Format

Send to

Choose Destination
Int J Comput Assist Radiol Surg. 2020 Feb;15(2):297-307. doi: 10.1007/s11548-019-02103-z. Epub 2019 Dec 14.

Differentiating benign and malignant mass and non-mass lesions in breast DCE-MRI using normalized frequency-based features.

Author information

1
Electrical Engineering Department, Iran University of Science and Technology (IUST), Tehran, Iran. fazael_ayatollahi@elec.iust.ac.ir.
2
Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands. fazael_ayatollahi@elec.iust.ac.ir.
3
Electrical Engineering Department, Iran University of Science and Technology (IUST), Tehran, Iran.
4
Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands.
5
Department of Radiation Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands.

Abstract

PURPOSE:

In this study, we propose a new computer-aided diagnosis (CADx) to distinguish between malign and benign mass and non-mass lesions in breast DCE-MRI. For this purpose, we introduce new frequency textural features.

METHODS:

In this paper, we propose novel normalized frequency-based features. These are obtained by applying the dual-tree complex wavelet transform to MRI slices containing a lesion for specific decomposition levels. The low-pass and band-pass frequency coefficients of the dual-tree complex wavelet transform represent the general shape and texture features, respectively, of the lesion. The extraction of these features is computationally efficient. We employ a support vector machine to classify the lesions, and investigate modified cost functions and under- and oversampling strategies to handle the class imbalance.

RESULTS:

The proposed method has been tested on a dataset of 80 patients containing 103 lesions. An area under the curve of 0.98 for the mass and 0.94 for the non-mass lesions is obtained. Similarly, accuracies of 96.9% and 89.8%, sensitivities of 93.8% and 84.6% and specificities of 98% and 92.3% are obtained for the mass and non-mass lesions, respectively.

CONCLUSION:

Normalized frequency-based features can characterize benign and malignant lesions efficiently in both mass- and non-mass-like lesions. Additionally, the combination of normalized frequency-based features and three-dimensional shape descriptors improves the CADx performance.

KEYWORDS:

Complex wavelet; Computer-aided diagnosis; Imbalanced data; Magnetic resonance imaging (MRI); Mass and non-mass breast lesions

PMID:
31838643
DOI:
10.1007/s11548-019-02103-z

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center