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

Hotelling trace criterion and its correlation with human-observer performance.

R D Fiete, H H Barrett, W E Smith

    Journal of the Optical Society of America. A, Optics and Image Science
    |May 1, 1987
    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

    CT metal artifact reduction algorithms: Toward a framework for objective performance assessment.

    Medical physics·2020
    Same author

    Towards continuous-to-continuous 3D imaging in the real world.

    Physics in medicine and biology·2019
    Same author

    Reply to commentary by R Duggleby (2019).

    Progress in biophysics and molecular biology·2018
    Same author

    Elucidation of the bonding of a near infrared dye to hollow gold nanospheres - a chalcogen tripod.

    Chemical science·2018
    Same author

    Assessment of bulbar function in amyotrophic lateral sclerosis: validation of a self-report scale (Center for Neurologic Study Bulbar Function Scale).

    European journal of neurology·2018
    Same author

    Reply to editorial and commentaries on Steele, Al-Mufti, Augustyn, Chandrajith, Coghlan, Coulson et al. (2018) "Cause of Cambrian explosion - Terrestrial or Cosmic?"

    Progress in biophysics and molecular biology·2018
    Same journal

    Phase retrieval with prior information.

    Journal of the Optical Society of America. A, Optics and image science·2008
    Same journal

    Clinical microscopy of the cornea utilizing optical sectioning and a high-numerical-aperture objective.

    Journal of the Optical Society of America. A, Optics and image science·1993
    Same journal

    Eye-tracking laser Doppler velocimeter stabilized in two dimensions: principle, design, and construction.

    Journal of the Optical Society of America. A, Optics and image science·1993
    Same journal

    Effects of aging in retinal image quality.

    Journal of the Optical Society of America. A, Optics and image science·1993
    Same journal

    Axial eye-length measurement by wavelength-shift interferometry.

    Journal of the Optical Society of America. A, Optics and image science·1993
    Same journal

    Fractal analysis of steady-state-flicker visual evoked potentials: feasibility.

    Journal of the Optical Society of America. A, Optics and image science·1993
    See all related articles

    The Hotelling trace criterion (HTC) effectively separates simulated livers with and without tumors. This method highly correlates with human performance, suggesting its use for optimizing imaging systems.

    Area of Science:

    • Medical Imaging Analysis
    • Machine Learning for Diagnostics
    • Biomedical Signal Processing

    Background:

    • The Hotelling trace criterion (HTC) is a statistical method for feature extraction and dimensionality reduction.
    • Accurate detection of tumors in medical imaging is crucial for diagnosis and treatment planning.
    • Simulated data with realistic noise and variability are essential for robust algorithm development.

    Purpose of the Study:

    • To evaluate the effectiveness of the Hotelling trace criterion (HTC) in classifying simulated livers with and without tumors.
    • To assess the correlation between HTC performance and human observer performance in tumor detection.
    • To determine if HTC can serve as a reliable figure of merit for optimizing imaging system parameters.

    Main Methods:

    Related Experiment Videos

  • Generation of simulated liver objects with and without tumors, incorporating noise, blur, and object variability.
  • Application of the Hotelling trace criterion (HTC) to extract linear features for classification.
  • Quantification of classification performance using the receiver-operating-characteristic parameter d-prime (d').
  • Comparison of HTC-based classification accuracy with human observer performance on the same dataset.

    • Main Results:

    • The Hotelling trace criterion (HTC) demonstrated a strong ability to separate simulated livers into tumor-present and tumor-absent classes.
    • A high correlation (0.988) was observed between the HTC's classification performance (d') and human observer performance.
    • The HTC generated a single, scalar figure of merit that accurately reflected the separability of the classes.

    Conclusions:

    • The Hotelling trace criterion (HTC) is a highly effective method for feature selection in classifying medical images, specifically simulated livers.
    • The strong correlation with human performance validates the HTC as a robust measure for evaluating image quality and system optimization.
    • HTC's capability to provide a scalar figure of merit makes it suitable for optimizing imaging system parameters to enhance diagnostic accuracy.