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

Methodological considerations for evaluating deep learning segmentation models in digital pathology whole-slide images.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

NeoCircle: pre- and post-operative circulating tumor DNA dynamics predicts survival in neoadjuvant-treated early breast cancer.

EMBO molecular medicine·2026
Same author

High-depth whole genome sequencing of premalignant breast lesions reveals rearrangement hotspots and personalized management opportunities.

Nature communications·2026
Same author

Development of the W-PREV Model: Integrating HIV/STBBI Prevention and Women's Sexual and Reproductive Healthcare Using an Intersectional Women-Centered Approach.

Journal of the International Association of Providers of AIDS Care·2026
Same author

The critical role of accurate neoplastic cell percentage (NCP) assessment: investigating targeted training strategies for pulmonary biopsy and cytology specimens.

Virchows Archiv : an international journal of pathology·2026
Same author

HER2 expression and <i>HER2</i> gene amplification in thymic epithelial tumors: a narrative review.

Mediastinum (Hong Kong, China)·2026
Same journal

Literature Reviews After AI.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Illustration of transfer learning from breast cancer detection to risk prediction: adaptation to local data and local objectives.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

RadGazeGen: radiomics and gaze-guided chest X-ray generation using diffusion models.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

DDARes-U<sup>2</sup>Net: a dual-decoder adversarial residual U<sup>2</sup>Net algorithm for segmentation of COVID-19 pneumonia lesions.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

High-speed optical tracking and augmented reality platform for image-guided interventions.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Transplant-ready? Evaluating AI lung segmentation models in candidates with severe lung disease.

Journal of medical imaging (Bellingham, Wash.)·2026
See all related articles

Related Experiment Video

Updated: Sep 2, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K

Pilot study to evaluate tools to collect pathologist annotations for validating machine learning algorithms.

Katherine Elfer1,2, Sarah Dudgeon3,4, Victor Garcia1

  • 1United States Food and Drug Administration, Center for Devices and Radiological Health, Office of Science and Engineering Laboratories, Division of Imaging Diagnostics & Software Reliability, Silver Spring, Maryland, United States.

Journal of Medical Imaging (Bellingham, Wash.)
|August 1, 2022
PubMed
Summary
This summary is machine-generated.

Creating a reference standard for artificial intelligence (AI) in digital pathology requires pathologist annotations. This pilot study on stromal tumor-infiltrating lymphocytes (sTILs) density in breast cancer informs AI algorithm validation datasets.

Keywords:
artificial intelligencedigital pathologymachine learningreader studiesreader variabilitytrothing

More Related Videos

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

215
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

521

Related Experiment Videos

Last Updated: Sep 2, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.9K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

215
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

521

Area of Science:

  • Digital pathology
  • Computational pathology
  • Breast cancer research

Background:

  • Artificial intelligence (AI) algorithms require validation using reference standards before clinical use.
  • Creating robust reference standards often relies on pathologist annotations.
  • Stromal tumor-infiltrating lymphocytes (sTILs) are crucial prognostic markers in breast cancer.

Purpose of the Study:

  • To assess the feasibility of creating a reference standard for AI validation using pathologist annotations of sTILs density.
  • To inform the development of a validation dataset for AI algorithms in breast cancer pathology.
  • To evaluate the variability in sTILs density estimates by pathologists.

Main Methods:

  • A pilot study involving 29 pathologists who provided sTILs density estimates.
  • Pathologists used both optical light microscopy and digital image viewing platforms.
  • Annotations were collected from 640 regions of interest (ROIs) across 64 breast cancer biopsy specimens.

Main Results:

  • 7373 sTILs density estimates were generated.
  • Variability in density estimates increased with higher mean densities.
  • Root mean square differences ranged from 4.46 to 26.25 across different density ranges.

Conclusions:

  • The pilot study highlights the need for improved technical workflows, annotation platforms, and agreement analysis methods for AI validation.
  • New statistical approaches are required to analyze inter-pathologist agreement.
  • The dataset and methods are publicly available to foster community feedback and guide future AI development.