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

CT-based Deep Learning Model for Automatic Segmentation and Early Predicting of Pyogenic Liver Abscess Caused by

Zibo Gong1, Hairui Wang1, Yawen Guo1

  • 1Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China (Z.G., H.W., Y.G., Y.W., C.W., Z.C.).

Academic Radiology
|July 10, 2026
PubMed

Related Concept Videos

Brain Abscess l: Introduction01:26

Brain Abscess l: Introduction

A brain abscess is a focal, intracerebral infection characterized by a localized collection of pus within the brain parenchyma, resulting from microbial invasion and the body’s inflammatory response. It progresses through stages: early and late cerebritis, followed by early and late capsule formation, reflecting tissue destruction, immune response, and eventual encapsulation.Etiology and PathogenesisCausative organisms vary with source and host factors, often involving polymicrobial infections,...

You might also read

Related Articles

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

Sort by
Same author

CIED-Related Tricuspid Regurgitation Managed With Lead Extraction, Leadless Pacing, and Annuloplasty.

JACC. Case reports·2026
Same author

Predictors for Improvement of Mitral Regurgitation in Patients With Pure Severe Aortic Regurgitation Undergoing Transcatheter Aortic Valve Replacement: Can We Kill Two Birds With One Stone?

Reviews in cardiovascular medicine·2026
Same author

To dig oneself into a hole or to dig the tunnel to the core? A study on the Swartz sheath support strategy for patent foramen ovale closure in migraine patients.

Journal of translational internal medicine·2026
Same author

Corrigendum to "First-in-human study of the K-Clip™ transcatheter annular repair system for severe functional tricuspid regurgitation" [International Journal of Cardiology 390(2023) / IJCA 131174].

International journal of cardiology·2026
Same author

Early Feasibility of Registration of Micro-PET/CT Scans to Annotated 3D Specimen Models.

Head & neck·2026
Same author

Two-year outcomes of transcatheter aortic valve replacement with the vitaflow libertyTM system in high-surgical-risk patients with severe aortic stenosis.

Journal of cardiothoracic surgery·2026
Summary

Deep learning models predict extended-spectrum β-lactamase-producing Enterobacteriaceae (ESBL) pyogenic liver abscesses (PLA) using CT imaging. This aids early diagnosis and risk stratification for difficult-to-treat infections.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Infectious Diseases

Background:

  • Pyogenic liver abscess (PLA) caused by extended-spectrum β-lactamase-producing Enterobacteriaceae (ESBL-PLA) poses significant treatment challenges.
  • Delayed pathogen identification in ESBL-PLA complicates antimicrobial therapy.

Purpose of the Study:

  • To develop and validate deep learning models for early prediction of ESBL-PLA.
  • To integrate clinical and CT imaging features for pre-microbiological confirmation diagnosis.
  • To enable early risk stratification for multidrug-resistant pathogen infections.

Main Methods:

  • Retrospective multicenter study with 442 patients across 6 centers.
  • Development of an automated PLA segmentation model using nnUNetv2.
Keywords:
Computed tomographyDeep learningExtended-spectrum β-lactamase-producing EnterobacteriaceaePyogenic liver abscessRadiomics

Related Experiment Videos

  • Construction of combined clinical-imaging models (CIM) integrating clinical, radiomics, and deep learning imaging features.
  • Performance evaluation using Area Under the Receiver Operating Characteristic Curve (AUC).

    • Main Results:

    • The clinical-imaging model (CIM) demonstrated strong predictive performance for ESBL-PLA.
    • AUCs for CIM were 0.945 (training), 0.889 (internal test), and 0.844 (external test).
    • High-risk groups identified by CIM showed a significantly higher incidence of ESBL-PLA (74.58%) compared to low-risk groups (6.00%).

    Conclusions:

    • Deep learning-based radiomics facilitates early, imaging-based prediction of ESBL-PLA.
    • This approach supports risk stratification for infections caused by multidrug-resistant pathogens.
    • The developed models show promise for improving clinical management of ESBL-PLA.