Breast MRI lesion classification: improved performance of human readers with a backpropagation neural network computer-aided diagnosis (CAD) system

Lina Arbash Meinel; Alan H Stolpen; Kevin S Berbaum; Laurie L Fajardo; Joseph M Reinhardt

doi:10.1002/jmri.20794

Back

Journal article

Peer reviewed

Breast MRI lesion classification: improved performance of human readers with a backpropagation neural network computer-aided diagnosis (CAD) system

Lina Arbash Meinel, Alan H Stolpen, Kevin S Berbaum, Laurie L Fajardo and Joseph M Reinhardt

Journal of magnetic resonance imaging, Vol.25(1), pp.89-95

01/2007

DOI: 10.1002/jmri.20794

PMID: 17154399

View Online

Abstract

To develop and test a computer-aided diagnosis (CAD) system to improve the performance of radiologists in classifying lesions on breast MRI (BMRI). A CAD system was developed that uses a semiautomated segmentation method. After segmentation, 42 features based on lesion shape, texture, and enhancement kinetics were computed, and the 13 best features were selected and used as inputs to a backpropagation neural network (BNN). The BNN was trained and tested using the leave-one-out method on 80 BMRI lesions (37 benign, 43 malignant). Lesion histopathology was used as the reference standard. Five human readers classified the 80 lesions first without and then with CAD assistance. The performance of the computer classifier and the human readers was assessed using receiver operating characteristic curves; the performance of the human readers was also evaluated using multireader multicase (MRMC) analysis. The performance of the human readers significantly improved when aided by the CAD system (P < 0.05). MRMC analysis showed that human reader performance with and without CAD system assistance can be generalized to the population of cases (P < 0.001). A CAD system based on lesion morphology and enhancement kinetics can improve the performance of human readers in classifying lesions on breast MRI.

Clinical Competence

Diagnosis, Differential

Diagnosis, Computer-Assisted

Humans

Magnetic Resonance Imaging - methods

Meglumine - analogs & derivatives

Organometallic Compounds

Contrast Media

Female

ROC Curve

Breast Neoplasms - diagnosis

Software

Observer Variation

Neural Networks (Computer)

Details

Title: Subtitle: Breast MRI lesion classification: improved performance of human readers with a backpropagation neural network computer-aided diagnosis (CAD) system
Creators: Lina Arbash Meinel - Department of Biomedical Engineering, The University of Iowa, Iowa City, Iowa 52242, USA
Alan H Stolpen
Kevin S Berbaum
Laurie L Fajardo
Joseph M Reinhardt
Resource Type: Journal article
Publication Details: Journal of magnetic resonance imaging, Vol.25(1), pp.89-95
DOI: 10.1002/jmri.20794
PMID: 17154399
NLM abbreviation: J Magn Reson Imaging
ISSN: 1053-1807
eISSN: 1522-2586
Publisher: United States
Language: English
Date published: 01/2007
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Internal Medicine
Record Identifier: 9984051887102771

Metrics

24 Record Views

123 Times Cited - Web of Science