Multiple instance learning for breast MRI based on generic spatio-temporal features

Maken, Fahira Afzal and Bradley, Andrew P. (2015). Multiple instance learning for breast MRI based on generic spatio-temporal features. In: 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings. International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Conference, Brisbane, QLD, Australia, (902-906). 19-24 April 2015. doi:10.1109/ICASSP.2015.7178100


Author Maken, Fahira Afzal
Bradley, Andrew P.
Title of paper Multiple instance learning for breast MRI based on generic spatio-temporal features
Conference name International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Conference
Conference location Brisbane, QLD, Australia
Conference dates 19-24 April 2015
Convener IEEE
Proceedings title 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings   Check publisher's open access policy
Journal name ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   Check publisher's open access policy
Place of Publication Piscataway, NJ, United States
Publisher IEEE (Institute for Electrical and Electronic Engineers)
Publication Year 2015
Sub-type Fully published paper
DOI 10.1109/ICASSP.2015.7178100
Open Access Status Not yet assessed
ISBN 9781467369978
ISSN 1520-6149
Volume 2015-August
Start page 902
End page 906
Total pages 5
Collection year 2016
Language eng
Formatted Abstract/Summary
In this paper we investigate multiple instance learning (MIL), using generic tile-based spatio-temporal features, for the classification of benign and malignant lesions in breast cancer magnetic resonance imaging (MRI). In particular, we compare the performance of citation-kNN (CkNN) and conventional kNN against a traditional approach based on bespoke features extracted from a segmented region-of-interest (ROI). Results demonstrate that tile-based CkNN has equivalent performance to ROI-based classification. However, the tile-based approach does not require any domain specific features typically used in breast MRI. This not only has the potential to make tile-based classification robust to inaccuracies in the delineation of suspicious lesions, but also makes it suitable for the detection of suspicious lesions prior to segmentation
Keyword Multiple Instance Learning
Breast MRI
Feature Extraction
Feature Selection
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 25 Aug 2015, 11:30:25 EST by Anthony Yeates on behalf of School of Information Technol and Elec Engineering