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

Classification of breast masses using selected shape, edge-sharpness, and texture features with linear and

Tingting Mu1, Asoke K Nandi, Rangaraj M Rangayyan

  • 1Department of Electrical Engineering and Electronics, The University of Liverpool, Brownlow Hill, L69 3GJ, Liverpool, UK.

Journal of Digital Imaging
|February 29, 2008
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

Integrated BSA-Seq and RNA-Seq reveals genes associated with salt tolerance at the germination stage in foxtail millet (Setaria italica (L.) P. Beauv.).

BMC plant biology·2026
Same author

Organic amendments as partial replacements for synthetic fertilizers in foxtail millet.

BMC plant biology·2026
Same author

Artificial neural networks fighting real neural decline: a systematic review of AI in Alzheimer's research.

Artificial intelligence review·2026
Same author

Regulation of photosynthesis by exogenous MeJA under phosphorus deficiency: a review.

Plant cell reports·2026
Same author

MeJA regulates plant root growth, development and phosphorus uptake to adapt to low phosphorus stress.

Plant science : an international journal of experimental plant biology·2026
Same author

Changes in Soil Fungal Communities Following Exogenously Added Tobacco Mosaic Virus Disease.

Current microbiology·2026
Same journal

Bayesian Convolutional Neural Networks in Medical Imaging Classification: A Promising Solution for Deep Learning Limits in Data Scarcity Scenarios.

Journal of digital imaging·2023
Same journal

Detecting and Characterizing Inferior Vena Cava Filters on Abdominal Computed Tomography with Data-Driven Computational Frameworks.

Journal of digital imaging·2023
Same journal

DMCA-GAN: Dual Multilevel Constrained Attention GAN for MRI-Based Hippocampus Segmentation.

Journal of digital imaging·2023
Same journal

Left Ventricular Myocardial Dysfunction Evaluation in Thalassemia Patients Using Echocardiographic Radiomic Features and Machine Learning Algorithms.

Journal of digital imaging·2023
Same journal

Public Imaging Datasets of Gastrointestinal Endoscopy for Artificial Intelligence: a Review.

Journal of digital imaging·2023
Same journal

External Validation of Robust Radiomic Signature to Predict 2-Year Overall Survival in Non-Small-Cell Lung Cancer.

Journal of digital imaging·2023
See all related articles

This study analyzed shape, edge, and texture features from mammograms to differentiate benign and malignant breast masses. Combining these features improved breast cancer classification accuracy, reaching 0.95 area under the curve.

Area of Science:

  • Medical Imaging
  • Biomedical Engineering
  • Radiology

Background:

  • Breast masses exhibit distinct shape, edge-sharpness, and texture characteristics between benign and malignant conditions.
  • Accurate differentiation is crucial for timely breast cancer diagnosis and treatment.

Purpose of the Study:

  • To evaluate the effectiveness of combining shape, edge-sharpness, and texture features for classifying breast masses.
  • To compare the performance of various machine learning classifiers using selected features.

Main Methods:

  • Extracted 22 features (5 shape, 3 edge-sharpness, 14 texture) from 111 mammogram regions (46 malignant, 65 benign).
  • Employed a genetic algorithm for optimal feature selection based on class separability and other criteria.
  • Classified masses using Fisher's linear discriminant analysis, Support Vector Machine (SVM), and a Strict Two-Surface Proximal (S2SP) classifier, including nonlinear kernel versions.

Related Experiment Videos

Main Results:

  • Nonlinear classification using kernel Fisher's discriminant analysis, SVM, and S2SP with a Gaussian kernel achieved an area under the receiver operating characteristics curve of 0.95.
  • Selected combinations of shape, edge-sharpness, and texture features demonstrated significant potential for improving classification accuracy.

Conclusions:

  • The study highlights the value of integrating diverse imaging features for enhanced breast mass classification.
  • Selected feature combinations show promise for developing more accurate computer-aided diagnosis systems for breast cancer.