Medical Case Retrieval From a Committee of Decision Trees

A novel content-based information retrieval framework, designed to cover several medical applications, is presented in this paper. The presented framework allows the retrieval of possibly incomplete medical cases consisting of several images together with semantic information. It relies on a committ...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2010-09, Vol.14 (5), p.1227-1235
Main Authors: Quellec, G, Lamard, M, Bekri, L, Cazuguel, G, Roux, C, Cochener, B
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Biomedical equipment
Biomedical imaging
CAD
Computer Science
Content based retrieval
content-based image retrieval (CBIR)
Databases, Factual
Decision Support Systems, Clinical
Decision Trees
decision trees (DTs)
Delta-sigma modulation
Diabetes
Diabetic Retinopathy - diagnosis
Diagnosis, Computer-Assisted - methods
Engineering Sciences
Fundus Oculi
Humans
Image Processing, Computer-Assisted
Image retrieval
Information retrieval
Information Storage and Retrieval - methods
Machine Learning
Mammography
medical databases
Medical diagnostic imaging
Medical services
Signal and Image processing
Signal Processing, Computer-Assisted
Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A novel content-based information retrieval framework, designed to cover several medical applications, is presented in this paper. The presented framework allows the retrieval of possibly incomplete medical cases consisting of several images together with semantic information. It relies on a committee of decision trees, decision support tools well suited to process this type of information. In our proposed framework, images are characterized by their digital content. It was applied to two heterogeneous medical datasets for computer-aided diagnoses: a diabetic retinopathy follow-up dataset (DRD) and a mammography-screening dataset (DDSM). Measure of precision among the top five retrieved results of 0.788 ± 0.137 and 0.869 ± 0.161 was obtained on DRD and DDSM, respectively. On DRD, for instance, it increases by half the retrieval of single images.
ISSN:1089-7771
2168-2194
1558-0032
2168-2208
DOI:10.1109/TITB.2010.2053716