Deep learning techniques on texture analysis of chest and breast images

Jie Zhi Cheng, Chung Ming Chen, Dinggang Shen

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

The deep learning techniques can automatically learn texture and image context features from training data without the need of explicit feature engineering. With proper and sufficient training data, useful features can be learned to support various medical image analysis applications. In this chapter, we discuss recent deep learning studies on the analysis of chest and breast images. The specific elaborated computerized techniques are computer-aided detection, computer-aided diagnosis, and automatic semantic mapping. We show that the feature learned with the deep learning techniques can be helpful to boost the performances of these computerized applications for the analysis of medical images.

Original languageEnglish
Title of host publicationBiomedical Texture Analysis
Subtitle of host publicationFundamentals, Tools and Challenges
PublisherElsevier
Pages247-279
Number of pages33
ISBN (Electronic)9780128121337
ISBN (Print)9780128123218
DOIs
Publication statusPublished - 2017 Jan 1
Externally publishedYes

Keywords

  • Breast imaging
  • Computer-aided detection
  • Computer-aided diagnosis
  • Deep learning
  • Lung imaging
  • Semantic mapping

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Deep learning techniques on texture analysis of chest and breast images'. Together they form a unique fingerprint.

Cite this