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 Video

Updated: Jul 8, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Feature selection in the pattern classification problem of digital chest radiograph segmentation.

M F McNitt-Gray1, H K Huang, J W Sayre

  • 1Dept. of Radiol. Sci., California Univ., Los Angeles, CA.

IEEE Transactions on Medical Imaging
|January 1, 1995
PubMed
Summary

Stepwise discriminant analysis effectively selects features for digital chest radiograph segmentation. This method reduces computational resources while maintaining classification performance comparable to using the full feature set.

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

[Effects of Shugan Jieyu capsules combined with Zolpidem on sleep quality and daytime cognitive function in insomnia with depressive symptoms patients].

Zhonghua yi xue za zhi·2025
Same author

Transfemoral Venous Access Facilitates Upper Extremity Dialysis Interventions: Procedural Success and Clinical Outcomes.

Cardiovascular and interventional radiology·2019
Same author

Variability in CT lung-nodule quantification: Effects of dose reduction and reconstruction methods on density and texture based features.

Medical physics·2016
Same author

Medical imaging, PACS, and imaging informatics: retrospective.

Radiological physics and technology·2013
Same author

Comprehensive low-dose imaging of carotid and coronary arteries with a single-injection dual-source CT angiography protocol.

Clinical radiology·2013
Same author

Medical imaging informatics simulators: a tutorial.

International journal of computer assisted radiology and surgery·2013

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Pattern Recognition

Background:

  • Feature selection is critical in pattern classification for optimal performance and efficiency.
  • Digital chest radiograph segmentation involves classifying pixels into anatomic classes using local features.

Purpose of the Study:

  • To evaluate stepwise discriminant analysis as a feature selection technique for digital chest radiograph segmentation.
  • To assess the impact of a reduced feature set on classifier performance compared to the full feature set.

Main Methods:

  • Applied stepwise discriminant analysis to select a subset of features for pixel classification.
  • Evaluated classifier performance using a linear discriminator and a neural network with full, selected, and random feature sets.
  • Incorporated a rule-based spatial information heuristic for postprocessing classification results.

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Related Experiment Videos

Last Updated: Jul 8, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

Main Results:

  • The selected feature set achieved performance comparable to the full feature set.
  • Feature selection significantly reduced computational resource requirements.
  • The reduced feature set maintained classification accuracy after postprocessing.

Conclusions:

  • Stepwise discriminant analysis is an effective feature selection method for digital chest radiograph segmentation.
  • Reduced feature sets offer comparable performance with enhanced computational efficiency.
  • This approach is valuable for optimizing pattern classification tasks in medical imaging.