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

In-vitro Mutagenesis01:16

In-vitro Mutagenesis

To learn more about the function of a gene, researchers can observe what happens when the gene is inactivated or “knocked out,” by creating genetically engineered knockout animals. Knockout mice have been particularly useful as models for human diseases such as cancer, Parkinson’s disease, and diabetes.
In vitro Mutagenesis01:16

In vitro Mutagenesis

To learn more about the function of a gene, researchers can observe what happens when the gene is inactivated or “knocked out,” by creating genetically engineered knockout animals. Knockout mice have been particularly useful as models for human diseases such as cancer, Parkinson’s disease, and diabetes.

You might also read

Related Articles

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

Sort by
Same author

Increased copy number of mitochondrial DNA predicts poor prognosis of esophageal squamous cell carcinoma.

Oncology letters·2018
Same author

Del17p does not always significantly influence the survival of B-cell chronic lymphoproliferative disorders.

Oncotarget·2018
Same author

Processing bulk natural wood into a high-performance structural material.

Nature·2018
Same author

Retrospective study of paraneoplastic neurological syndromes in a Chinese Han population from Shandong, East China.

The International journal of neuroscience·2018
Same author

Genetics of Magnesium Disorders.

Kidney diseases (Basel, Switzerland)·2018
Same author

Efficacy of Rituximab for Patients with Chronic Lymphocytic Leukemia.

Zhongguo yi xue ke xue yuan xue bao. Acta Academiae Medicinae Sinicae·2018

Related Experiment Video

Updated: Jun 9, 2026

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening
15:28

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening

Published on: January 17, 2014

8.1K

A weakly supervised framework for automated biological assay assessment.

Hongru Jiang1, Qianyu Guo2, Xiao Zhi2

  • 1School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.

Virus Research
|December 19, 2025
PubMed
Summary

This study introduces a weakly supervised framework for automated biological assay quantification. The method efficiently segments viral plaques and microbial colonies, reducing manual labor and maintaining high accuracy in research applications.

Keywords:
Biological assaysImage segmentationMicrobial assayPlaque assayWeakly supervised learning

More Related Videos

A Manual Small Molecule Screen Approaching High-throughput Using Zebrafish Embryos
07:45

A Manual Small Molecule Screen Approaching High-throughput Using Zebrafish Embryos

Published on: November 8, 2014

18.2K
Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
08:58

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

556

Related Experiment Videos

Last Updated: Jun 9, 2026

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening
15:28

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening

Published on: January 17, 2014

8.1K
A Manual Small Molecule Screen Approaching High-throughput Using Zebrafish Embryos
07:45

A Manual Small Molecule Screen Approaching High-throughput Using Zebrafish Embryos

Published on: November 8, 2014

18.2K
Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow
08:58

Efficient Sampling of Genetically Encoded Biosensor Design Space Enabled with a Design of Experiments and Automation Workflow

Published on: October 17, 2025

556

Area of Science:

  • Virology and Microbiology
  • Bioimage Analysis
  • Computational Biology

Background:

  • Accurate quantification of biological assays like plaque and microbial assays is crucial in virology and microbiology.
  • Manual assessment of stain-free, low-contrast images is time-consuming and labor-intensive.
  • Automated segmentation methods often require extensive labeled data, posing a challenge.

Purpose of the Study:

  • To develop a weakly supervised framework for automated biological assay quantification.
  • To reduce the annotation burden in image segmentation for biological specimens.
  • To improve the efficiency and accuracy of analyzing viral plaques and microbial colonies.

Main Methods:

  • Collected and constructed weakly supervised datasets for viral plaque and microbial colony segmentation using point and bounding box annotations.
  • Developed an adaptive region-growing algorithm to generate mask annotations, minimizing manual labeling.
  • Adapted and fine-tuned the Segment Anything Model (SAM) for biological specimen segmentation.

Main Results:

  • The proposed framework achieved accurate segmentation of viral plaques and microbial colonies across diverse assay types.
  • The adaptive region-growing algorithm effectively reduced annotation requirements.
  • Validation on live cell segmentation and antiviral compound assessment demonstrated comparable results to manual methods.

Conclusions:

  • The developed framework offers an efficient and automated solution for biological assay quantification.
  • Weakly supervised learning and adaptive annotation generation significantly reduce the annotation burden.
  • The method maintains high accuracy, making it a valuable tool for virology and microbiology research.