Enhanced generative model for unsupervised discovery of spatially-informed macroscopic emphysema: The mesa COPD study

Yu Gan, Jie Yang, Benjamin Smith, Pallavi Balte, Eric Hoffman, Christine Hendon, R. Graham Barr, Andrew F. Laine, Elsa D. Angelini

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Pulmonary emphysema, overlapping with Chronic Obstructive Pulmonary Disorder (COPD), contributes to a significant amount of morbidity and mortality annually. Computed tomography is used for in vivo quantification of emphysema and labeling into three standard subtypes at a macroscopic level. Unsupervised learning of texture patterns has great potential to discover more radiological emphysema subtypes. In this work, we improve a probabilistic Latent Dirichlet Allocation (LDA) model to discover spatially-informed lung macroscopic patterns (sLMPs) from previously learned spatially-informed lung texture patterns (sLTPs). We exploit a specific reproducibility metric to empirically tune the number of sLMPs and the size of patches. Experimental results on the MESA COPD cohort show that our algorithm can discover highly reproducible sLMPs, which are able to capture relationships between sLTPs and preferred localizations within the lung. The discovered sLMPs also achieve higher prediction accuracy of three standard emphysema subtypes than in our previous implementation.

Original languageEnglish
Title of host publicationISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
Pages1212-1215
Number of pages4
ISBN (Electronic)9781538636411
DOIs
StatePublished - Apr 2019
Event16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy
Duration: 8 Apr 201911 Apr 2019

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2019-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
Country/TerritoryItaly
CityVenice
Period8/04/1911/04/19

Keywords

  • COPD
  • Classification
  • Ct
  • Emphysema
  • Latent dirichlet allocation
  • Lung
  • Texture
  • Unsupervised learning

Fingerprint

Dive into the research topics of 'Enhanced generative model for unsupervised discovery of spatially-informed macroscopic emphysema: The mesa COPD study'. Together they form a unique fingerprint.

Cite this