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

Automatic lung nodule detection using profile matching and back-propagation neural network techniques

S C Lo1, M T Freedman, J S Lin

  • 1Radiology Department, Georgetown University Medical Center, Washington, DC.

Journal of Digital Imaging
|February 1, 1993
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

[Application and progress of artificial intelligence technology in interventional pulmonology].

Zhonghua jie he he hu xi za zhi = Zhonghua jiehe he huxi zazhi = Chinese journal of tuberculosis and respiratory diseases·2025
Same author

[Spatiotemporal changes of COVID-19 outbreak in Shanghai].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2022
Same author

Estimating Local Cellular Density in Glioma Using MR Imaging Data.

AJNR. American journal of neuroradiology·2020
Same author

Imaging-Based Algorithm for the Local Grading of Glioma.

AJNR. American journal of neuroradiology·2020
Same author

Virtual memory CD8 T cells expanded by helminth infection confer broad protection against bacterial infection.

Mucosal immunology·2018
Same author

[Value of p16/Ki-67 dual-staining immunocytochemistry in cervical cancer screening].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2018

Computer-assisted detection using neural networks improves lung nodule identification accuracy. This digital technique enhances true-positive lung nodule detections while reducing false positives in radiographic analysis.

Area of Science:

  • Radiology
  • Medical Imaging
  • Computer-Aided Diagnosis

Background:

  • Digital radiography offers advantages over film-based methods.
  • Computer-assisted detection (CAD) is a key application in digital radiography.
  • Detecting small lung nodules (3-15 mm) is challenging, with current methods achieving only ~65% accuracy.

Purpose of the Study:

  • To investigate the use of neural networks for computer-assisted detection of lung nodules.
  • To improve the accuracy of true-positive lung nodule detections.
  • To reduce false-positive detections in lung nodule identification.

Main Methods:

  • Utilized image processing techniques like thresholding and morphological analysis for signal enhancement.
  • Developed and trained a neural network program to differentiate true-positive nodule detections.

Related Experiment Videos

  • Implemented a system with three detection modes: thresholding, profile matching analysis, and neural network.

    • Main Results:

    • The trained neural network program demonstrated an increase in true-positive lung nodule detections.
    • The system moderately reduced the number of false-positive detections.
    • The fully automatic program processed all three detection methods in under 35 seconds.

    Conclusions:

    • Neural networks show promise in enhancing the accuracy of computer-assisted lung nodule detection.
    • The developed system offers a faster and potentially more accurate method for identifying lung nodules compared to traditional approaches.
    • Further research and validation are warranted for clinical implementation of this digital technique.