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

Computer-aided diagnoses: automatic detection of lung nodules

M J Carreira1, D Cabello, M G Penedo

  • 1Department of Electronics and Computer Science, University of Santiago de Compostela, Spain. mjose@dec.usc.es

Medical Physics
|November 4, 1998
PubMed
Summary

This study presents a computational method for automatically detecting lung nodules in chest X-rays. The system achieved 100% nodule detection with high accuracy, aiding early diagnosis.

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

X-chromosomal STRs: Metapopulations and mutation rates.

Forensic science international. Genetics·2025
Same author

Randomised-crossover clinical trial on the substantivity of a single application of a gel containing chlorhexidine and o-cymen-5-ol on the oral biofilm and saliva.

BMC oral health·2024
Same author

Pollen production in olive cultivars and its interannual variability.

Annals of botany·2023
Same author

Short-term anti-plaque effect of a cymenol mouthwash analysed using the DenTiUS Deep Plaque software: a randomised clinical trial.

BMC oral health·2023
Same author

Robust segmentation of retinal layers in optical coherence tomography images based on a multistage active contour model.

Heliyon·2019
Same author

[A comparative study of three systems for quantifying the spike and wave index in patients with continuous spikes and waves during slow sleep].

Revista de neurologia·2017

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Radiology

Background:

  • Lung nodules are often detected in chest radiographs.
  • Accurate and automated detection of lung nodules is crucial for early diagnosis and treatment.
  • Current methods may face challenges with false positives and varying nodule characteristics.

Purpose of the Study:

  • To develop and evaluate a computational scheme for automatic detection of suspected lung nodules in chest radiographs.
  • To improve the accuracy and reduce false positives in lung nodule detection.
  • To provide a confidence factor for identifying suspicious regions as nodules.

Main Methods:

  • A knowledge-based system was used to extract lung masks.
  • Normalized cross-correlation and thresholding were applied to detect suspicious regions.

Related Experiment Videos

  • The facet model was employed to reduce false positives.
  • An algorithmic classification process generated a confidence factor for nodule identification.

    • Main Results:

    • The system achieved 100% detection of known lung nodules in the test set.
    • An average of six false positives per image was recorded.
    • The system demonstrated 96% accuracy and specificity in nodule detection.

    Conclusions:

    • The developed computational scheme effectively detects lung nodules in chest radiographs.
    • The system shows high accuracy and specificity, with a manageable false positive rate.
    • This automated approach holds promise for enhancing lung nodule detection in clinical practice.