Deep-learning-based classification of FDG-PET data for Alzheimer's disease categories

Shibani Singh, Anant Srivastava, Liang Mi, Richard J. Caselli, Kewei Chen, Dhruman Goradia, Eric M. Reiman, Yalin Wang

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

9 Scopus citations

Abstract

Fluorodeoxyglucose (FDG) positron emission tomography (PET) measures the decline in the regional cerebral metabolic rate for glucose, offering a reliable metabolic biomarker even on presymptomatic Alzheimer's disease (AD) patients. PET scans provide functional information that is unique and unavailable using other types of imaging. However, the computational efficacy of FDG-PET data alone, for the classification of various Alzheimers Diagnostic categories, has not been well studied. This motivates us to correctly discriminate various AD Diagnostic categories using FDG-PET data. Deep learning has improved state-of-the-art classification accuracies in the areas of speech, signal, image, video, text mining and recognition. We propose novel methods that involve probabilistic principal component analysis on max-pooled data and mean-pooled data for dimensionality reduction, and multilayer feed forward neural network which performs binary classification. Our experimental dataset consists of baseline data of subjects including 186 cognitively unimpaired (CU) subjects, 336 mild cognitive impairment (MCI) subjects with 158 Late MCI and 178 Early MCI, and 146 AD patients from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. We measured F1-measure, precision, recall, negative and positive predictive values with a 10-fold cross validation scheme. Our results indicate that our designed classifiers achieve competitive results while max pooling achieves better classification performance compared to mean-pooled features. Our deep model based research may advance FDG-PET analysis by demonstrating their potential as an effective imaging biomarker of AD.

Original languageEnglish (US)
Title of host publication13th International Conference on Medical Information Processing and Analysis
EditorsNatasha Lepore, Jorge Brieva, Juan David Garcia, Eduardo Romero
PublisherSPIE
ISBN (Electronic)9781510616332
DOIs
StatePublished - Jan 1 2017
Event13th International Conference on Medical Information Processing and Analysis, SIPAIM 2017 - San Andres Island, Colombia
Duration: Oct 5 2017Oct 7 2017

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10572
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

Other13th International Conference on Medical Information Processing and Analysis, SIPAIM 2017
CountryColombia
CitySan Andres Island
Period10/5/1710/7/17

Keywords

  • Alzheimers
  • Cross Validation
  • Deep Learning
  • Dimensionality Reduction
  • Multilayer Perceptrons
  • Neural Networks
  • PET

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Deep-learning-based classification of FDG-PET data for Alzheimer's disease categories'. Together they form a unique fingerprint.

  • Cite this

    Singh, S., Srivastava, A., Mi, L., Caselli, R. J., Chen, K., Goradia, D., Reiman, E. M., & Wang, Y. (2017). Deep-learning-based classification of FDG-PET data for Alzheimer's disease categories. In N. Lepore, J. Brieva, J. D. Garcia, & E. Romero (Eds.), 13th International Conference on Medical Information Processing and Analysis [105720J] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10572). SPIE. https://doi.org/10.1117/12.2294537