Improved Biliary Detection and Diagnosis through Intelligent Machine Analysis


Logeswaran, Rajasvaran (2012) Improved Biliary Detection and Diagnosis through Intelligent Machine Analysis. Computer Methods and Programs in Biomedicine, 107 (3). pp. 404-412. ISSN 01692607

Full text not available from this repository.


This paper reports on work undertaken to improve automated detection of bile ducts in magnetic resonance cholangiopancreatography (MRCP) images, with the objective of conducting preliminary classification of the images for diagnosis. The proposed I-BDeDIMA (Improved Biliary Detection and Diagnosis through Intelligent Machine Analysis) scheme is a multi-stage framework consisting of successive phases of image normalization, denoising, structure identification, object labeling, feature selection and disease classification. A combination of multiresolution wavelet, dynamic intensity thresholding, segment-based region growing, region elimination, statistical analysis and neural networks, is used in this framework to achieve good structure detection and preliminary diagnosis. Tests conducted on over 200 clinical images with known diagnosis have shown promising results of over 90% accuracy. The scheme outperforms related work in the literature, making it a viable framework for computer-aided diagnosis of biliary diseases. (C) 2010 Elsevier Ireland Ltd. All rights reserved.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 28 Dec 2012 07:35
Last Modified: 28 Dec 2012 07:35


Downloads per month over past year

View ItemEdit (login required)