TY - JOUR
T1 - Ensemble discretewavelet transform and gray-level co-occurrence matrix for microcalcification cluster classification in digital mammography
AU - Fanizzi, Annarita
AU - Basile, Teresa Maria
AU - Losurdo, Liliana
AU - Bellotti, Roberto
AU - Bottigli, Ubaldo
AU - Campobasso, Francesco
AU - Didonna, Vittorio
AU - Fausto, Alfonso
AU - Massafra, Raffaella
AU - Tagliafico, Alberto
AU - Tamborra, Pasquale
AU - Tangaro, Sabina
AU - Lorusso, Vito
AU - La Forgia, Daniele
PY - 2019/12/1
Y1 - 2019/12/1
N2 - 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%.
AB - 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%.
KW - Computer-Aided Diagnosis (CADx)
KW - Digital mammograms
KW - Gray-level co-occurrence matrix
KW - Haar wavelet transform
KW - Microcalcification clusters
KW - Random forest
UR - http://www.scopus.com/inward/record.url?scp=85077343143&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077343143&partnerID=8YFLogxK
U2 - 10.3390/app9245388
DO - 10.3390/app9245388
M3 - Article
AN - SCOPUS:85077343143
VL - 9
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
SN - 2076-3417
IS - 24
M1 - 5388
ER -