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 Experiment Video

Updated: Feb 20, 2026

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

1.1K

Cell Detection Using Extremal Regions in a Semisupervised Learning Framework.

Nisha Ramesh1,2, Ting Liu3, Tolga Tasdizen1,2

  • 1Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT 84112, USA.

Journal of Healthcare Engineering
|October 26, 2017
PubMed
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

Bortezomib-contained chemotherapy and thalidomide combined with CHOP (Cyclophosphamide, Doxorubicin, Vincristine, and Prednisone) play promising roles in plasmablastic lymphoma: a case report and literature review.

Clinical lymphoma, myeloma & leukemia·2014
Same author

Activation of a novel c-Myc-miR27-prohibitin 1 circuitry in cholestatic liver injury inhibits glutathione synthesis in mice.

Antioxidants & redox signaling·2014
Same author

[Development of Neglect Evaluation Scale for primary school students aged 6-11 years old in rural areas of China].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2014
Same author

A novel transgenic mouse model of Chinese Charcot-Marie-Tooth disease type 2L.

Neural regeneration research·2014
Same author

Recombinant adenovirus-mediated overexpression of 3β-hydroxysteroid-Δ24 reductase.

Neural regeneration research·2014
Same author

Development and characterization of microsatellite markers for Melastoma dodecandrum (Melastomataceae).

Applications in plant sciences·2014
Same journal

RETRACTION: Meta-Analysis of the Prognostic Value of Narcotrend Monitoring of Different Depths of Anesthesia and Different Bispectral Index (BIS) Values for Cognitive Dysfunction after Tumor Surgery in Elderly Patients.

Journal of healthcare engineering·2026
Same journal

Correction to "Representation of Differential Learning Method for Mitosis Detection".

Journal of healthcare engineering·2026
Same journal

RETRACTION: Effect of Combined Etomidate-Ketamine Anesthesia on Perioperative Electrocardiogram and Postoperative Cognitive Dysfunction of Elderly Patients with Rheumatic Heart Valve Disease Undergoing Heart Valve Replacement.

Journal of healthcare engineering·2026
Same journal

RETRACTION: Ensemble Learning-Based Hybrid Segmentation of Mammographic Images for Breast Cancer Risk Prediction Using Fuzzy C-Means and CNN Model.

Journal of healthcare engineering·2026
Same journal

RETRACTION: Wavelet Transform Image Enhancement Algorithm-Based Evaluation of Lung Recruitment Effect and Nursing of Acute Respiratory Distress Syndrome by Ultrasound Image.

Journal of healthcare engineering·2025
Same journal

RETRACTION: lncRNA FGD5-AS1 Regulates Bone Marrow Stem Cell Proliferation and Apoptosis by Affecting miR-296-5p/STAT3 Axis in Steroid-Induced Osteonecrosis of the Femoral Head.

Journal of healthcare engineering·2025
See all related articles

This study introduces a semisupervised learning framework for cell detection, reducing the need for extensive training data. The novel algorithm uses maximally stable extremal regions and a Bayesian approach for efficient cell identification.

Area of Science:

  • Computational Biology
  • Image Analysis
  • Machine Learning

Background:

  • Supervised cell detection requires substantial annotated data, posing a significant challenge.
  • Hierarchical image representations are complex for direct cell candidate extraction.
  • Maximally stable extremal region (MSER) detection offers a method for identifying image regions.

Purpose of the Study:

  • To develop an efficient semisupervised learning framework for cell detection.
  • To reduce the burden of manual data annotation in cell detection tasks.
  • To integrate supervised and unsupervised learning within a probabilistic model.

Main Methods:

  • Utilizing maximally stable extremal region (MSER) detector for generating cell candidates.
  • Developing a novel differentiable unsupervised loss term to enforce non-overlapping constraints.

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.4K

Related Experiment Videos

Last Updated: Feb 20, 2026

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

1.1K
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.4K
  • Employing a Bayesian framework to combine supervised and unsupervised losses for probabilistic learning.

    • Main Results:

    • The proposed algorithm significantly reduces the requirement for large training datasets.
    • Achieved effective cell detection with minimal annotated examples (simple dot annotations).
    • Demonstrated successful integration of supervised and unsupervised learning components.

    Conclusions:

    • The semisupervised framework offers a practical solution for cell detection in biological imaging.
    • The novel unsupervised loss term enhances the robustness of the cell detection algorithm.
    • This approach paves the way for more efficient and scalable cell analysis in research.