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

Search research articles

Related Experiment Video

Updated: Dec 29, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Geometry-Aware Cell Detection with Deep Learning.

Hao Jiang¹, Sen Li¹, Weihuang Liu¹

¹College of Science, Harbin Institute of Technology, Shenzhen, China.

|February 6, 2020

Summary

This summary is machine-generated.

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

Controllable Protein Design by Prefix-Tuning Protein Language Models.

Journal of chemical information and modeling·2026

Same author

Single-round evolution of RNA aptamers with GRAPE-LM.

Nature biotechnology·2026

Same author

AI-empowered super-resolution microscopy: a revolution in nanoscale cellular imaging.

Nature methods·2025

Same author

Biomolecular Interaction Prediction: The Era of AI.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

Same author

iMFP-LG: Identify Novel Multi-functional Peptides Using Protein Language Models and Graph-based Deep Learning.

Genomics, proteomics & bioinformatics·2024

Same author

Clinical Translation of Aptamers for COVID-19.

Journal of medicinal chemistry·2023

Same journal

Global distribution of isoprenoid quinones across Bacteria.

mSystems·2026

Same journal

Environmental former <i>Massilia</i> group bacteria secrete metabolites that promote <i>Leptospira</i> growth.

mSystems·2026

Same journal

Signatures in the gut microbiome of German elite athletes: insights from a matched-subgroup analysis.

mSystems·2026

Same journal

MeLSI: Metric Learning for Statistical Inference in microbiome community composition analysis.

mSystems·2026

Same journal

Disentangling production and persistence of extracellular virions in grassland soils with SIP-viromics.

mSystems·2026

Same journal

Microbial consortia mediating lignocellulose turnover and denitrification in eutrophic lake sediment enrichments.

mSystems·2026

See all related articles

A new deep-learning method, geometric-feature spectrum ExtremeNet (GFS-ExtremeNet), accurately detects diverse cell types by analyzing geometric features. This automated cell detection system improves accuracy and consistency in microscopy image analysis.

Area of Science:

Microscopy and Cell Biology
Artificial Intelligence in Medicine
Computational Biology

Background:

Microscopy image analysis is crucial for research and clinical practice but faces challenges in accuracy and consistency.
Existing deep-learning methods for cell detection often require extensive modifications for new cell types.
Cells exhibit inherent geometrical order, suggesting potential for geometry-based detection methods.

Purpose of the Study:

To develop a generalizable deep-learning method for accurate and consistent cell detection in microscopy images.
To address the limitations of current automated cell detection techniques that lack adaptability to diverse cell morphologies.
To introduce a geometry-aware approach for robust cell recognition across different cell types.

Main Methods:

Keywords:

ExtremeNet adjacency spectrum cell detection geometry aware microscopic image protozoa

More Related Videos

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

Related Experiment Videos

Last Updated: Dec 29, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

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

Proposed geometric-feature spectrum ExtremeNet (GFS-ExtremeNet), a deep-learning model incorporating geometric features.
Utilized ExtremeNet framework with key point detection (topmost, bottommost, rightmost, leftmost, center).
Implemented an adjacency spectrum postprocessing step to validate cell candidates based on key point distances.

Main Results:

GFS-ExtremeNet achieved accurate detection of diverse cell types, including mammalian cell nuclei and protozoa.
Demonstrated successful detection of unicellular parasites within red blood cells without misclassification.
The geometry-aware method outperformed conventional object detection techniques in accuracy and consistency.

Conclusions:

GFS-ExtremeNet offers a novel, geometry-aware deep-learning approach for automated cell detection.
The method shows high accuracy and generalizability across various cell types with defined geometrical order.
This work paves the way for advanced automated cell detection systems in microscopy, with potential applications in diagnostics.