Open AccessAutomatic Detection of Breast Calcification in Ultrasound Imaging with Convolutional Neural Network
Author(s) -
P. D. Karunia,
Prawito Prajitno,
Djarwani Soeharso Soejoko
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2019/1/012077
Subject(s) - breast cancer , ultrasound , mammography , calcification , medicine , breast ultrasound , convolutional neural network , radiology , speckle noise , cancer , artificial intelligence , computer science , speckle pattern
Breast cancer is a common type of cancer that leading death causes of female in the worldwide. Breast calcification can be one of indicator that can be used to detect the breast cancer early. One of the preferred methods used by radiologist to detect breast cancer is ultrasound imaging. Ultrasound imaging is much safer than mammography that followed by radiological effect. However, ultrasound imaging contaminated with speckle noise that looks similar to breast calcification. It can be the cause of the long time diagnosis process. It encourages so many methods of computed aided diagnosis (CADx) that can detect abnormalities automatically. One of them is Convolutional Neural Network (CNN). CNN can be used to classify the normal breast and breast with abnormalities. In this paper, CNN has been proposed for the classification of the ultrasound images into normal breasts and breasts with calcification. Experimental results classification accuracy was 76 % and a sensitivity of 84.61%.