Multimodal medical information retrieval with unsupervised rank fusion

Multimodal medical information retrieval with unsupervised rank fusion

Highlights • We propose a medical retrieval system supporting text and image queries. • It can retrieve either relevant PubMed articles or images from those articles. • It supports automatic query term expansion from the MeSH thesaurus. • Novel fusion algorithm, ISR, improves results from existing r...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computerized medical imaging and graphics 2015-01, Vol.39, p.35-45
Hauptverfasser: Mourão, André, Martins, Flávio, Magalhães, João
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Artificial Intelligence
Assisted query formulation
Data fusion
Data integration
Documentation - methods
Health care
Information retrieval
Information Storage and Retrieval - methods
Internal Medicine
Medical
Medical search
Medical Subject Headings
Multimodal Imaging - methods
Multimodal retrieval
Natural Language Processing
Other
Pattern Recognition, Automated - methods
PubMed
Radiology Information Systems - organization & administration
Retrieval
Search interfaces
Searching
Subtraction Technique
Terminology as Topic
Thesauri
User-Computer Interface
Vocabulary, Controlled
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Highlights • We propose a medical retrieval system supporting text and image queries. • It can retrieve either relevant PubMed articles or images from those articles. • It supports automatic query term expansion from the MeSH thesaurus. • Novel fusion algorithm, ISR, improves results from existing rank fusion algorithms. • We got the best result on multimodal case-based retrieval in 2013 ImageCLEFMedical
ISSN:0895-6111
1879-0771
DOI:10.1016/j.compmedimag.2014.05.006