Next Article in Journal
Carotenoids Overproduction in Dunaliella Sp.: Transcriptional Changes and New Insights through Lycopene β Cyclase Regulation
Next Article in Special Issue
Automatic Segmentation of Coronary Arteries in X-ray Angiograms using Multiscale Analysis and Artificial Neural Networks
Previous Article in Journal
Using Acoustic Emission Measurements for Ice-Melting Detection
Previous Article in Special Issue
Gradient-Guided Convolutional Neural Network for MRI Image Super-Resolution
Open AccessArticle

Ensemble Discrete Wavelet Transform and Gray-Level Co-Occurrence Matrix for Microcalcification Cluster Classification in Digital Mammography

1
I.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, 70124 Bari, Italy
2
Dip. Interateneo di Fisica “M. Merlin”, Università degli Studi di Bari, 70125 Bari, Italy
3
INFN—Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70126 Bari, Italy
4
Dip. di Scienze Fisiche, della Terra e dell’Ambiente, Università degli Studi di Siena, 53100 Siena, Italy
5
Dip. di Economia e finanza, Università degli Studi di Bari, 70124 Bari, Italy
6
Dip. di Diagnostica per Immagini, Azienda Ospedaliera Universitaria Senese, 53100 Siena, Italy
7
Dip. di Scienze della Salute, Università degli Studi di Genova, 16132 Genova, Italy
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Appl. Sci. 2019, 9(24), 5388; https://doi.org/10.3390/app9245388
Received: 23 October 2019 / Revised: 28 November 2019 / Accepted: 4 December 2019 / Published: 9 December 2019
(This article belongs to the Special Issue Signal Processing and Machine Learning for Biomedical Data)
The presence of clusters of microcalcifications is a primary sign of breast cancer. Their identification is still difficult today for radiologists, and the wrong evaluations involve unnecessary biopsies. In this paper, an automatic tool for characterizing and discriminating clusters of microcalcifications into benign/malignant in digital mammograms is proposed. A set of 104 digital mammograms including microcalcification clusters was randomly extracted from a public available database and manually labeled by our radiologists, obtaining 96 abnormal ROIs. For each so-identified ROI, a multi-scale image decomposition based on the Haar wavelet transform was performed. On the decomposition, a textural features extraction step was carried out both on each sub-image and on the corresponding gray-level co-occurrence matrix. Then, a random forest classifier was employed for classifying microcalcification clusters into benign and malignant. The study found that the most discriminant features extracted from the ROIs decomposition by Haar transform were variance and relative smoothness, whereas as regards the textural features calculated on the GLCMs corresponding to the Haar-decomposed ROI, it emerged that the relationship between the pixels of the sub-image in the diagonal direction had high discriminating power for the classification of microcalcification clusters into benign and malignant. The proposed method was evaluated in cross-validation and performed highly in the prediction of the benign/malignant ROIs, with a mean AUC value of 97.39 ± 0.01 % . View Full-Text
Keywords: Computer-Aided Diagnosis (CADx); microcalcification clusters; digital mammograms; Haar wavelet transform; gray-level co-occurrence matrix; random forest Computer-Aided Diagnosis (CADx); microcalcification clusters; digital mammograms; Haar wavelet transform; gray-level co-occurrence matrix; random forest
Show Figures

Figure 1

MDPI and ACS Style

Fanizzi, A.; Basile, T.M.; Losurdo, L.; Bellotti, R.; Bottigli, U.; Campobasso, F.; Didonna, V.; Fausto, A.; Massafra, R.; Tagliafico, A.; Tamborra, P.; Tangaro, S.; Lorusso, V.; La Forgia, D. Ensemble Discrete Wavelet Transform and Gray-Level Co-Occurrence Matrix for Microcalcification Cluster Classification in Digital Mammography. Appl. Sci. 2019, 9, 5388.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop