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

Classifying mammographic lesions using computerized image analysis.

J Kilday1, F Palmieri, M D Fox

  • 1Dept. of Electr. & Syst. Eng., Connecticut Univ., Storrs, CT.

IEEE Transactions on Medical Imaging
|January 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

Robotic ventral mesh rectopexy for obstructed defecation syndrome using the Hugo RAS™ system-A video vignette.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2025
Same author

Early presentation of Covid-19 related paracentral acute middle maculopathy in a healthy young patient.

Journal francais d'ophtalmologie·2024
Same author

Drugs for treating infections caused by non-tubercular mycobacteria: a narrative review from the study group on mycobacteria of the Italian Society of Infectious Diseases and Tropical Medicine.

Infection·2024
Same author

VIDAS<sup>®</sup> TB-IGRA reagents induce a CD4<sup>+</sup> and CD8<sup>+</sup> T-cell IFN-γ response for both TB infection and active TB.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2021
Same author

Therapeutic strategies and outcomes of MDR and pre-XDR-TB in Italy: a nationwide study.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2021
Same author

Outcome of treatment of MDR-TB or drug-resistant patients treated with bedaquiline and delamanid: Results from a large global cohort.

Pulmonology·2021
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026
Same journal

4D Reconstruction of Fetal Left Ventricle from Echocardiography via 2.5D Radial Segmentation and Graph-Fourier Reconstruction.

IEEE transactions on medical imaging·2026
See all related articles

Computerized image analysis of breast lesion shape and patient age can classify tumors. This method achieved up to 82% accuracy in distinguishing fibroadenomas, cysts, and cancers from mammograms.

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Biomedical Engineering

Background:

  • Accurate classification of breast lesions is crucial for timely diagnosis and treatment.
  • Traditional methods rely on subjective interpretation of mammographic images.
  • Developing objective, automated classification tools can improve diagnostic efficiency.

Purpose of the Study:

  • To develop and evaluate a computerized method for classifying common breast lesions (fibroadenomas, cysts, cancers).
  • To assess the efficacy of using tumor shape features and patient age for lesion classification.
  • To compare classification performance with and without patient age as a feature.

Main Methods:

  • Digitization of 69 mammographic images using a PC-based system.

Related Experiment Videos

  • Interactive segmentation of tumor boundaries using a thresholding technique.
  • Extraction of 7 shape-based features (radial length measures, circularity) and inclusion of patient age.
  • Classification using linear discriminant analysis and Euclidean distance metric.
  • Validation through apparent and leave-one-out testing methods.

    • Main Results:

    • Segmentation successfully identified boundaries in 57% of lesions.
    • The best classification accuracy achieved was 82% (apparent test) using shape features and patient age.
    • Leave-one-out testing yielded a maximum accuracy of 69% with a subset of features.
    • Excluding patient age, shape features alone achieved 72% accuracy (apparent test) and 51% (leave-one-out).

    Conclusions:

    • Computerized analysis of breast lesion shape, combined with patient age, offers a promising approach for automated classification.
    • Shape descriptors derived from mammographic images can effectively differentiate between benign and malignant breast lesions.
    • Further refinement of segmentation and feature extraction may enhance classification accuracy.