DocumentCode
3253053
Title
A fuzzy multilayer perceptron network based detection and classification of lobar intra-cerebral hemorrhage from Computed Tomography images of brain
Author
Datta, Aparna ; Datta, Ashis ; Biswas, Biswajit
Author_Institution
Dept. of Comput. Applic., Meghnad Saha Inst. of Technol., Kolkata, India
fYear
2011
fDate
21-23 Dec. 2011
Firstpage
257
Lastpage
262
Abstract
Medical imaging techniques and analysis tools like Computed Tomography (CT) enable the doctors and radiologists to identify as well as diagnose various disorders in internal structures. In this paper, fuzzy multilayer perceptron network based algorithm used for segmentation and region classification and region severance algorithm is used for detection and location of Intra-cerebral hemorrhage. According to location different types of lobar Intra-cerebral hemorrhages are classified. Experimental visualization results are presented which were computed on real intra-cerebral hemorrhage patient brain data. The objective of this paper is to propose a method to assist the radiologists in identifying the different type of lobar Intracerebral hemorrhage and to arrive at a decision faster and accurate.
Keywords
brain; computerised tomography; fuzzy neural nets; image classification; image segmentation; medical disorders; medical image processing; multilayer perceptrons; object detection; brain; computed tomography images; fuzzy multilayer perceptron network; image segmentation; lobar intra-cerebral hemorrhage detection; medical imaging; radiologists; region classification; region severance algorithm; Blood; Classification algorithms; Computed tomography; Hemorrhaging; Histograms; Labeling; Mathematical model; Computed Tomography (CT); Fuzzy Multilayer Perceptron Network (FMLP); Intra-cerebral hemorrhage (ICH); Lobar;
fLanguage
English
Publisher
ieee
Conference_Titel
Recent Trends in Information Systems (ReTIS), 2011 International Conference on
Conference_Location
Kolkata
Print_ISBN
978-1-4577-0790-2
Type
conf
DOI
10.1109/ReTIS.2011.6146878
Filename
6146878
Link To Document