Share Email Print
cover

Proceedings Paper

Marginal shape deep learning: applications to pediatric lung field segmentation
Author(s): Awais Mansoor; Juan J. Cerrolaza; Geovany Perez; Elijah Biggs; Gustavo Nino; Marius George Linguraru
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Representation learning through deep learning (DL) architecture has shown tremendous potential for identification, local- ization, and texture classification in various medical imaging modalities. However, DL applications to segmentation of objects especially to deformable objects are rather limited and mostly restricted to pixel classification. In this work, we propose marginal shape deep learning (MaShDL), a framework that extends the application of DL to deformable shape segmentation by using deep classifiers to estimate the shape parameters. MaShDL combines the strength of statistical shape models with the automated feature learning architecture of DL. Unlike the iterative shape parameters estimation approach of classical shape models that often leads to a local minima, the proposed framework is robust to local minima optimization and illumination changes. Furthermore, since the direct application of DL framework to a multi-parameter estimation problem results in a very high complexity, our framework provides an excellent run-time performance solution by independently learning shape parameter classifiers in marginal eigenspaces in the decreasing order of variation. We evaluated MaShDL for segmenting the lung field from 314 normal and abnormal pediatric chest radiographs and obtained a mean Dice similarity coefficient of 0:927 using only the four highest modes of variation (compared to 0:888 with classical ASM1 (p-value=0:01) using same configuration). To the best of our knowledge this is the first demonstration of using DL framework for parametrized shape learning for the delineation of deformable objects.

Paper Details

Date Published: 24 February 2017
PDF: 6 pages
Proc. SPIE 10133, Medical Imaging 2017: Image Processing, 1013304 (24 February 2017); doi: 10.1117/12.2254412
Show Author Affiliations
Awais Mansoor, Children's National Health System (United States)
Juan J. Cerrolaza, Children's National Health System (United States)
Geovany Perez, Children's National Health System (United States)
Elijah Biggs, Children's National Health System (United States)
Gustavo Nino, Children's National Health System (United States)
Marius George Linguraru, Children's National Health System (United States)
George Washington Univ. (United States)


Published in SPIE Proceedings Vol. 10133:
Medical Imaging 2017: Image Processing
Martin A. Styner; Elsa D. Angelini, Editor(s)

© SPIE. Terms of Use
Back to Top