Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys.

Nature communications·2026

Same author

Dissecting autonomous enzymatic variability in single cells.

Nature communications·2026

Same author

A genome-scale CRISPRi perturbation atlas of human induced pluripotent stem cells.

Nature biotechnology·2026

Same author

From Fundamental Photophysics to Photocatalysis: Energy Gap Law Analysis of Anion Radical Excited States.

ACS central science·2026

Same author

Optimizing Performance and Satisfaction in Matching and Movement Tasks in Virtual Reality with Interventions Using the Data Visualization Literacy Framework.

Frontiers in virtual reality·2026

Same author

Cell shapes decode molecular phenotypes in image-based spatial proteomics.

Cell systems·2026

Same journal

PCSK5 promotes angiogenesis and cardiac repair after myocardial infarction.

Nature communications·2026

Same journal

PfApiAT2 is a proline transporter essential for the transmission of Plasmodium falciparum by the mosquito vector.

Nature communications·2026

Same journal

Transient distortions of the South Atlantic Anomaly radiation environments driven by electric fields.

Nature communications·2026

Same journal

Structural basis of the regulation by CDK11 kinase of early spliceosome activation and evidence for its proofreading by DHX15 helicase.

Nature communications·2026

Same journal

Structural and mechanistic insights into primer synthesis initiation by DNA primase.

Nature communications·2026

Same journal

Changes in heritability and shared environmentality of educational attainment across twentieth-century Norway.

Nature communications·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 20, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Segmenting functional tissue units across human organs using community-driven development of generalizable machine

Yashvardhan Jain¹, Leah L Godwin², Sripad Joshi²

¹Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, 47408, USA. yashjain@iu.edu.

Nature Communications

|August 3, 2023

Summary

This summary is machine-generated.

Machine learning models were developed to automatically segment anatomical structures in human histology images for the Human Reference Atlas. This community effort overcame tissue variations, with the best model to be integrated into the HuBMAP portal.

More Related Videos

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

Related Experiment Videos

Last Updated: Jul 20, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

Area of Science:

Computational biology and digital pathology
Artificial intelligence in biomedical imaging

Background:

Creating a comprehensive reference atlas of the healthy human body necessitates automated segmentation of anatomical structures from diverse bioimage sources.
Variations in sample preparation and tissue types present significant challenges for accurate image analysis.

Purpose of the Study:

To foster community-driven development of machine learning (ML) models for automated segmentation of anatomical structures in histology images.
To establish a robust ML pipeline for processing large-scale tissue image datasets to support the Human Reference Atlas (HRA) construction.

Main Methods:

A machine learning algorithm development competition, 'Hacking the Human Body', was hosted on Kaggle by the Human Biomolecular Atlas (HuBMAP) and Human Protein Atlas (HPA) teams.
A dataset of 880 histology images with 12,901 segmented structures was created.
Participating teams (1175) utilized techniques such as color normalization and hybrid models (vision transformers with convolutional neural networks) to address tissue variations.

Main Results:

The competition successfully engaged a global community in developing advanced ML models for bioimage segmentation.
Effective strategies, including color normalization and combined model architectures, were employed to overcome dataset challenges.
The top-performing model demonstrated high accuracy in segmenting diverse anatomical structures.

Conclusions:

Community-driven, open-science approaches can accelerate the development of sophisticated ML tools for biomedical research.
The best ML model will be integrated into the HuBMAP portal, enabling scalable processing of tissue images for HRA.
This initiative advances the creation of a detailed Human Reference Atlas, crucial for understanding human biology and disease.