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

Deep-learning-based breast cancer stage prediction from H&E-stained whole-slide images in resource-constrained settings.

Journal of pathology informatics·2026
Same author

Comparison of QuPath and HALO Platforms for Analysis of the Tumor Microenvironment in Prostate Cancer.

Laboratory investigation; a journal of technical methods and pathology·2025
Same author

CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification.

Medical image analysis·2025
Same author

Comparison of QuPath and HALO platforms for analysis of the tumor microenvironment in prostate cancer.

bioRxiv : the preprint server for biology·2025
Same author

Human Immunodeficiency Virus-Associated Differences in the Tumor Immune Microenvironment of Lung, Breast, and Prostate Cancers.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2025
Same author

Intermediate risk prostate tumors contain lethal subtypes.

Frontiers in urology·2025

Related Experiment Video

Updated: Dec 13, 2025

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment
06:05

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

9.5K

Deep learning-based image analysis methods for brightfield-acquired multiplex immunohistochemistry images.

Danielle J Fassler1, Shahira Abousamra2, Rajarsi Gupta3

  • 1Department of Pathology, Stony Brook University Renaissance School of Medicine, 101 Nicolls Rd, Stony Brook, 11794, USA.

Diagnostic Pathology
|July 30, 2020
PubMed
Summary
This summary is machine-generated.

Deep learning tools analyze multiplex immunohistochemistry (mIHC) whole-slide images, enabling precise classification of six cell types. These methods offer a scalable solution for tumor microenvironment research in pancreatic cancer.

Keywords:
Deep learningDigital pathology image analysisMultiplex immunohistochemistryTumor immune microenvironment

More Related Videos

Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples
08:18

Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples

Published on: April 7, 2023

2.1K
A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections
07:50

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

10.0K

Related Experiment Videos

Last Updated: Dec 13, 2025

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment
06:05

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

9.5K
Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples
08:18

Multiplexed Barcoding Image Analysis for Immunoprofiling and Spatial Mapping Characterization in the Single-Cell Analysis of Paraffin Tissue Samples

Published on: April 7, 2023

2.1K
A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections
07:50

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

10.0K

Area of Science:

  • Computational pathology
  • Digital pathology
  • Biomedical image analysis

Background:

  • Multiplex immunohistochemistry (mIHC) allows simultaneous detection of multiple biomarkers in a single tissue section.
  • Digital pathology and whole-slide image (WSI) analysis offer reproducible evaluation of mIHC slides.
  • Existing methods struggle to analyze more than four biomarkers, necessitating advanced computational approaches.

Purpose of the Study:

  • To develop and validate deep learning tools for quantitative analysis of six biomarkers in mIHC WSIs.
  • To address limitations in current methods for analyzing high-plex mIHC data.
  • To enable detailed spatial analysis of the tumor microenvironment (TME) in pancreatic ductal adenocarcinoma (PDAC).

Main Methods:

  • Utilized six chromogens to label T-cells (CD3, CD4, CD8), B-cells (CD20), macrophages (CD16), and tumor cells (K17) in FFPE PDAC tissues.
  • Developed deep learning models: ColorAE (autoencoder for color segmentation) and U-Net (CNN for cell segmentation).
  • Created ensemble methods (ColorAE:U-Net) and assessed performance against pathologist annotations using metrics like DICE score and F1 score.

Main Results:

  • ColorAE performance is comparable to traditional color deconvolution for single stains.
  • ColorAE and U-Net are complementary, achieving comparable performance in detecting six cell classes.
  • Ensemble methods (ColorAE:U-Net) outperform individual models, enabling detailed TME analysis.
  • Demonstrated proof of concept for quantitative spatial analysis of immune cells within the PDAC TME.

Conclusions:

  • Scalable deep learning methods reliably detect and classify six cell populations in mIHC WSIs.
  • The ColorAE:U-Net ensemble method facilitates quantitative description of immune cell spatial distribution in the tumor microenvironment.
  • These computational tools are readily deployable for clinical research, advancing PDAC studies.