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 Video

Updated: Jun 4, 2026

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

Machine Learning Assessment of Pathologic Response in Lung Cancer Resections After Neoadjuvant Therapy-IASLC MPR

Sanja Dacic1, Daniel Shenker2, Mary Redman3

  • 1Department of Pathology, Yale School of Medicine, New Haven, Connecticut.

Journal of Thoracic Oncology : Official Publication of the International Association for the Study of Lung Cancer
|June 2, 2026
PubMed

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

Ki67 proliferation index augments two-tier tumour grade in prediction of survival and progression-free survival in epithelioid pleural mesothelioma.

ERJ open research·2026
Same author

The 2025 ATS/ERS update of the international multidisciplinary classification of the interstitial pneumonias: implications for the pathologist.

Histopathology·2026
Same author

Association of bronchoalveolar lavage cellular analysis and radiological findings in fibrotic interstitial lung diseases.

BMJ open respiratory research·2026
Same author

Bronchiolocentric interstitial pneumonia is a more accurate interstitial lung disease classification than hypersensitivity pneumonitis: pro.

American journal of respiratory and critical care medicine·2026
Same author

Rebuttal to "Bronchiolocentric interstitial pneumonia is a more accurate interstitial lung disease classification than hypersensitivity pneumonitis: con".

American journal of respiratory and critical care medicine·2026
Same author

Clinical applications of the 2025 ERS/ATS update of the international multidisciplinary classification of the interstitial pneumonias.

The European respiratory journal·2026
Summary
This summary is machine-generated.

Machine learning models accurately assess pathologic response (PR) in non-small cell lung cancer (NSCLC) after neoadjuvant therapy, showing high agreement with pathologists and similar survival outcomes.

Area of Science:

  • Pathology
  • Oncology
  • Artificial Intelligence in Medicine

Background:

  • Accurate assessment of pathologic response (PR) is crucial for treatment efficacy in surgically resected lung cancers post-neoadjuvant therapy.
  • Machine learning (ML) offers potential for enhanced efficiency and accuracy in PR evaluation.

Purpose of the Study:

  • Develop and validate digital models using ML for quantifying tumor bed (TB) area and residual viable tumor (VT).
  • Compare ML-derived PR assessments against pathologist evaluations from the IASLC reproducibility study.

Main Methods:

  • Trained convolutional neural network (digital AI) and Convex Hull algorithm (CHA) models using extensive manual pathologist annotations (N=15,564).
  • Calculated PR as the percentage of VT within the TB area for both digital models and pathologist average PR (APR).
Keywords:
Lung cancerMPRMachine learningNeoadjuvant therapyReproducibility

Related Experiment Videos

Last Updated: Jun 4, 2026

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

  • Assessed concordance between pathologist APR, digital AI, and CHA, correlating findings with patient outcomes.

    • Main Results:

    • Demonstrated strong correlations between all approaches: APR vs. Digital AI (0.97), APR vs. CHA (0.97), and Digital AI vs. CHA (0.99).
    • Achieved 100% agreement for major pathologic response (MPR) between digital PR and CHA, with high kappa concordance (0.82) between pathologist APR and digital methods.
    • Observed higher concordance in squamous cell carcinoma (Kappa 0.92) compared to non-squamous carcinoma (Kappa 0.77).
    • Digital AI and pathologist APR showed comparable relapse-free survival (RFS) and overall survival (OS) outcomes.

    Conclusions:

    • The high agreement between machine learning approaches and pathologist assessments supports their utility in evaluating PR for NSCLC patients.
    • Digital AI and CHA models provide reliable and reproducible PR evaluations, potentially aiding clinical decision-making.