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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Educational Effects of Training With a Virtual Reality-Based Objective Structured Clinical Examination Software.

Journal of medical education and curricular development·2026
Same author

Contactless Respiratory Waveform Estimation Using a Depth Camera and AI-Based Body Detection.

Sensors (Basel, Switzerland)·2026
Same author

Radiation effects of a CT scan on chromosomal aberrations in cancer and non-cancer patients.

Journal of radiation research·2026
Same author

Appropriate dose reduction using photon-counting detector CT for temporal bone imaging: phantom and clinical studies with helical acquisition.

Japanese journal of radiology·2026
Same author

The effect of age-related decline in physiological activity on the concealed information test.

Frontiers in psychology·2026
Same author

Subphenotype-Specific Risk of Intracranial Hemorrhage During Extracorporeal Membrane Oxygenation in Acute Respiratory Distress Syndrome.

ASAIO journal (American Society for Artificial Internal Organs : 1992)·2026

Related Experiment Video

Updated: Sep 9, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Artificial intelligence software to detect small hepatic lesions on hepatobiliary-phase images using multiscale

Shogo Maeda1, Yuko Nakamura2, Toru Higaki1

  • 1Diagnostic Radiology, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima City, Hiroshima, 734-8551, Japan.

Japanese Journal of Radiology
|August 29, 2025
PubMed
Summary

Multiscale sampling artificial intelligence (msAI) software improved the detection of small hepatic lesions on hepatobiliary-phase (HBP) images. This enhancement was particularly notable when readers accurately assessed the AI

Keywords:
Artificial intelligenceDetectabilityHepatobiliary-phase imagesMultiscale sampling method

More Related Videos

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
06:09

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

1.4K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

227

Related Experiment Videos

Last Updated: Sep 9, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
06:09

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI

Published on: July 21, 2023

1.4K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

227

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Radiology
  • Hepatobiliary Imaging

Background:

  • Gadoxetic acid-enhanced hepatobiliary-phase (HBP) imaging is crucial for detecting hepatic lesions.
  • Accurate interpretation of small hepatic lesions remains a diagnostic challenge.
  • Artificial intelligence (AI) offers potential to improve diagnostic performance in radiology.

Purpose of the Study:

  • To evaluate the impact of multiscale sampling artificial intelligence (msAI) software on the diagnostic performance of readers interpreting HBP images.
  • To assess the effect of msAI on the detection and characterization of small hepatic lesions.
  • To analyze reader performance with and without msAI assistance.

Main Methods:

  • HBP images from 30 patients with 186 hepatic lesions were reviewed.
  • Three radiologists, nine residents, and two general physicians interpreted images twice: with and without msAI software.
  • Jackknife free-response receiver-operating characteristic (ROC) analysis was used to calculate the figure of merit (FOM) and lesion localization fraction (LLF).
  • Negative consultation ratio (NCR) was calculated to assess reader accuracy in evaluating AI findings.

Main Results:

  • msAI software significantly improved the lesion localization fraction (LLF) for all readers (0.74 to 0.82, p<0.01).
  • Overall figure of merit (FOM) did not significantly change (0.76 to 0.78, p=0.45).
  • For lesions smaller than 6 mm, msAI significantly improved LLF (0.40 to 0.53, p<0.01), but FOM remained unchanged (0.63 to 0.66, p=0.51).
  • Readers with a low negative consultation ratio (<10%) showed significant improvements in both LLF and FOM when using msAI.

Conclusions:

  • Multiscale sampling artificial intelligence (msAI) software enhances the detectability of small hepatic lesions on HBP images.
  • The benefit of msAI is most pronounced when readers can accurately interpret and utilize its output.
  • AI tools show promise in improving diagnostic accuracy for challenging liver lesion detection.