Image dissimilarity-based quantification of lung disease from CT

Authors:
Lauge Sørensen;Marco Loog;Pechin Lo;Haseem Ashraf;Asger Dirksen;Robert P. W. Duin;Marleen de Bruijne
Affiliations:
Department of Computer Science, University of Copenhagen, Denmark;Department of Computer Science, University of Copenhagen, Denmark and Pattern Recognition Laboratory, Delft University of Technology, The Netherlands;Department of Computer Science, University of Copenhagen, Denmark;Department of Respiratory Medicine, Gentofte University Hospital, Denmark;Department of Respiratory Medicine, Gentofte University Hospital, Denmark;Pattern Recognition Laboratory, Delft University of Technology, The Netherlands;Department of Computer Science, University of Copenhagen, Denmark and Departments of Radiology & Medical Informatics, Erasmus, The Netherlands
Venue:
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Year:
2010

Citing 6
Cited 4

Solving the multiple instance problem with axis-parallel rectangles

Artificial Intelligence
Dissimilarity representations allow for building good classifiers

Pattern Recognition Letters
Multi-Instance Kernels

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Static Posterior Probability Fusion for Signal Detection: Applications in the Detection of Interstitial Diseases in Chest Radiographs

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Learning COPD Sensitive Filters in Pulmonary CT

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Global and Local Multi-valued Dissimilarity-Based Classification: Application to Computer-Aided Detection of Tuberculosis

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II

An improvement of dissimilarity-based classifications using sift algorithm

PReMI'11 Proceedings of the 4th international conference on Pattern recognition and machine intelligence
Dissimilarity-based classification of anatomical tree structures

IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
Hierarchical spatial matching for medical image retrieval

MMAR '11 Proceedings of the 2011 international ACM workshop on Medical multimedia analysis and retrieval
Dissimilarity-Based classifications in eigenspaces

CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose to classify medical images using dissimilarities computed between collections of regions of interest. The images are mapped into a dissimilarity space using an image dissimilarity measure, and a standard vector space-based classifier is applied in this space. The classification output of this approach can be used in computer aided-diagnosis problems where the goal is to detect the presence of abnormal regions or to quantify the extent or severity of abnormalities in these regions. The proposed approach is applied to quantify chronic obstructive pulmonary disease in computed tomography (CT) images, achieving an area under the receiver operating characteristic curve of 0.817. This is significantly better compared to combining individual region classifications into an overall image classification, and compared to common computerized quantitative measures in pulmonary CT.