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

Retention vs. Stability: A Comparative Study of Thermoplastic Materials for Oral Appliance Therapy.

Cureus·2026
Same author

Correction to: Proactive preventive dental care to maintain eating function in palliative care: a narrative review.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2026
Same author

Proactive preventive dental care to maintain eating function in palliative care: a narrative review.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2026
Same author

Mechanistic and Therapeutic Insights into Nrf2-Mediated Redox Regulation in Periodontitis.

Antioxidants (Basel, Switzerland)·2026
Same author

Efficacy and safety of efgartigimod PH20 SC for Sjögren's disease-associated dryness: study protocol for an investigator-initiated, multicenter, phase 2, randomized, double-blind, placebo-controlled trial (OASIS study).

Frontiers in medicine·2026
Same author

Giant Peripheral Osteoma of the Mandibular Antegonial Notch in an Elderly Patient: A Case Report.

Cureus·2026

Related Experiment Video

Updated: Jun 23, 2025

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells
06:03

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

Published on: June 23, 2023

455

Background removal for debiasing computer-aided cytological diagnosis.

Keita Takeda1, Tomoya Sakai2,3, Eiji Mitate4

  • 1School of Information and Data Sciences, Nagasaki University, 1-14 Bunkyo, Nagasaki, 8528521, Japan. ktakeda@nagasaki-u.ac.jp.

International Journal of Computer Assisted Radiology and Surgery
|June 25, 2024
PubMed
Summary

This study introduces a deep learning method for cell segmentation and background removal in cytology images, improving accuracy without needing cell annotations. The approach effectively debiases cell detection and classification, aiding in accurate cytological diagnosis.

Keywords:
Data cleaningDeep learningOral cytologyRobust principal component analysisU-Net

More Related Videos

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
07:05

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

2.6K
Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation
10:33

Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation

Published on: September 4, 2017

15.7K

Related Experiment Videos

Last Updated: Jun 23, 2025

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells
06:03

AMEBaS: Automatic Midline Extraction and Background Subtraction of Ratiometric Fluorescence Time-Lapses of Polarized Single Cells

Published on: June 23, 2023

455
Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures
07:05

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

2.6K
Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation
10:33

Expedited Radiation Biodosimetry by Automated Dicentric Chromosome Identification ADCI and Dose Estimation

Published on: September 4, 2017

15.7K

Area of Science:

  • Digital pathology
  • Artificial intelligence in medicine
  • Computational cytology

Background:

  • Microscopic slide deterioration causes background-bias in computer-aided cytology.
  • This bias affects deep learning-based cell classification and diagnosis.
  • Cell annotation is labor-intensive and time-consuming.

Purpose of the Study:

  • To propose a deep learning approach for unsupervised cell segmentation and background removal.
  • To address the background-bias problem in oral liquid-based cytology (LBC) images.
  • To enable accurate cytological diagnosis without cell annotation.

Main Methods:

  • A U-Net-based deep learning model was developed.
  • The model was trained in an unsupervised manner to separate cells from background.
  • Leveraged background redundancy and cell sparsity in liquid-based cytology (LBC) images.

Main Results:

  • The U-Net model accurately segmented cells and excluded background features.
  • The method demonstrated effectiveness even with a small set of cytology images.
  • Successfully debiased cell detection and classification in oral LBC.

Conclusions:

  • The proposed method effectively removes background noise from cytology images.
  • Enables accurate cell segmentation and debiasing without the need for cell annotation.
  • Facilitates reliable deep learning-based cytological diagnosis from microscopic slide images.