Search research articles

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

Invasion dynamics of multifocal breast tumor spheroids in three-dimensional extracellular matrix.

Biophysical journal·2026

Same author

Cancer cell dynamics navigating the complex microenvironment: active nematics and dynamic heterogeneity.

Soft matter·2026

Same author

Coupled Dynamics in Phenotype and Tissue Spaces Shape the Three-Dimensional Cancer Invasion.

PRX life·2025

Same author

Collective Dynamics of Frustrated Biological Neuron Networks.

PRX life·2025

Same author

MiroSCOPE: An AI-driven digital pathology platform for annotating functional tissue units.

bioRxiv : the preprint server for biology·2025

Same author

COEXIST: Coordinated single-cell integration of serial multiplexed tissue images.

PLoS computational biology·2025

Same journal

Quantitative models of photoreceptor metabolisms: implications for rod outer segment length, retinal glycolysis and choroidal blood flow.

Physical biology·2026

Same journal

Mechanical interactions govern self-organized ordering in bacterial colonies on surfaces.

Physical biology·2026

Same journal

Robust chemotaxis beyond sensing limits: signal, noise, and strategy.

Physical biology·2026

Same journal

Ecological dynamics of pro-tumor and anti-tumor teams in the tumor microenvironment.

Physical biology·2026

Same journal

Swarms of female<i>Anopheles gambiae</i>mosquitoes may fracture when perturbed.

Physical biology·2026

Same journal

How exercise scheduling affects IL-6-mediated tumor suppression: a fixed exercise volume perspective.

Physical biology·2026

See all related 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

Search research articles

Related Experiment Video

Updated: Jul 15, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Facilitating cell segmentation with the projection-enhancement network.

Christopher Z Eddy¹, Austin Naylor¹, Christian T Cunningham¹

¹Department of Physics, Oregon State University, Corvallis, OR 97331, United States of America.

Physical Biology

|September 28, 2023

Summary

This summary is machine-generated.

We introduce the Projection Enhancement Network (PEN) to improve 2D cell segmentation from suboptimal 3D microscopy data. PEN enhances semantic representations, boosting segmentation accuracy in crowded samples.

Keywords:

cancer invasion deep learning segmentation spheroid

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jul 15, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Cell biology
Microscopy
Image analysis

Background:

Instance segmentation in cell science typically uses 2D or 3D convolutional networks.
Sub-optimally sampled 3D data from microscopy limits the utility of 3D segmentation, especially in crowded samples with overlapping cells.
2D segmentations offer greater reliability for cell morphology and ease of annotation in such challenging conditions.

Purpose of the Study:

To develop a novel convolutional module, the Projection Enhancement Network (PEN), to process sub-sampled 3D microscopy data.
To generate a 2D RGB semantic compression from 3D data that enhances 2D instance segmentation.
To improve the accuracy and reliability of 2D cell segmentation from challenging 3D datasets.

Main Methods:

Proposed the Projection Enhancement Network (PEN), a novel convolutional module for processing sub-sampled 3D data.
Trained PEN in conjunction with instance segmentation networks (e.g., CellPose, Mask-RCNN).
Utilized data augmentation to increase cell density for training PEN and curated datasets for evaluation.

Main Results:

PEN produces a 2D RGB semantic compression that significantly improves 2D segmentation performance when used with CellPose, outperforming maximum intensity projection.
The learned semantic representation from PEN encodes depth information, benefiting segmentation in complex cellular environments.
PEN's effectiveness was demonstrated by dissecting segmentation strength against cell density using disseminated cells.

Conclusions:

PEN offers a data-driven solution for creating compressed representations of 3D microscopy data.
The Projection Enhancement Network enhances 2D instance segmentation from sub-optimally sampled 3D data, particularly for cell morphology and crowded samples.
PEN provides a valuable tool for improving cell segmentation accuracy and utility in cell science research.