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

Correspondence in texture features between two mammographic views.

Shalini Gupta1, Mia K Markey

  • 1Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas 78712-0240, USA.

Medical Physics
|July 15, 2005
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

Correction: Rapid pan-cancer detection <i>via</i> label-free impedance profiling of cell-free DNA.

Lab on a chip·2026
Same author

Garment-related patient-reported outcomes: a longitudinal pre-post comparison of autologous versus implant-based breast reconstruction.

European journal of oncology nursing : the official journal of European Oncology Nursing Society·2026
Same author

Premenstrual syndrome and its relation to socio demographic variables among middle -aged women in India.

Bioinformation·2026
Same author

Panoramic Insights: Predicting Age and Gender from Dental X-Rays Using Deep Learning Models.

Journal of imaging informatics in medicine·2026
Same author

Role of Dexmedetomidine on Hemodynamics and Anesthetic Requirement in Patients Undergoing Elective Infratentorial Tumor Surgery: A Prospective, Randomized, Double-blind, Placebo-controlled Study.

Annals of African medicine·2026
Same author

Ovarian Rev-erbα: a central regulator of fertility following chronodisruption.

Frontiers in endocrinology·2026
Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026
Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026
Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026
Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
See all related articles

Radiologists improve mammogram interpretation with two views. This study found texture features from mediolateral oblique (MLO) and craniocaudal (CC) views are less correlated for calcifications and benign lesions, impacting computer-aided diagnosis (CADx) accuracy.

Area of Science:

  • Medical Imaging
  • Radiology
  • Computer-Aided Diagnosis

Background:

  • Radiologists interpret mammograms more effectively with two standard views: mediolateral oblique (MLO) and craniocaudal (CC).
  • Computer-aided diagnosis (CADx) algorithms are used to assist in breast lesion detection and diagnosis from mammograms.
  • Combining evidence from multiple mammographic views may enhance CADx system performance.

Purpose of the Study:

  • To investigate the correlation of Haralick's texture features between MLO and CC mammographic views of breast lesions.
  • To determine if texture feature information is complementary between the two views.
  • To assess how lesion type (mass vs. calcification) and malignancy (benign vs. malignant) affect feature correlation.

Main Methods:

  • Calculated correlation coefficients for Haralick's texture features between MLO and CC views.

Related Experiment Videos

  • Ranked features based on correlation values.
  • Compared two-view feature correlations for subgroups: masses vs. calcifications and benign vs. malignant lesions.
  • Utilized a subset of mammography cases from the Digital Database for Screening Mammography (DDSM).

    • Main Results:

    • Texture features showed lower correlation between MLO and CC views for calcification lesions compared to mass lesions.
    • Texture features exhibited lower correlation between the two views for benign lesions compared to malignant lesions.
    • These differences in correlation were statistically significant.

    Conclusions:

    • The degree of correlation between MLO and CC view texture features varies significantly based on lesion type and malignancy.
    • Integrating texture features from multiple mammographic views into CADx algorithms may differentially impact diagnostic accuracy for calcifications and benign lesions.
    • Further research is needed to optimize CADx algorithms considering view-specific feature correlations.