STATISTICAL CLASSIFICATION OF MAGNETIC RESONANCE IMAGES OF BRAIN EMPLOYING RANDOM FOREST CLASSIFIER

Joshi S.¹*, Deepa Shenoy P.², Venugopal K.R.³, Patnaik L.M.^4
1Department of Computer Science and Engineering, MGR University, Chennai
²Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, K R Circle, Bangalore – 01
³Department of Computer Science and Engineering, University Visvesvaraya College of Engineering, K R Circle, Bangalore – 01
⁴Vice Chancellor, Defence Institute of Advanced Technology, Pune, India
* Corresponding Author : sanjoshi17@yahoo.com

Received : -     Accepted : -     Published : 21-12-2009
Volume : 1     Issue : 2       Pages : 55 - 61
Int J Mach Intell 1.2 (2009):55-61
DOI : http://dx.doi.org/10.9735/0975-2927.1.2.55-61

Keywords : Data mining, Machine learning, Dementia, Alzheimer’s disease, Random forest classifier
Conflict of Interest : None declared

Data mining in brain imaging is an emerging field of high importance for providing prognosis, treatment, and a deeper understanding of how the brain functions. Dementia due to Alzheimer’s disease constitutes the fourth most common disorder among the elderly. Early detection of dementia and correct staging of the severity of dementia is critical to select the optional treatment. The present study was designed to classify and categorize brain images of dementia patients into three distinct classes i.e., Normal, Moderately diseased, and Severe. Decision Forest Classifier was employed to classify the various Magnetic Resonance Images (MRIs) of dementia patients. Results of screening the MRIs are organized by classification and finally grouped into the three categories, i.e., Normal, Moderate and Severe. Experimental results obtained indicated that the proposed method performs relatively well with the classification accuracy reaching nearly 99.32% in comparison with the already existing algorithms.

[1] Scatena R., Martorona Bottani P., Botta G., Pastove P. and Giardina. (2007) Expert Opin. Investig. Drugs, 16, 59-72  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[2] Jay M. E. (2005) JAOA, 3, 145-158  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[3] Caselli R .J., Beach T. J., Yaari R. and Reiman E. (2006) J. Clini. Psychiatry, 67, 1784 -1800  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[4] Hashimoto M., Rockenstein E., Crews and Masliah E. (2003) Neuromolecular. Med., .4, 21-36  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[5] Kerr M. and Small D. (2007) J. Neurosis. 80, 151-159  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[6] Hanumanthachar Joshi, Parle M. and Disale C. (2008) Alzheimer’s and Dementia, 4, 760-763  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[7] Hanumanthachar Joshi and Parle M. (2007) Colombia medica, 38(2), 132-139.  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[8] Hanumanthachar Joshi and Disale C. (2008) Frontiers in Neuroscience, 8, 12- 18  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[9] Francesco C., Audrey M. N., David R. M., Ercolano M. and Paolo. (2006) Evid Based Complement Alternat Med, 3, 411-424  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[10] Jogren M. S., Mielxe M., Gustafson D., Zandi P. and Skoog I. (2006) Mech. ageing dev, 127, 138-147  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[11] Jogren M. S., Mielxe M., Gustafson D., Zandi P. and Skoog I. (2006) Mech. ageing dev, 127, 138-147  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[12] Subramani M., William Rodman Shankle, Michael J., Pazzani, Padhraic Smyth and Malcolm B. (1999) J. Inter Neuropsycholog Soc., 12, 377-392  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[13] Vasileios Megalooikonomou, Despina Kontos and Dragoljub Pokrajac. (2004) Artificial Intelligence, 3 -6  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[14] Despina Kontos and Vasileios Megalooikonomou. (2004) SPIE, 53-70  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[15] Vasileios Megalooikonomou (2004) International Conference on acoustics, speech, and signal processing, Montreal, Canada. Published by IEEE Computer Society in IEEE Xplore USA, 614-615  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[16] Lazarevic A., Pokrajac D., Megalooikonomou V., and Obradovic Z. (2001) 4th International Conference on Neural Networks and Expert Systems in Medicine and Healthcare, Milos Island, Greece 20-22  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[17] Han M. and Kamber (2001) Data Mining: Concepts and Techniques, Published by Morgan Kaufmann, San Francisco, 279- 284.  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus  

[18] Leo Breiman (1999) Random Forests- Random Features Technical report published by university of California, Berkeley, 567.  
» CrossRef   » Google Scholar   » PubMed   » DOAJ   » CAS   » Scopus