.

(5) Stuart J. Russell, Peter Norvig (2010) Artificial Intelligence: A Modern Approach, Third Edition, Prentice Hall ISBN 9780136042594.

(6) T K Biswas, R Bandopadhyay, A Dutta, Validating The Discriminating Efficacy Of MR T2 Relaxation Value Of Different Brain Lesions And Comparison With Other Differentiating Factors: Use Of Artificial Neural Network And Principal Component Analysis. The Internet Journal of Radiology. 2017 Volume 20 Number 1. ISPUB DOI: 10.5580/IJRA.52614

(7) Biswas TK, Gupta A. Retrieval of true color of the internal organ of CT images and attempt to tissue characterization by refractive index : Initial experience. Indian Journal of Radiology and Imaging 2002;12:169-178

(8) Biswas TK, Luu T In vivo MR Measurement of Refractive Index, Relative Water Content and T2 Relaxation time of Various Brain lesions With Clinical Application to Discriminate Brain Lesions. The Internet Journal of Radiology 2009;13(1).

(9) T K Biswas, S R Choudhury, A Ganguly, R Bandopadhyay, A Dutta, Refractive Index As Surrogate Biological Marker Of Tumefactive And Other Form Of Multiple Sclerosis And Its Superiority Over Other Methods, Internet Journal of Radiology, https://print.ispub.com/api/0/ispub-article/46167.

(10) Kono K, Inoue Y, Nakayama K, et al. The role of diffusion-weighted imaging in patients with brain tumors. AJNR Am J Neuroradiol 2001; 22: 1081–1088.

(11) G. James Variance and Bias for General Loss Functions, Machine Learning 2003; 51, 115135. (http://www-bcf.usc.edu/~gareth/research/bv.pdf

(12) Haykin S., Neural Networks: A Comprehensive Foundation, 2nd edition, Pearson Educ. Asia, Hong Kong, 2001.

(13) Neural Network,http://www.palisade.com/neuraltools/neural_networks.asp.

(14) Bishop C.M., Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.

(15) Jain Sparsh, Biswas Tapan K, Bandyopadhyay Rajib; Diagnosis of Brain Lesions, Glioma, Multiple-Sclerosis and Metastases from MRI: An efficient classifier-aided method using Refractive Index as a surrogate Biological Marker. Journal of Biomedical Engineering and Medical Imaging, 2018;5 (3) :19-26

(16) Samuel, Arthur, Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development,1959;Vol 3(3): 210–229

(17) Stone, Mervyn, Asymptotics for and against cross-validation. Biometrika 1977;64 (1): 29–35.

(18) Ronald L Wasserstein, Nicole Lazar. A The ASA's Statement on p-Values: Context, Process, and Purpose 2016; 70(2): 129-133.

(19) Wells, S Lillian, Stereotaxic Brain Biopsy, https://neurosurgery.ufl.edu/residency/about-us/clinical- specialties/stereotactic-brain-biopsy/

Published
2018-09-07
How to Cite
Biswas, T. K., Ganguly, A., Bandopadhyay, R., & Dutta, A. K. (2018). Application of Artificial Neural Network to Live Predict Brain Lesions like Multiple Sclerosis, Glioma, Glioblastoma and Metastases and Superiority of Refractive Index Over other Parameters. Journal of Biomedical Engineering and Medical Imaging, 5(4), 09. https://doi.org/10.14738/jbemi.54.4919