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 25, 2026

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

Deep learning‑based cell type prediction in lung tissue from brightfield histology using CODEX-derived labels.

Sumanth Devarasetty1, Nicholas Lucarelli1, Sayat Mimar1

  • 1Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, University of Florida, Gainesville, FL.

Proceedings of Spie--The International Society for Optical Engineering
|June 24, 2026
PubMed
Summary

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

DigitAb: Domain-Adaptive Cell Type Prediction Method from Light Microscopy Images.

bioRxiv : the preprint server for biology·2026
Same author

Spatially Resolved Banff Tubulitis and Glomerulitis Scoring in Kidney Allograft Biopsies via Artificial Intelligent -Based Structure Segmentation and Spatial Transcriptomics.

bioRxiv : the preprint server for biology·2026
Same author

Fusion Annotator: A Platform for Accelerating Consensus-Driven Ground Truth Generation with AI Assistance.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Pathomic analysis of 5-year surveillance biopsies as predictors of kidney allograft loss.

American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons·2026
Same author

AI-Based Digital Pathology-Enabled Spatial-Omics Data Analyses of the Human Kidney.

Journal of proteome research·2026
Same author

A MEF2C transcription factor network regulates proliferation of glomerular endothelial cells in diabetic kidney disease.

Kidney international·2026
This summary is machine-generated.

Researchers developed a deep learning method to identify lung cell types from inexpensive H&E stains, using data from advanced CODEX imaging. This approach shows promise for scalable cell mapping in pathology and research.

Area of Science:

  • Computational pathology
  • Biomedical imaging analysis
  • Deep learning in histology

Background:

  • Accurate cell type identification in lung biopsies is crucial for diagnosis and research.
  • Multiplex imaging (e.g., CODEX) provides detailed cell maps but is costly and labor-intensive.
  • Routine Hematoxylin and Eosin (H&E) staining is cost-effective but lacks detailed cell-type resolution.

Purpose of the Study:

  • To develop a deep learning pipeline for automated cell type detection in H&E stained lung tissue.
  • To leverage high-resolution CODEX data as ground truth for training the model.
  • To assess the feasibility of approximating multiplexed imaging cell maps from standard histology.

Main Methods:

  • A dataset of over 2.3 million cells from H&E stained lung sections was annotated using paired CODEX images.
Keywords:
Computational pathologyPhenocyclercell type predictioncomputer visionhistologyproteomicsspatial omics

More Related Videos

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

Related Experiment Videos

Last Updated: Jun 25, 2026

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

  • Cells were categorized into five broad classes: epithelial, immune, endothelial, stromal, and contractile.
  • A DeepLabV3+ semantic segmentation model with a ResNet backbone was trained and tested on the annotated data.

    • Main Results:

    • The deep learning model achieved 51.3% balanced accuracy in classifying five broad cell types.
    • This performance is approximately 2.5 times better than a random guessing baseline (20%).
    • The framework successfully demonstrated the potential to map cell types from routine H&E histology.

    Conclusions:

    • Deep learning can effectively predict cell types from standard H&E stained lung tissue.
    • This approach offers a scalable and cost-effective alternative to advanced imaging techniques for cell mapping.
    • The developed pipeline shows feasibility for enhancing diagnostic and research capabilities in lung pathology.