Automated interpretation of ventilation-perfusion lung scintigrams for the diagnosis of pulmonary embolism using support vector machines

Anders Ericsson, A Huart, A Ekefjard, Karl Åström, H Holst, Eva Evander, Per Wollmer, Lars Edenbrandt

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

The purpose of this study was to develop a new completely automated method for the interpretation of ventilation-perfusion (V-P) lung scintigrams for the diagnosis of pulmonary embolism. A new way of extracting features, characteristic for pulmonary embolism is presented. These features are then used as input to a Support Vector Machine, which discriminates between pulmonary embolism or no embolism. Using a material of 509 training cases and 104 test cases, the performance of the system, measured as the area under the ROC curve, was 0.86 in the test group. It is concluded that a completely automatic method can be used for interpretation of V-P scintigrams. It is faster and more robust than a previously presented method [4,5] and the accuracy is at the same level as the the previous method. It also handles abnormalities in the lungs.
Original languageEnglish
Title of host publication13th Scandinavian Conference, SCIA 2003 Halmstad, Sweden, June 29 – July 2, 2003 Proceedings/Lecture Notes in Computer Science
PublisherSpringer
Pages415-421
Volume2749
ISBN (Print)978-3-540-40601-3
Publication statusPublished - 2003
Event13th Scandinavian Conference, SCIA 2003 - Halmstad, Sweden
Duration: 2003 Jun 292003 Jul 2

Publication series

Name
Volume2749
ISSN (Print)1611-3349
ISSN (Electronic)0302-9743

Conference

Conference13th Scandinavian Conference, SCIA 2003
Country/TerritorySweden
CityHalmstad
Period2003/06/292003/07/02

Subject classification (UKÄ)

  • Respiratory Medicine and Allergy
  • Cardiac and Cardiovascular Systems

Fingerprint

Dive into the research topics of 'Automated interpretation of ventilation-perfusion lung scintigrams for the diagnosis of pulmonary embolism using support vector machines'. Together they form a unique fingerprint.

Cite this