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

Pattern recognition system for focal liver lesions using "crisp" and "fuzzy" classifiers

H M Klein1, T Eisele, K C Klose

  • 1Diagnostic Radiology, RWTH Aachen, Germany.

Investigative Radiology
|January 1, 1996
PubMed
Summary

An artificial intelligence system achieved 90.2% accuracy in classifying focal liver lesions, comparable to human observers. This AI tool shows promise for improving liver lesion diagnosis.

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

Mechanical ventilation for young people with Duchenne muscular dystrophy: a factorial survey of the main influences on clinician decision-making.

European journal of pediatrics·2025
Same author

Navigating healthcare decision-making for children requiring life-sustaining medical treatment in Ireland: exploring clinician perspectives through the lens of the Irish legal system.

BMC medical ethics·2025
Same author

Correction: Sediment biomarkers elucidate the Holocene ontogeny of a shallow lake.

PloS one·2018
Same author

Sediment biomarkers elucidate the Holocene ontogeny of a shallow lake.

PloS one·2018
Same author

Research priorities for specialized nursing practice in the United Arab Emirates.

International nursing review·2017
Same author

Tackling the burden of the hepatitis C virus in the UK: characterizing and assessing the clinical and economic consequences.

Public health·2016

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Hepatology

Background:

  • Accurate classification of focal liver lesions is crucial for patient management.
  • Distinguishing between benign and malignant liver lesions can be challenging.

Purpose of the Study:

  • To evaluate the diagnostic performance of an artificial intelligence (AI) system for classifying focal liver lesions.
  • To compare the AI system's accuracy against that of human observers.

Main Methods:

  • Dynamic computed tomography (CT) was used to evaluate 143 focal hepatic lesions.
  • Lesions included hemangiomas, other benign lesions, and malignant liver lesions.
  • An AI classifier was trained and tested, with results compared to human observers using ROC analysis.

Related Experiment Videos

Main Results:

  • The AI system achieved an overall diagnostic accuracy of 90.2% for classifying liver lesions.
  • Factors affecting accuracy included lesion size, contrast enhancement, and morphology.
  • The AI system's performance, measured by the area under the ROC curve, was comparable to human observers.

Conclusions:

  • The AI system demonstrated diagnostic accuracy on par with human experts for focal liver lesion classification.
  • Further improvements in AI performance are anticipated with larger training datasets of CT scans.