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

Synthetic Priors for Real-World Detection: a Label-Free Framework for Identifying Ultra-Rare Objects.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Explainable Deep Reinforcement Learning for Anomaly Detection in IoT-Enabled Metaverse Healthcare: Toward Trustworthy Cyber Threat Intelligence.

Research (Washington, D.C.)·2026
Same author

CBAM-Enhanced CNN-LSTM with Improved DBSCAN for High-Precision Radar-Based Gesture Recognition.

Sensors (Basel, Switzerland)·2026
Same author

Intercomparisons of computed epithelial/absorbed power density and temperature rise in anatomical human face models under localized exposures at 10 GHz and 30 GHz.

Physics in medicine and biology·2025
Same author

Simultaneous classification and delineation of seven types of histological growth patterns in lung adenocarcinomas using self-supervised learning and online hard patch mining.

Quantitative imaging in medicine and surgery·2025
Same author

Diffusion Model with Relation-Aware Attention and Edge-Aware Constraint for Multi-Modal Brain Tumor Segmentation.

IEEE journal of biomedical and health informatics·2025

Related Experiment Video

Updated: Aug 7, 2025

Micromanipulation of Circulating Tumor Cells for Downstream Molecular Analysis and Metastatic Potential Assessment
05:17

Micromanipulation of Circulating Tumor Cells for Downstream Molecular Analysis and Metastatic Potential Assessment

Published on: May 14, 2019

8.7K

Attention Mask R-CNN with edge refinement algorithm for identifying circulating genetically abnormal cells.

Xu Xu1, Congsheng Li1, Xianjun Fan2

  • 1China Academy of Information and Communications Technology, Beijing, China.

Cytometry. Part a : the Journal of the International Society for Analytical Cytology
|March 13, 2023
PubMed
Summary
This summary is machine-generated.

A new AI method, CACNET, accurately identifies circulating genetically abnormal cells (CACs) from FISH images, improving early lung cancer detection by overcoming challenges like overlapping cells and noise.

Keywords:
cell identificationcirculating genetically abnormal cellsconvolutional neural networknon-local module

More Related Videos

Capture and Release of Viable Circulating Tumor Cells from Blood
08:10

Capture and Release of Viable Circulating Tumor Cells from Blood

Published on: October 28, 2016

8.6K
Clinical Microfluidic Chip Platform for the Isolation of Versatile Circulating Tumor Cells
05:58

Clinical Microfluidic Chip Platform for the Isolation of Versatile Circulating Tumor Cells

Published on: October 13, 2023

1.3K

Related Experiment Videos

Last Updated: Aug 7, 2025

Micromanipulation of Circulating Tumor Cells for Downstream Molecular Analysis and Metastatic Potential Assessment
05:17

Micromanipulation of Circulating Tumor Cells for Downstream Molecular Analysis and Metastatic Potential Assessment

Published on: May 14, 2019

8.7K
Capture and Release of Viable Circulating Tumor Cells from Blood
08:10

Capture and Release of Viable Circulating Tumor Cells from Blood

Published on: October 28, 2016

8.6K
Clinical Microfluidic Chip Platform for the Isolation of Versatile Circulating Tumor Cells
05:58

Clinical Microfluidic Chip Platform for the Isolation of Versatile Circulating Tumor Cells

Published on: October 13, 2023

1.3K

Area of Science:

  • Biomedical Engineering
  • Computational Biology
  • Oncology

Background:

  • Circulating genetically abnormal cells (CACs) show potential for non-invasive detection of pulmonary nodules.
  • Current identification methods using 4-color fluorescence in situ hybridization (FISH) face challenges with overlapping cells and fluorescence noise, impacting diagnostic efficiency.

Purpose of the Study:

  • To develop an advanced, end-to-end method (CACNET) for accurate and efficient identification of CACs from FISH images.
  • To improve the accuracy and speed of CAC identification, addressing limitations in existing diagnostic approaches.

Main Methods:

  • Proposed CACNET, an end-to-end FISH-based method utilizing an improved Mask region-based convolutional neural network (R-CNN).
  • Enhanced Mask R-CNN with an edge constraint head for improved nuclear segmentation of overlapping cells.
  • Integrated a non-local module to reduce fluorescence noise interference during feature extraction.

Main Results:

  • CACNET achieved high performance metrics: 94.06% accuracy, 92.1% sensitivity, and 99.8% specificity for CAC identification.
  • The method demonstrated efficient processing with an approximate identification speed of 0.22 seconds per frame.
  • CACNET significantly outperformed existing CAC identification methods in accuracy and efficiency.

Conclusions:

  • CACNET offers a robust and efficient solution for identifying circulating genetically abnormal cells (CACs) from FISH data.
  • The developed method shows significant promise for improving the early screening and diagnosis of lung cancer.