Table of Contents Author Guidelines Submit a Manuscript
Computational and Mathematical Methods in Medicine
Volume 2019, Article ID 2717454, 10 pages
https://doi.org/10.1155/2019/2717454
Research Article

Breast Microcalcification Diagnosis Using Deep Convolutional Neural Network from Digital Mammograms

1School of Computer Science and Engineering, South China University of Technology, Guangzhou 510000, China
2Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information, South China University of Technology, Guangzhou, China
3Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, Guangdong 510060, China
4Medical Imaging Center, Shenzhen Hospital of Southern Medical University, Shenzhen, Guangdong 518101, China

Correspondence should be addressed to Hongmin Cai; nc.ude.tucs@iacmh

Received 31 October 2018; Revised 22 December 2018; Accepted 4 February 2019; Published 3 March 2019

Academic Editor: Cristiana Corsi

Copyright © 2019 Hongmin Cai et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Mammography is successfully used as an effective screening tool for cancer diagnosis. A calcification cluster on mammography is a primary sign of cancer. Early researches have proved the diagnostic value of the calcification, yet their performance is highly dependent on handcrafted image descriptors. Characterizing the calcification mammography in an automatic and robust way remains a challenge. In this paper, the calcification was characterized by descriptors obtained from deep learning and handcrafted descriptors. We compared the performances of different image feature sets on digital mammograms. The feature sets included the deep features alone, the handcrafted features, their combination, and the filtered deep features. Experimental results have demonstrated that the deep features outperform handcrafted features, but the handcrafted features can provide complementary information for deep features. We achieved a classification precision of 89.32% and sensitivity of 86.89% using the filtered deep features, which is the best performance among all the feature sets.