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 detection of small lung nodules on CT utilizing a local density maximum algorithm.

Binsheng Zhao1, Gordon Gamsu, Michelle S Ginsberg

  • 1Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, 1275 York Avenue, New York, New York 10021, USA. zhaob@mskcc.org

Journal of Applied Clinical Medical Physics
|July 5, 2003
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

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

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

AI-MIRACLE: Artificial Intelligence and MultIpaRAmetric MRI Predict CLinical OutcomEs to Neoadjuvant Immunotherapy in Patients with Muscle-invasive Bladder Cancer Undergoing Radical Cystectomy.

European urology oncology·2026
Same author

"Why Is There a Tumor?": Tell Me the Reason, Show Me the Evidence.

Proceedings of machine learning research·2026
Same author

AI-BLADE toolbox: AI-powered BLADdEr multiparametric MRI analysis for clinical application.

BJR artificial intelligence·2026
Same author

Optimizing Colorectal Liver Metastasis Ablation through Metabolic Imaging, Margin Assessment, and Biopsy (The OPTABLATE Prospective Trial).

Radiology·2026
Same author

Trial Design and Objectives for Patients With Prostate Cancer: Recommendations From the Prostate Cancer Working Group 4.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026

This study introduces an automated method for identifying small lung nodules on computed tomography (CT) scans. The computerized approach aims to improve early lung cancer detection by assisting radiologists.

Area of Science:

  • Radiology
  • Medical Imaging
  • Computer-Aided Diagnosis

Background:

  • Computed tomography (CT) advancements enable higher resolution and faster scans, leading to the detection of small lung nodules.
  • Early detection of lung nodules, potentially indicative of cancer, is crucial for curable treatment.
  • Current radiologist review of numerous CT images may lead to missed small nodules.

Purpose of the Study:

  • To present a computerized method for automated identification of small lung nodules on multislice CT (MSCT) images.
  • To enhance the accuracy and efficiency of lung nodule detection in clinical practice.

Main Methods:

  • A three-step automated method was developed: lung separation, nodule candidate detection, and false-positive reduction.
  • Lung segmentation utilized density histogram analysis and morphological operations.

Related Experiment Videos

  • Nodule candidate identification employed a local density maximum algorithm, refined by nodule size and shape information.

    • Main Results:

    • The method achieved an 84.2% sensitivity in detecting computer-simulated small lung nodules (2-7 mm).
    • The system produced an average of five false-positive results per scan.
    • Preliminary results indicate the technique's potential for assisting radiologists.

    Conclusions:

    • The developed computerized method shows promise for automated detection of small lung nodules on chest MSCT images.
    • This technique can aid radiologists in identifying potentially cancerous nodules earlier, improving patient outcomes.