Feature selection for SVM-based vascular anomaly detection

Authors:
Maria A. Zuluaga;Edgar J. F. Delgado Leyton;Marcela Hernández Hoyos;Maciej Orkisz
Affiliations:
Universidad de los Andes, Bogotá, Colombia and CREATIS, Université de Lyon, Université Lyon 1, INSA-Lyon, CNRS UMR5220, INSERM U630, Villeurbanne, France;Universidad de los Andes, Bogotá, Colombia and CREATIS, Université de Lyon, Université Lyon 1, INSA-Lyon, CNRS UMR5220, INSERM U630, Villeurbanne, France;Universidad de los Andes, Bogotá, Colombia;CREATIS, Université de Lyon, Université Lyon 1, INSA-Lyon, CNRS UMR5220, INSERM U630, Villeurbanne, France
Venue:
MCV'10 Proceedings of the 2010 international MICCAI conference on Medical computer vision: recognition techniques and applications in medical imaging
Year:
2010

Citing 7
Cited 1

Random Forests

Machine Learning
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Muliscale Vessel Enhancement Filtering

MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
A Classification Framework for Anomaly Detection

The Journal of Machine Learning Research
Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy

IEEE Transactions on Pattern Analysis and Machine Intelligence
Assessment of carotid artery stenoses in 3D contrast-enhanced magnetic resonance angiography, based on improved generation of the centerline

Machine Graphics & Vision International Journal
Particle filters, a quasi-monte carlo solution for segmentation of coronaries

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I

Learning from only positive and unlabeled data to detect lesions in vascular CT images

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work explores feature selection to improve the performance in the vascular anomaly detection domain. Starting from a previously defined classification framework based on Support Vector Machines (SVM), we attempt to determine features that improve classification performance and to define guidelines for feature selection. Three different strategies were used in the feature selection stage, while a Density Level Detection-SVM (DLD-SVM) was used to validate the performance of the selected features over testing data. Results show that a careful feature selection results in a good classification performance. DLD-SVM shows a poor performance when using all the features together, owing to the curse of dimensionality.