Automated domain-specific feature selection for classificationbased segmentation of tomographic medical image data

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

1 Citation (Scopus)

Abstract

Classification-based segmentation is an approach to establish generic analysis of medical image data. Significant feature sets covering different characteristics of regions to segment allow for robust discrimination of topologically defined classes. In this work a method for automated domain-specific feature selection to achieve a higher level of predictability is presented, incorporating multivariate feature analysis. For calculation of the probability density function, different approaches, like histogram analysis, enumeration of the entire feature space or umbrella Monte Carlo Integration are investigated. Furthermore, meta features calculated on entire classification results rather than on particular regions are introduced. Predictability of both, single local and meta features, is evaluated for different medical datasets as well for simulated intensity volumes, allowing testing and evaluating specific classification problems. The automated feature selection proofs to be accurate for classification-based segmentation utilizing well-known machine learning approaches.

Original languageEnglish
Title of host publication3rd International Workshop on Innovative Simulation for Health Care, IWISH 2014
EditorsFrancesco Longo, Marco Frascio, Yury Merkuryev, Vera Novak, Agostino G. Bruzzone
PublisherDIME UNIVERSITY OF GENOA
Pages26-35
Number of pages10
ISBN (Electronic)9788897999379
Publication statusPublished - 2014
Event3rd International Workshop on Innovative Simulation for Health Care, IWISH 2014 - Bordeaux, France
Duration: 10 Sep 201412 Sep 2014

Publication series

Name3rd International Workshop on Innovative Simulation for Health Care, IWISH 2014

Conference

Conference3rd International Workshop on Innovative Simulation for Health Care, IWISH 2014
Country/TerritoryFrance
CityBordeaux
Period10.09.201412.09.2014

Keywords

  • Automated feature selection
  • Classification-based segmentation
  • Monte Carlo Integration
  • Multivariate feature analysis

Fingerprint

Dive into the research topics of 'Automated domain-specific feature selection for classificationbased segmentation of tomographic medical image data'. Together they form a unique fingerprint.

Cite this