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

A knowledge-guided deep learning framework for quantitative nucleic acid testing.

Briefings in bioinformatics·2026

Same author

DyMamba: dynamic Mamba for microscopy image semantic segmentation.

Bioinformatics (Oxford, England)·2026

Same author

Earthworm-Inspired Self-Powered Multistimuli Neuromorphic Vision Skin with Homogeneous Ion Heterogel Arrays.

ACS applied materials & interfaces·2026

Same author

A variational framework with composite sparse regularization for cryo-electron tomography reconstruction.

Bioinformatics (Oxford, England)·2026

Same author

Corrective osteotomy for distal radius malunion using 3D-printed patient-specific guides and spacers: a retrospective comparative study.

BMC musculoskeletal disorders·2026

Same author

MSFSNet: Multi-Source Few-Shot Adaptation Network for Cross-Subject Depression Recognition from EEG Signals.

IEEE journal of biomedical and health informatics·2026

Same journal

EC-isHCR: A rapid method for in situ hybridization chain reaction in diverse animal samples.

Methods (San Diego, Calif.)·2026

Same journal

Single-Molecule methods to investigate mechanisms of transcription by RNA polymerase of Mycobacterium tuberculosis.

Methods (San Diego, Calif.)·2026

Same journal

Detection and sequencing of Usutu virus during mosquito surveillance: Use of multiple assays and techniques for identification at low levels.

Methods (San Diego, Calif.)·2026

Same journal

Experimental validation of an AI-driven digital healthcare platform for oral health behavior and plaque assessment among vietnamese children.

Methods (San Diego, Calif.)·2026

Same journal

Zeta potential: An efficient and cost-effective alternative for investigating cell-surface interactions.

Methods (San Diego, Calif.)·2026

Same journal

An automated workflow for quantifying the formation of synuclein aggregates in human dopaminergic neurons.

Methods (San Diego, Calif.)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 11, 2025

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

Hexagonal image segmentation on spatially resolved transcriptomics.

Jing Gao¹, Kai Hu¹, Fa Zhang²

¹Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan 411105, China.

Methods (San Diego, Calif.)

|November 6, 2023

Summary

This summary is machine-generated.

A new hexagonal Convolutional Neural Network (hexCNN) effectively identifies spatial domains in spatial transcriptomics data. This method reduces noise and compensates for missing gene expression, improving accuracy over existing approaches.

Keywords:

Batch effect Convolutional neural network Graph neural network Spatial domain identification Spatial transcriptomics

More Related Videos

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis

Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis

Published on: May 16, 2025

Related Experiment Videos

Last Updated: Jul 11, 2025

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Mapping the Emergent Spatial Organization of Mammalian Cells using Micropatterns and Quantitative Imaging

Published on: April 30, 2019

Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis

Spatially Compact Arrangement of Larval Zebrafish Sections for Spatial Transcriptomic Analysis

Published on: May 16, 2025

Area of Science:

Genomics
Computational Biology
Bioinformatics

Background:

Spatial transcriptomics captures molecular profiles with spatial information.
Identifying distinct spatial domains with unique gene expression is crucial but challenging.
Current unsupervised methods struggle with noise and dropout in spatial transcriptomic data.

Purpose of the Study:

To propose a novel hexagonal Convolutional Neural Network (hexCNN) for spatial domain identification.
To address noise and dropout issues in spatial transcriptomic data.
To improve the accuracy of spatial domain segmentation.

Main Methods:

Developed a hexagonal Convolutional Neural Network (hexCNN) for hexagonal image segmentation.
Extended an unsupervised algorithm to a supervised learning method to reduce noise.
Designed a hexagonal convolution to compensate for missing gene expression data.

Main Results:

hexCNN achieved 86.8% classification accuracy and 77.1% average Rand index (ARI) on the DLPFC dataset.
Outperformed Graph Neural Networks (GNNs) by 1.4% in accuracy and 2.5% in ARI.
Demonstrated noise removal from batch effects while preserving biological signals.

Conclusions:

hexCNN is a robust method for spatial domain identification in spatial transcriptomics.
The hexagonal convolution effectively handles noise and missing data.
This approach enhances the analysis of spatially resolved transcriptomic data.