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

Interventional radiology in the management of complications after pancreatic surgery: a single-center experience.

Abdominal radiology (New York)·2026
Same author

Can AI applied on MRI reliably predict shunt response in INPH? A comprehensive exploration of deep learning and radiomics approaches using preoperative MRI.

PloS one·2026
Same author

Exploratory PET/CT Radiomics for Predicting Early Progression in Locally Advanced Pancreatic Cancer.

Diagnostics (Basel, Switzerland)·2026
Same author

Cone-beam computed tomography-guided navigation-assisted irreversible electroporation for recurrent cervical lymph node metastasis: technical feasibility and early experience.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

Feasibility of Artificial Intelligence Models for Longitudinal CT Analysis of Epicardial Adipose Tissue After Immunotherapy.

Diagnostics (Basel, Switzerland)·2026
Same author

Machine Learning Models for Sepsis: From Early Detection to Short- and Long-Term Prognosis.

International journal of molecular sciences·2026

Related Experiment Video

Updated: Jul 16, 2026

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT
10:28

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT

Published on: January 22, 2018

[18F]FDG PET/CT Radiomics for Predicting Pathological Risk Subtypes of Thymic Epithelial Tumors: A Bicentric Study.

Antonio Sarubbi1, Luca Frasca1, Fatih Aksu2

  • 1Department of Thoracic Surgery, Fondazione Policlinico Universitario Campus Bio-Medico, 00128 Rome, Italy.

Cancers
|July 15, 2026
PubMed
Summary

Machine learning radiomics models using PET/CT imaging showed moderate ability to differentiate low-risk from high-risk thymic epithelial tumors (TETs). Further research is needed to improve non-invasive risk stratification for these rare mediastinal malignancies.

Keywords:
PET/CTmachine learningradiomicsthymic epithelial tumorsthymoma

More Related Videos

Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates
10:04

Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates

Published on: September 5, 2017

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

Related Experiment Videos

Last Updated: Jul 16, 2026

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT
10:28

Gene Regulation and Targeted Therapy in Gastric Cancer Peritoneal Metastasis: Radiological Findings from Dual Energy CT and PET/CT

Published on: January 22, 2018

Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates
10:04

Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates

Published on: September 5, 2017

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

Area of Science:

  • Oncology
  • Radiology
  • Medical Imaging

Background:

  • Thymic epithelial tumors (TETs) are rare mediastinal malignancies with prognosis dependent on histology.
  • Current risk stratification methods using clinical data and imaging are suboptimal.
  • Non-invasive pre-treatment risk assessment is crucial for surgical planning and patient management.

Purpose of the Study:

  • To evaluate a machine learning-based radiomics model for differentiating low-risk and high-risk TETs.
  • To assess the utility of fluorine-18 (18F) fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) radiomic features.
  • To develop a non-invasive tool for risk stratification in TET patients.

Main Methods:

  • A bicentric study included 75 patients with histopathologically diagnosed TETs who underwent PET/CT.
  • Radiomic features (first-order, shape, texture) were extracted from segmented tumors using PyRadiomics.
  • A machine learning model was trained and evaluated using stratified 5-fold cross-validation.

Main Results:

  • The radiomics model achieved a moderate average balanced accuracy of 0.58 ± 0.07 and an average AUC of 0.71 ± 0.04.
  • Average sensitivity was 0.48 and specificity was 0.68.
  • The model demonstrated balanced and stable classification performance with an average Gmean of 0.57.

Conclusions:

  • Machine learning models utilizing PET/CT radiomic features demonstrate moderate discriminatory performance for TET risk stratification.
  • The findings suggest potential for radiomics in non-invasive assessment of TET aggressiveness.
  • Further validation and refinement are necessary to enhance clinical applicability.