Curvelet analysis of breast masses on dynamic magnetic resonance mammography. Issue 5 (1st May 2018)

• Record Type: Journal Article
• Authors: Nirouei, Mahyar; Pouladian, Majid; Abdolmaleki, Parviz; Akhlaghpoor, Shahram
• Is Part Of: IET image processing. Volume 12:Issue 5(2018)
• Page Start: 745
• Page End: 750
• Publication Date: 2018-05-01
• Subjects: image texture -- image classification -- feature extraction -- feature selection -- biomedical MRI -- mammography -- medical image processing -- neural nets -- genetic algorithms -- curvelet transforms -- statistical analysis -- tumours; curvelet analysis -- breast masses classification -- dynamic magnetic resonance mammography -- texture feature extraction -- dynamic contrast‐enhanced magnetic resonance imaging -- DCE‐MRI -- curvelet transform -- breast tumours -- contrast agent distribution -- mass lesions -- statistical parameters -- curvelet coefficients -- tumour texture -- sub‐band image texture -- inter‐correlated descriptors -- genetic algorithm -- Pearson correlation -- feature selection -- three‐layer artificial neural network -- benign breast lesion classification -- malignant breast lesion classification -- GA‐ANN model -- receiver operating characteristic curve; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2017.0125
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : This study is devoted to extracting significant texture features from dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) of the breast using curvelet features and to classify breast masses into malignant and benign using the calculated features. The authors utilised the first generation of curvelet transform in the interpretation of breast tumours on DCE‐MRI. The analysis is performed after injecting 23 patients with a contrast agent and 23 mass lesions were extracted from these patients. Then, 288 statistical parameters were extracted by calculating the mean and variance of the curvelet coefficients of tumour texture in sub‐band images. Due to a large number of extracted features and the presence of redundant and inter‐correlated descriptors, they used a combination of genetic algorithm (GA) and Pearson's correlation for feature selection and a three‐layer artificial neural network (ANN) for classification of malignant and benign breast lesions. The GA‐ANN model has yielded a good diagnostic accuracy (96%), sensitivity (92%) and specificity (100%). Also, the area under the receiver operating characteristic curve was 0.955. The curvelet transform was able to effectively quantify the distribution of contrast agent in tumour texture, which is different in malignant and benign tumours.