Premium
Computer‐aided diagnosis for dynamic contrast‐enhanced breast MRI of mass‐like lesions using a multiparametric model combining a selection of morphological, kinetic, and spatiotemporal features
Author(s) -
Agliozzo S.,
De Luca M.,
Bracco C.,
Vignati A.,
Giannini V.,
Martincich L.,
Carbonaro L. A.,
Bert A.,
Sardanelli F.,
Regge D.
Publication year - 2012
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.3691178
Subject(s) - pattern recognition (psychology) , breast mri , receiver operating characteristic , computer aided diagnosis , artificial intelligence , magnetic resonance imaging , support vector machine , normalization (sociology) , feature (linguistics) , dynamic contrast enhanced mri , computer science , feature selection , breast cancer , nuclear medicine , mammography , radiology , medicine , cancer , linguistics , philosophy , machine learning , sociology , anthropology
Purpose : Dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) is a radiological tool for the detection and discrimination of breast lesions. The aim of this study is to evaluate a computer‐aided diagnosis (CAD) system for discriminating malignant from benign breast lesions at DCE‐MRI by the combined use of morphological, kinetic, and spatiotemporal lesion features.Methods : Fifty‐four malignant and 19 benign breast lesions in 51 patients were retrospectively evaluated. Images were acquired at two centers at 1.5 T. Mass‐like lesions were automatically segmented after image normalization and elastic coregistration of contrast‐enhanced frames. For each lesion, a set of 28 3D features were extracted: ten morphological (related to shape, margins, and internal enhancement distribution); nine kinetic (computed from signal‐to‐time curves); and nine spatiotemporal (related to the variation of the signal between adjacent frames). A support vector machine (SVM) was trained with feature subsets selected by a genetic search. Best subsets were composed of the most frequent features selected by majority rule. The performance was measured by receiver operator characteristics analysis with a stratified tenfold cross‐validation and bootstrap method for confidence intervals.Results : SVM training by the three separated classes of features resulted in an area under the curve (AUC) of 0.90 ± 0.04 (mean ± standard deviation), 0.87 ± 0.06, and 0.86 ± 0.06 for morphological, kinetic, and spatiotemporal feature, respectively. Combined training with all 28 features resulted in AUC of 0.96 ± 0.02 obtained with a selected feature subset composed by two morphological, one kinetic, and two spatiotemporal features.Conclusions : Quantitative combination of morphological, kinetic, and spatiotemporal features is feasible and provides a higher discriminating power than using the three different classes of features separately.