Interpretable exemplar-based shape classification using constrained sparse linear models

Gunnar A. Sigurdsson, Zhen Yang, Trac D. Tran, Jerry L. Prince

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

Abstract

Many types of diseases manifest themselves as observable changes in the shape of the affected organs. Using shape classification, we can look for signs of disease and discover relationships between diseases. We formulate the problem of shape classification in a holistic framework that utilizes a lossless scalar field representation and a non-parametric classification based on sparse recovery. This framework generalizes over certain classes of unseen shapes while using the full information of the shape, bypassing feature extraction. The output of the method is the class whose combination of exemplars most closely approximates the shape, and furthermore, the algorithm returns the most similar exemplars along with their similarity to the shape, which makes the result simple to interpret. Our results show that the method offers accurate classification between three cerebellar diseases and controls in a database of cerebellar ataxia patients. For reproducible comparison, promising results are presented on publicly available 2D datasets, including the ETH-80 dataset where the method achieves 88.4% classification accuracy.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2015
Subtitle of host publicationImage Processing
EditorsMartin A. Styner, Sebastien Ourselin
PublisherSPIE
ISBN (Electronic)9781628415032
DOIs
StatePublished - Jan 1 2015
EventMedical Imaging 2015: Image Processing - Orlando, United States
Duration: Feb 24 2015Feb 26 2015

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9413
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2015: Image Processing
CountryUnited States
CityOrlando
Period2/24/152/26/15

    Fingerprint

Keywords

  • interpretable classifiers
  • morphology
  • shape classification
  • signed distance functions
  • sparse recovery

ASJC Scopus subject areas

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

Cite this

Sigurdsson, G. A., Yang, Z., Tran, T. D., & Prince, J. L. (2015). Interpretable exemplar-based shape classification using constrained sparse linear models. In M. A. Styner, & S. Ourselin (Eds.), Medical Imaging 2015: Image Processing [94130R] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9413). SPIE. https://doi.org/10.1117/12.2082141