Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A neural network classifier for cerebral perfusion imaging

K H Chan1, K A Johnson, J A Becker

  • 1Department of Radiology, Brigham and Women's Hospital, Boston, MA 02115.

Journal of Nuclear Medicine : Official Publication, Society of Nuclear Medicine
|May 1, 1994
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Challenges and strategies for globally resilient shrimp aquaculture.

NPJ science of food·2026
Same author

Parasite detection in the ornamental fish trade using environmental DNA.

Scientific reports·2019
Same author

Correction to: Monogenean parasites infect ornamental fish imported to Australia.

Parasitology research·2018
Same author

Monogenean parasites infect ornamental fish imported to Australia.

Parasitology research·2018
Same author

Susceptibility of a number of Australian freshwater fishes to dwarf gourami iridovirus (Infectious spleen and kidney necrosis virus).

Journal of fish diseases·2016
Same author

Development of perampanel in epilepsy.

Acta neurologica Scandinavica. Supplementum·2013
Same journal

Overall Survival with [<sup>177</sup>Lu]Lu-PSMA-617 Versus [<sup>177</sup>Lu]Lu-PSMA I&T: A Propensity Score-Matched Real-World Analysis.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same journal

Toward a Biopsy-Free Diagnosis of Prostate Cancer: Potential of Combined <sup>18</sup>F-Flotufolastat PSMA PET and mpMRI.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same journal

PSMA PET/CT-Targeted Biopsy in Men with Negative or Equivocal Multiparametric MRI and Exploratory Dynamic Total-Body PET: The FUPERMAN Study.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same journal

Erratum.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same journal

Live from 2026 SNMMI Annual Meeting in Los Angeles!

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same journal

CAR T-Cell Therapy for Cancer: Updates and Challenges for Response Assessment.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
See all related articles

Artificial neural networks effectively distinguish Alzheimer's disease and cocaine abuse from normal brain perfusion patterns. This AI tool shows high accuracy in classifying abnormal cerebral perfusion, aiding in medical diagnosis.

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Neuroscience

Background:

  • Artificial neural networks (ANNs) are powerful tools for pattern recognition in medical imaging.
  • Discriminating normal from abnormal cerebral perfusion patterns is crucial for diagnosing neurological conditions.

Purpose of the Study:

  • To investigate the effectiveness of ANNs in classifying cerebral perfusion patterns.
  • To differentiate between normal controls, Alzheimer's disease (AD) patients, and chronic cocaine polydrug abuse patients.

Main Methods:

  • Cerebral perfusion imaging using 99mTc-HMPAO in 52 controls, 29 AD patients, and 25 cocaine abusers.
  • ANN classifier trained on 120 standardized cortical regions for pattern discrimination.
  • Receiver operating characteristic (ROC) analysis with cross-validation to evaluate performance.

Related Experiment Videos

Main Results:

  • The ANN achieved an area under the ROC curve of 0.93 +/- 0.04 for AD discrimination.
  • The ANN achieved an area under the ROC curve of 0.89 +/- 0.04 for cocaine abuse discrimination.

Conclusions:

  • Neural networks demonstrate significant potential as a decision-making tool in clinical settings.
  • ANNs can accurately discriminate between normal individuals and patients with AD or cocaine abuse based on cerebral perfusion.
  • This technology offers a promising approach for improving diagnostic accuracy in neurological disorders.