Paper Info
Title
Feature Selection for Privileged Modalities in Disease Classification
Abstract
Multimodal data allows supervised learning while considering multiple complementary views of a problem, improving final diagnostic performance of trained models. Data modalities that are missing or difficult to obtain in clinical situations can still be incorporated into model training using the learning using privileged information (LUPI) framework. However, noisy or redundant features in the privileged modality space can limit the amount of knowledge transferred to the diagnostic model during the LUPI learning process. We consider the problem of selecting desirable features from both standard features which are available during both model training and testing, and privileged features which are only available during model training. A novel filter feature selection method named NMIFS+ is introduced that considers redundancy between standard and privileged feature spaces. The algorithm is evaluated on two disease classification datasets with privileged modalities. Results demonstrate an improvement in diagnostic performance over comparable filter selection algorithms.
Year
DOI
Venue
2021
10.1007/978-3-030-89847-2_7
MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT
Keywords
DocType
Volume
Privileged learning, Mutual information, Knowledge transfer, Feature selection, Multimodal data, Clinical decision support
Conference
13050
ISSN
Citations 
PageRank 
0302-9743
0
0.34
References 
Authors
0
16
Name
Order
Citations
PageRank
Winston Zhang100.68
Najla Al Turkestani201.69
Jonas Bianchi302.70
Celia Le400.68
Romain Deleat-Besson501.69
Antonio Ruellas603.04
Lucia Cevidanes723.43
Marilia Yatabe801.01
Joao Goncalves901.35
Erika Benavides1000.34
Fabiana Soki1102.37
Juan Prieto1212.39
Beatriz Paniagua1300.34
Jonathan Gryak1438.64
Kayvan Najarian1583.23
Reza Soroushmehr1602.70