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

Artificial intelligence-guided analysis of the tumor microenvironment predicts response to pembrolizumab in rare tumors.

Journal for immunotherapy of cancer·2026
Same author

Analysis of the impact of altitude changes on human physiological indicators and response capabilities.

Scientific reports·2026
Same author

Automated recognition of surgical phases in robot-assisted radical prostatectomy using a Hiera-based vision transformer.

BJU international·2026
Same author

A foundation model of cancer genotype enables precise predictions of therapeutic response.

Cancer discovery·2026
Same author

Synergistic mechanisms of bacteria and fungi in the biodegradation of Benzo[a]pyrene: Insights from metagenomic and metabolomic analyses.

Environmental research·2026
Same author

Spatial transcriptional mapping reveals the molecular characteristics of juxtaglomerular cell tumors.

Frontiers in oncology·2026
Same journal

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Medical image analysis·2026
Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026
Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026
Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026
Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026
Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026
See all related articles

Related Experiment Video

Updated: Sep 12, 2025

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
07:46

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

4.9K

OCELOT 2023: Cell detection from cell-tissue interaction challenge.

JaeWoong Shin1, Jeongun Ryu1, Aaron Valero Puche1

  • 1Lunit Inc., Seoul, Republic of Korea.

Medical Image Analysis
|August 9, 2025
PubMed
Summary
This summary is machine-generated.

Understanding cell and tissue interactions in whole-slide images significantly improves deep learning models for pathology. The OCELOT 2023 challenge demonstrated that incorporating multi-scale cell-tissue semantics boosts performance over cell-only detection.

Keywords:
Cancerous tissue segmentationCell–Tissue relationshipsTumor cell detection

More Related Videos

A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication
09:52

A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication

Published on: September 20, 2016

10.5K
In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces
07:42

In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces

Published on: March 19, 2010

10.9K

Related Experiment Videos

Last Updated: Sep 12, 2025

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
07:46

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

4.9K
A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication
09:52

A Mimic of the Tumor Microenvironment: A Simple Method for Generating Enriched Cell Populations and Investigating Intercellular Communication

Published on: September 20, 2016

10.5K
In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces
07:42

In-vivo Detection of Protein-protein Interactions on Micro-patterned Surfaces

Published on: March 19, 2010

10.9K

Area of Science:

  • Digital pathology
  • Computational biology
  • Artificial intelligence in medicine

Background:

  • Pathologists use varying magnifications on whole-slide images for diagnosis, assessing both tissue morphology and cellular detail.
  • Current deep learning cell detection models lack the ability to integrate multi-scale information and understand interdependent semantics between structures at different magnifications.
  • A critical limitation in the field is the absence of datasets with multi-scale, overlapping cell and tissue annotations.

Purpose of the Study:

  • To validate the hypothesis that understanding cell-tissue interactions is crucial for achieving human-level performance in digital pathology.
  • To accelerate research in multi-scale cell and tissue analysis by providing a standardized challenge and dataset.
  • To foster community engagement and gather insights on advanced deep learning approaches for pathology image analysis.

Main Methods:

  • The OCELOT 2023 challenge dataset was curated, featuring overlapping cell detection and tissue segmentation annotations from six organs.
  • Data was sourced from The Cancer Genome Atlas (TCGA) whole-slide images with hematoxylin and eosin staining.
  • The dataset comprised 673 annotated pairs from 306 whole-slide images, divided into training, validation, and test subsets.

Main Results:

  • Participating models demonstrated significant improvements in understanding cell-tissue relationships.
  • The top-performing models achieved up to a 7.99 increase in F1-score on the test set compared to baseline cell-only models.
  • These results highlight the substantial performance gains achievable by incorporating multi-scale semantics and cell-tissue interactions.

Conclusions:

  • Integrating multi-scale semantics and cell-tissue relationships is essential for advancing deep learning in digital pathology.
  • The OCELOT 2023 challenge successfully spurred innovation in cell-tissue interaction modeling.
  • Future research should focus on developing models that can effectively leverage multi-scale contextual information for more accurate diagnostic support.