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

Logarithmic simulated annealing for X-ray diagnosis.

A Albrecht1, K Steinhöfel, M Taupitz

  • 1Department of Computer Science and Engineering, CUHK, N.T, Shatin, Hong Kong.

Artificial Intelligence in Medicine
|May 30, 2001
PubMed
Summary

A novel stochastic learning algorithm accurately classifies liver tumors in CT images using a depth-three threshold circuit. This computational approach achieved approximately 97% correct classification, demonstrating its potential for medical image analysis.

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

An Observational Study of Afatinib 30 mg Daily in Patients With Advanced Non-Small-Cell Lung Cancer Harboring Common EGFR Mutations Treated With Afatinib.

Thoracic cancer·2026
Same author

First Evidence for Mixing-Induced CP Violation in B_{s}^{0}→J/ψϕ(1020) Decays in pp Collisions at sqrt[s]=13  TeV.

Physical review letters·2026
Same author

Measurement of D^{0} Meson Photoproduction in Ultraperipheral Heavy Ion Collisions.

Physical review letters·2026
Same author

Observation of Coherent ϕ(1020) Meson Photoproduction in Ultraperipheral PbPb Collisions at sqrt[s_{NN}]=5.36  TeV.

Physical review letters·2026
Same author

From scientific promise to clinical reality: Nanomedicine for breast cancer.

The Malaysian journal of pathology·2025
Same author

Search for New Physics in Jet Multiplicity Patterns of Multilepton Events at sqrt[s]=13  TeV.

Physical review letters·2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Biology

Background:

  • Accurate detection of focal liver tumors in Computed Tomography (CT) images is crucial for effective patient management.
  • Existing image analysis methods may face challenges in accurately segmenting and classifying complex structures within medical scans.
  • Developing advanced computational algorithms can enhance the diagnostic capabilities of medical imaging.

Purpose of the Study:

  • To introduce a new stochastic learning algorithm for analyzing liver CT images.
  • To evaluate the performance of a depth-three threshold circuit in classifying liver tumors.
  • To assess the algorithm's accuracy using computational experiments.

Main Methods:

  • A novel stochastic learning algorithm was developed, extending the Perceptron algorithm with simulated annealing.

Related Experiment Videos

  • A depth-three threshold circuit was computed, with the first layer using the enhanced Perceptron.
  • The algorithm processed 119x119 pixel fragments from CT images (DICOM standard) with 8-bit grayscale levels.

    • Main Results:

    • The algorithm successfully computed hypotheses for classification, with 348 positive (focal liver tumors) and 348 negative examples.
    • Threshold functions for the second and third circuit layers were determined experimentally.
    • A depth-three circuit achieved approximately 97% correct classification on independent test sets (50+50 examples).

    Conclusions:

    • The developed stochastic learning algorithm demonstrates high accuracy in classifying focal liver tumors from CT images.
    • The depth-three threshold circuit offers a promising approach for automated medical image analysis.
    • This computational method holds potential for improving diagnostic accuracy in radiology.