Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks

Moi Hoon Yap, Gerard Pons, Joan Marti, Sergi Ganau, Melcior Sentís, Reyer Zwiggelaar, Adrian Davison, Robert Martí

Research output: Contribution to journalArticlepeer-review

602 Citations (SciVal)
1010 Downloads (Pure)

Abstract

Breast lesion detection using ultrasound imaging is considered an important step of Computer-Aided Diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing
the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e. Radial Gradient
Index, Multifractal Filtering, Rule-based Region Ranking and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the
lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure.
Original languageEnglish
Pages (from-to)1218-1226
Number of pages9
JournalIEEE Journal of Biomedical and Health Informatics
Volume22
Issue number4
Early online date09 Aug 2017
DOIs
Publication statusPublished - 31 Jul 2018

Keywords

  • Breast cancer
  • convolutional neural networks
  • lesion detection
  • transfer learning
  • ultrasound imaging
  • Breast Neoplasms/diagnostic imaging
  • Neural Networks, Computer
  • Breast/diagnostic imaging
  • Humans
  • Ultrasonography, Mammary/methods
  • Algorithms
  • Female
  • Image Interpretation, Computer-Assisted/methods
  • Databases, Factual

Fingerprint

Dive into the research topics of 'Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this