Retrieval of medical cases for diagnostic decisions : VISCERAL retrieval benchmark

Jimenez-del-Toro, Oscar (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Müller, Henning (University and University Hospitals of Geneva, Switzerland) ; Foncubierta-Rodriguez, Antonio (Swiss Federal Institue of Technology (ETH)ZurichSwitzerland) ; Langs, Georg (Medical University of Vienna, Austria) ; Hanbury, Allan (TU Wien, Austria)

Health providers currently construct their differential diagnosis for a given medical case most often based on textbook knowledge and clinical experience. Data mining of the large amount of medical records generated daily in hospitals is only very rarely done, limiting the reusability of these cases. As part of the VISCERAL project, the Retrieval benchmark was organized to evaluate available approaches for medical case-based retrieval. Participant algorithms were required to find and rank relevant medical cases from a large multimodal dataset (including semantic RadLex terms extracted from text and visual 3D data) for common query topics. The relevance assessment of the cases was done by medical experts who selected cases that are useful for a differential diagnosis for the given query case. The approaches that integrated information from both the RadLex terms and the 3D volumes (mixed techniques) obtained the best results based on five standard evaluation metrics. The benchmark set up, dataset description and result analysis are presented.


Faculté:
Economie et Services
Ecole:
HEG-VS
Institut:
Institut Informatique de gestion
Classification:
Economie/gestion
Adresse bibliogr.:
Cham, Springer
Date:
Cham
Springer
2017
Pagination:
pp. 127-141
Veröffentlicht in
Cloud-based benchmarking of medical image analysis
DOI:
ISBN:
978-3-319-49642-9
Ressource(s) externe(s):
Le document apparaît dans:

Note: The status of this file is: restricted


 Datensatz erzeugt am 2017-10-23, letzte Änderung am 2018-12-11

Volltext:
Volltext herunterladen
PDF

Dieses Dokument bewerten:

Rate this document:
1
2
3
 
(Bisher nicht rezensiert)