Classification of mammographic masses by deep learning

Xiaoyong Zhang, Takuya Sasaki, Shintaro Suzuki, Yumi Takane, Yusuki Kawasumi, Tadashi Ishibashiz, Noriyasu Homma, Makoto Yoshizawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Classification of benign and malignant masses in mammograms is one of the most difficult tasks in development of mammographic computer-aided diagnosis (CAD) system. This paper presents a deep learning-based method that utilizes a deep convolutional neural network (DCNN) to classify mammographic masses into two classes: benign and malignant masses. In order to train the DCNN for mass classification, a transfer learning strategy which pre-trains the DCNN on a large-scale natural image database and subsequently fine-tunes the DCNN on a relative small-scale mam-mogram database is used in this study. We test our method on the mammogram database and evaluate the classification performance using a receiver operating characteristic (ROC) curve. The experimental results demonstrate that the area under the curve (AUC) of ROC is about 0.8 that is closed to the performance of radiologist.

Original languageEnglish
Title of host publication2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages793-796
Number of pages4
ISBN (Electronic)9784907764579
DOIs
Publication statusPublished - 2017 Nov 10
Event56th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2017 - Kanazawa, Japan
Duration: 2017 Sep 192017 Sep 22

Publication series

Name2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2017
Volume2017-November

Other

Other56th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2017
CountryJapan
CityKanazawa
Period17/9/1917/9/22

Keywords

  • Mammogram
  • computer-aided diagnosis (CAD)
  • deep convolutional neural network (DCNN)
  • deep learning
  • transfer learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Optimization
  • Control and Systems Engineering
  • Instrumentation

Fingerprint Dive into the research topics of 'Classification of mammographic masses by deep learning'. Together they form a unique fingerprint.

Cite this