Article

Incorporating domain knowledge into medical image clustering

Department of Computer Science, Harbin Engineering University, Harbin, PR China; Department of Computer Science, Harbin Institute of Technology, Harbin, PR China
Applied Mathematics and Computation DOI:10.1016/j.amc.2006.06.083 pp.844-856
Source: DBLP

ABSTRACT Image mining is more than just an extension of data mining to image domain but an interdisciplinary endeavor. Very few people have systematically investigated this field. Clustering medical images is an important part in domain-specific application image mining because there are several technical aspects which make this problem challenging. In this paper, we firstly quantify the domain knowledge about brain image (especially the brain symmetry), and then incorporate this quantified measurement into the clustering algorithm. Our algorithm contains two parts: (1) clustering regions of interest (ROI) detected from brain image; (2) clustering images based on the similarity of ROI. We apply the method to cluster brain images and present results to demonstrate its usefulness and effectiveness.

0 0
 · 
0 Bookmarks
 · 
43 Views
  • Source
    Article: Finding the largest area rectangle of arbitrary orientation in a closed contour
    Ruben Molano, Pablo G Rodriguez, Andres Caro, M Luisa Duran
    [show abstract] [hide abstract]
    ABSTRACT: For many software applications, it is sometimes necessary to find the rectangle of largest area inscribed in a polygon, in any possible direction. Thus, given a closed contour C, we consider approximation algorithms for the problem of finding the largest area rectangle of arbitrary orientation that is fully contained in C. Furthermore, we compute the largest area rectangle of arbitrary orientation in a quasi-lattice polygon, which models the C contour. In this paper, we propose an approximation algorithm that solves this problem with an O(n(3)) computational cost, where n is the number of vertices of the polygon. There is no other algorithm having lower computational complexity regardless of any constraints. In addition, we have developed a web application that uses the proposed algorithm. (C) 2012 Elsevier Inc. All rights reserved.
    Applied Mathematics and Computation 01/2012; 218(19):9866-9874. · 1.32 Impact Factor
  • Source
    Article: An Improved Image Mining Technique For Brain Tumour Classification Using Efficient Classifier
    Rajendran P, Madheswaran M
    [show abstract] [hide abstract]
    ABSTRACT: An improved image mining technique for brain tumor classification using pruned association rule with MARI algorithm is presented in this paper. The method proposed makes use of association rule mining technique to classify the CT scan brain images into three categories namely normal, benign and malign. It combines the low-level features extracted from images and high level knowledge from specialists. The developed algorithm can assist the physicians for efficient classification with multiple keywords per image to improve the accuracy. The experimental result on pre-diagnosed database of brain images showed 96% and 93% sensitivity and accuracy respectively.Keywords- Data mining; Image ming; Association rule mining; Medical Imaging; Medical image diagnosis; Classification;
    International Journal of Computer Science and Information Security. 01/2009;
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

algorithm
 
brain image
 
brain symmetry
 
cluster brain images
 
clustering algorithm
 
Clustering medical images
 
data mining
 
domain-specific application image mining
 
image domain
 
Image mining
 
interdisciplinary endeavor
 
quantified measurement
 
ROI
 
technical aspects