Diagnosis of Alzheimer’s Disease in Brain Images using Pulse Coupled Neural Network
Aiswarya.V.S1, Jemimah Simon2

1Aiswarya V.S, Master of Engineering Software Engineering, Vins Christian College of Engineering, Nagercoil (Tamil Nadu), India.
2Jemimah Simon, Assistant Professor, Vins Christian College of Engineering, Nagercoil (Tamil Nadu), India.
Manuscript received on 10 May 2013 | Revised Manuscript received on 18 May 2013 | Manuscript Published on 30 May 2013 | PP: 99-101 | Volume-2 Issue-6, May 2013 | Retrieval Number: F0804052613/13©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Alzheimer’s disease is most commonly occurring type of disease in elderly patients. An automatic computer-aided diagnosis tool that supports the interpretation of functional brain images is proposed in this paper for the diagnosis of the Alzheimer’s disease. This new technique is based on Pulse Coupled Neural Network (PCNN) for image classification. In Alzheimer’s disease diagnosis mainly two databases are selected: a Single photon emission computed tomography (SPECT) database and Positron emission tomography (PET) images, both contains details for Alzheimer’s disease patients(AD) and healthy references (NOR). The major steps in detection of Alzheimer’s disease are feature extraction, feature reduction and classification of these features for making correct decision. The features from the images are extracted using wavelet packet transform (WPT). The reduction & selection of the most relevant features is done using non-negative matrix factorization (NMF). The resulting sets of data, which contain a reduced number of features, are classified by means of a Pulse Coupled Neural Network – based classifier for decision. This novel technique provides high classification accuracy and also reduces time consumption compared to existing methods.
Keywords: Alzheimer’s Disease, Wavelet Packet Tree, Positron Emission Tomography (PET), Single Photon Emission Computed Tomography (SPECT), Pulse Coupled Neural Network (PCNN).

Scope of the Article: Network Operations & Management