Share Email Print
cover

Proceedings Paper

Toward content-based image retrieval with deep convolutional neural networks
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Content-based image retrieval (CBIR) offers the potential to identify similar case histories, understand rare disorders, and eventually, improve patient care. Recent advances in database capacity, algorithm efficiency, and deep Convolutional Neural Networks (dCNN), a machine learning technique, have enabled great CBIR success for general photographic images. Here, we investigate applying the leading ImageNet CBIR technique to clinically acquired medical images captured by the Vanderbilt Medical Center. Briefly, we (1) constructed a dCNN with four hidden layers, reducing dimensionality of an input scaled to 128x128 to an output encoded layer of 4x384, (2) trained the network using back-propagation 1 million random magnetic resonance (MR) and computed tomography (CT) images, (3) labeled an independent set of 2100 images, and (4) evaluated classifiers on the projection of the labeled images into manifold space. Quantitative results were disappointing (averaging a true positive rate of only 20%); however, the data suggest that improvements would be possible with more evenly distributed sampling across labels and potential re-grouping of label structures. This preliminary effort at automated classification of medical images with ImageNet is promising, but shows that more work is needed beyond direct adaptation of existing techniques.

Paper Details

Date Published: 19 March 2015
PDF: 6 pages
Proc. SPIE 9417, Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging, 94172C (19 March 2015); doi: 10.1117/12.2081551
Show Author Affiliations
Judah E. S. Sklan, Vanderbilt Univ. (United States)
Andrew J. Plassard, Vanderbilt Univ. (United States)
Daniel Fabbri, Vanderbilt Univ. (United States)
Bennett A. Landman, Vanderbilt Univ. (United States)


Published in SPIE Proceedings Vol. 9417:
Medical Imaging 2015: Biomedical Applications in Molecular, Structural, and Functional Imaging
Barjor Gimi; Robert C. Molthen, Editor(s)

© SPIE. Terms of Use
Back to Top