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

Consolidative Thoracic Radiotherapy With Atezolizumab Maintenance in Extensive-Stage Small Cell Lung Cancer: The Phase 2 TREASURE Randomized Clinical Trial (AIO-TRK-0320).

JAMA oncology·2026
Same author

Supporting Radiology Resident Education and Clinical Decision-Making With Large Language Models: Comparative Study of Reasoning Models DeepSeek-R1 and ChatGPT-o1.

JMIR AI·2026
Same author

Impact of enhanced recovery after surgery (ERAS) on postoperative morbidity and long-term survival in patients with perihilar cholangiocarcinoma.

Langenbeck's archives of surgery·2026
Same author

Imaging-based clinical decision tree enables risk stratification of extraprostatic extension before radical prostatectomy in prostate cancer patients.

Insights into imaging·2026
Same author

Prenylated Isoflavones Originating from East African Medicinal Plants Selectively Modulate the α-Glucosidase from <i>Saccharomyces cerevisiae</i>.

Journal of natural products·2026
Same author

Multimodal Deep Learning for Prediction of Progression-Free Survival in Patients with Neuroendocrine Tumors Undergoing <sup>177</sup>Lu-Based Peptide Receptor Radionuclide Therapy.

Cancers·2026

Related Experiment Video

Updated: Jan 7, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K

Independent Validation of a Machine Learning Classifier for Predicting Mediastinal Lymph Node Metastases in Non-Small

Agata Wdowiak1,2, Julian M M Rogasch1,3, Georg L Baumgärtner4

  • 1Department of Nuclear Medicine, Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, 13353 Berlin, Germany.

Current Oncology (Toronto, Ont.)
|December 24, 2025
PubMed
Summary
This summary is machine-generated.

A machine learning (ML) classifier improves lymph node staging accuracy in non-small cell lung cancer (NSCLC) patients. This validated ML tool offers higher specificity than standard PET/CT criteria for detecting advanced lymph node metastasis.

Keywords:
FDG-PET/CTNSCLC RadiogenomicsTCIAlymph node stagingmachine learningnon-small cell lung cancer

More Related Videos

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

11.5K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

470

Related Experiment Videos

Last Updated: Jan 7, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K
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

11.5K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

470

Area of Science:

  • Oncology
  • Radiology
  • Medical Imaging

Background:

  • 18F]FDG-PET/CT imaging in non-small cell lung cancer (NSCLC) is prone to false-positive lymph node (LN) staging.
  • Previous work showed machine learning (ML) improves diagnostic accuracy over visual assessment.
  • Independent validation of an ML classifier for LN staging in NSCLC is needed.

Purpose of the Study:

  • To independently validate a previously developed ML classifier for lymph node staging in NSCLC.
  • To compare the ML classifier's diagnostic performance against standard PET/CT criteria.
  • To assess the ML classifier's specificity and sensitivity in independent patient cohorts.

Main Methods:

  • An ML classifier using routine [18F]FDG-PET/CT and clinical data was applied to two independent NSCLC cohorts.
  • Cohort 1 (Charité) included 87 patients; Cohort 2 (TCIA) included 124 patients.
  • Performance was compared to the standard criterion (mediastinal LN uptake > mediastinum and/or short-axis > 10 mm), with histology as the reference standard.

Main Results:

  • The ML classifier demonstrated significantly higher specificity in the TCIA cohort (90% vs. 70%, p < 0.001) compared to standard criteria.
  • Specificity was similar between ML and standard criteria in the Charité cohort (65% vs. 60%, p = 0.5).
  • Sensitivity for advanced lymph node metastasis (pN2/3) was comparable between ML and standard criteria in both cohorts (Charité: 97%, TCIA: 27-33%).

Conclusions:

  • The ML classifier's diagnostic performance, particularly its superior specificity, was successfully validated in two independent NSCLC cohorts.
  • The ML approach shows promise for improving the accuracy of lymph node staging in NSCLC.
  • The validated ML classifier can enhance diagnostic accuracy beyond conventional visual assessment of [18F]FDG-PET/CT scans.