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

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.7K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
6.7K
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)01:15

Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)

455
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT) is an advanced Nuclear Magnetic Resonance (NMR) technique specifically designed to detect and enhance the signals of low-abundance nuclei, such as carbon-13 and nitrogen-15, in small molecules. The fundamental principle behind INEPT is the transfer of polarization from a more abundant and highly polarizable nucleus, typically hydrogen-1, to the low-abundance nucleus of interest. This process effectively boosts the NMR signal of the...
455
Detection of Black Holes01:10

Detection of Black Holes

2.3K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Quantitative 3D histology reveals localized immune remodeling during early pancreatic cancer progression.

Cell press blue·2026
Same author

The evolving role of DICOM in digital pathology.

Journal of pathology informatics·2026
Same author

Single-Stage Lesion Identification in $^{68}$Ga-DOTATATE PET Images.

IEEE transactions on bio-medical engineering·2026
Same author

Predicting intracranial pressure monitor placement in children with traumatic brain injury: a prospective cohort study to develop a clinical decision support tool.

Journal of the American Medical Informatics Association : JAMIA·2025
Same author

Precision Medicine in Pediatric Autoimmunity: Leniolisib Treatment of Childhood-Onset Lupus Nephritis Due to Activated Phosphoinositide 3-Kinase δ Syndrome.

Arthritis & rheumatology (Hoboken, N.J.)·2025
Same author

Population-Driven Synthesis of Personalized Cranial Development From Cross-Sectional Pediatric CT Images.

IEEE transactions on bio-medical engineering·2025

Related Experiment Video

Updated: Aug 21, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Low-Resource Adversarial Domain Adaptation for Cross-Modality Nucleus Detection.

Fuyong Xing1, Toby C Cornish2

  • 1Depatment of Biostatistics and Informatics, University of Colorado Anschutz Medical Campus.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|November 16, 2022
PubMed
Summary

This study introduces a novel unsupervised domain adaptation method for nucleus detection using limited data. The approach enhances generative adversarial networks (GANs) to improve cell/nucleus detection across different microscopy imaging modalities, even with scarce training examples.

Keywords:
Domain adaptationGANNucleus detection

More Related Videos

Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

393
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

606

Related Experiment Videos

Last Updated: Aug 21, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

393
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

606

Area of Science:

  • Computational Biology
  • Medical Imaging
  • Machine Learning

Background:

  • Deep learning models for nucleus detection struggle with domain shifts across different microscopy imaging modalities.
  • Unsupervised domain adaptation (UDA) using generative adversarial networks (GANs) shows promise but typically requires extensive unannotated data.
  • Existing UDA methods degrade significantly with limited target training data, a common issue in real-world scenarios.

Purpose of the Study:

  • To develop a robust UDA method for nucleus detection in low-resource settings, addressing the scarcity of annotated target domain data.
  • To improve the performance of nucleus detection models when only a very limited amount of unannotated target data is available.
  • To enable accurate nucleus detection across diverse microscopy imaging modalities without extensive manual labeling.

Main Methods:

  • Augmented a dual generative adversarial network (GAN) with a task-specific model to enhance the discriminator and aid generator learning with limited data.
  • Incorporated a stochastic, differentiable data augmentation module to mitigate discriminator overfitting and improve training stability.
  • The task model utilized cross-domain prediction consistency to preserve semantic content during image-to-image translation.

Main Results:

  • The proposed low-resource UDA method significantly outperformed state-of-the-art UDA approaches on public cross-modality microscopy datasets.
  • Achieved highly competitive or superior performance compared to fully supervised models, even with only a single training image in the target domain.
  • Demonstrated the effectiveness of the task-augmented GAN and data augmentation module in challenging low-resource UDA scenarios for nucleus detection.

Conclusions:

  • The developed method offers an effective solution for nucleus detection in low-resource domains, overcoming limitations of existing UDA techniques.
  • This approach significantly advances the applicability of deep learning for cell and nucleus detection in diverse biological imaging contexts.
  • The plug-and-play nature of the data augmentation module allows for easy integration into existing GAN-based UDA frameworks.