Breast image feature learning with adaptive deconvolutional networks

Andrew R. Jamieson, Karen Drukker, Maryellen L. Giger

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

31 Scopus citations

Abstract

Feature extraction is a critical component of medical image analysis. Many computer-aided diagnosis approaches employ hand-designed, heuristic lesion extracted features. An alternative approach is to learn features directly from images. In this preliminary study, we explored the use of Adaptive Deconvolutional Networks (ADN) for learning high-level features in diagnostic breast mass lesion images with potential application to computer-aided diagnosis (CADx) and content-based image retrieval (CBIR). ADNs (Zeiler, et. al., 2011), are recently-proposed unsupervised, generative hierarchical models that decompose images via convolution sparse coding and max pooling. We trained the ADNs to learn multiple layers of representation for two breast image data sets on two different modalities (739 full field digital mammography (FFDM) and 2393 ultrasound images). Feature map calculations were accelerated by use of GPUs. Following Zeiler et. al., we applied the Spatial Pyramid Matching (SPM) kernel (Lazebnik, et. al., 2006) on the inferred feature maps and combined this with a linear support vector machine (SVM) classifier for the task of binary classification between cancer and non-cancer breast mass lesions. Non-linear, local structure preserving dimension reduction, Elastic Embedding (Carreira-Perpiñán, 2010), was then used to visualize the SPM kernel output in 2D and qualitatively inspect image relationships learned. Performance was found to be competitive with current CADx schemes that use human-designed features, e.g., achieving a 0.632+ bootstrap AUC (by case) of 0.83 [0.78, 0.89] for an ultrasound image set (1125 cases).

Original languageEnglish (US)
Title of host publicationMedical Imaging 2012
Subtitle of host publicationComputer-Aided Diagnosis
DOIs
StatePublished - Dec 1 2012
EventMedical Imaging 2012: Computer-Aided Diagnosis - San Diego, CA, United States
Duration: Feb 7 2012Feb 9 2012

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume8315
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2012: Computer-Aided Diagnosis
CountryUnited States
CitySan Diego, CA
Period2/7/122/9/12

    Fingerprint

Keywords

  • Breast cancer
  • Computer-aided diagnosis
  • Dimension reduction
  • Image similarity
  • Sparse decomposition
  • Spatial pyramid matching
  • Unsupervised feature learning
  • Visualization

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

Jamieson, A. R., Drukker, K., & Giger, M. L. (2012). Breast image feature learning with adaptive deconvolutional networks. In Medical Imaging 2012: Computer-Aided Diagnosis [831506] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 8315). https://doi.org/10.1117/12.910710