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

Founders in Pediatric Pathology.

Pediatric and developmental pathology : the official journal of the Society for Pediatric Pathology and the Paediatric Pathology Society·2026
Same author

Pathogen to read: a rapid, automated workflow for public health-ready microbial sequencing.

BMC genomics·2026
Same author

Histological predictors of mismatch repair deficiency in endometrial endometrioid carcinoma.

Pathology, research and practice·2026
Same author

Comparative Evaluation of HepG2 Spheroid Generation Methods for Toxicology.

Cellular and molecular bioengineering·2026
Same author

FUGEA: Fused unified gradient ensemble for cross-architecture transferable attacks.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Integrated Experimental-Computational Framework for Drug Transport Quantification in 3D <i>Microtissues</i>™.

Micromachines·2026

Related Experiment Video

Updated: May 8, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.4K

BMT: A Cross-Validated ThinPrep Pap Cervical Cytology Dataset for Machine Learning Model Training and Validation.

E Celeste Welch1, Chenhao Lu2, C James Sung3

  • 1Center for Biomedical Engineering, School of Engineering, Brown University, Providence, RI, 02912, USA.

Scientific Data
|December 28, 2024
PubMed
Summary

This study introduces the first public multicellular ThinPrep® Pap smear dataset for AI training. This resource aids in developing more accurate cervical dysplasia diagnostic models.

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.2K
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

1.7K

Related Experiment Videos

Last Updated: May 8, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.4K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.2K
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

1.7K

Area of Science:

  • Cytopathology
  • Medical Imaging
  • Machine Learning

Background:

  • Existing Pap smear datasets often use older methods or single cells, limiting AI model generalizability.
  • Multicellular liquid-based Pap datasets better represent current cervical screening techniques.
  • Models trained on one preparation method (e.g., SurePath™) perform poorly on others (e.g., ThinPrep®) due to visual differences.

Purpose of the Study:

  • To present the first publicly available multicellular ThinPrep® Pap smear image dataset.
  • To provide a resource for training and testing artificial intelligence models for cervical screening.
  • To improve the accuracy of AI models in diagnosing cervical dysplasia.

Main Methods:

  • Creation of the "Brown Multicellular ThinPrep" (BMT) dataset.
  • Collection of 600 clinically vetted images from 180 Pap smear slides.
  • Classification of images into three key diagnostic categories.

Main Results:

  • The BMT dataset is the first of its kind, offering a valuable resource for AI development.
  • The dataset addresses the limitations of existing datasets, particularly the visual discrepancies between preparation methods.
  • Facilitates the development of AI models trained on the more common ThinPrep® protocol.

Conclusions:

  • The BMT dataset is crucial for advancing AI in cervical cancer screening.
  • This resource will enable the development of more robust and accurate diagnostic tools.
  • Aims to enhance the early detection of cervical dysplasia through improved AI performance.