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

  1. Home
  3. Research Domains
  5. Biomedical And Clinical Sciences
  7. Oncology And Carcinogenesis
  9. Predictive And Prognostic Markers
  11. Advancing Ki67 Hotspot Detection In Breast Cancer: A Comparative Analysis Of Automated Digital Image Analysis Algorithms

Advancing Ki67 hotspot detection in breast cancer: a comparative analysis of automated digital image analysis algorithms

Mieke C Zwager1, Shibo Yu1, Henk J Buikema1

  • 1Department of Pathology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands.

Histopathology
|August 6, 2024

Related Experiment Videos

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers
11:34

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers

Published on: December 5, 2017

12.6K
Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment
06:05

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

7.3K
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.3K

View abstract on PubMed

Summary
This summary is machine-generated.

Automated digital image analysis (DIA) for Ki67 hotspot detection shows strong correlation with manual scoring and offers higher proliferation index (PI) values. Deep learning (DL) algorithms demonstrate superior clinical applicability over virtual dual staining (VDS) for improved Ki67 assessment.

Area of Science:

  • Oncology
  • Pathology
  • Biomedical Imaging

Background:

  • Manual Ki67 hotspot detection is subjective and limits clinical utility.
  • Digital image analysis (DIA) offers potential for objective Ki67 proliferation index (PI) assessment.
  • Automated algorithms could standardize Ki67 PI scoring in breast cancer.

Purpose of the Study:

  • To compare the clinical performance of DIA algorithms for Ki67 hotspot detection and scoring.
  • To evaluate virtual dual staining (VDS) and deep learning (DL) algorithms against manual assessment.
  • To determine the utility of automated DIA for Ki67 PI in invasive breast carcinomas.

Main Methods:

  • 135 invasive breast carcinoma tissue sections were stained for Ki67.
  • Two DIA algorithms (VDS and DL) automatically determined Ki67 hotspot PI.
Keywords:
Ki67 proliferation indexartificial intelligence (AI)breast cancerdigital image analysis (DIA)

Related Experiment Videos

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers
11:34

Building Up a High-throughput Screening Platform to Assess the Heterogeneity of HER2 Gene Amplification in Breast Cancers

Published on: December 5, 2017

12.6K
Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment
06:05

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

Published on: June 2, 2023

7.3K
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
07:32

Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis

Published on: April 12, 2024

1.3K
  • Manual assessment involved two observers using a validated scoring protocol.

    • Main Results:

    • Automated detection was feasible in 73% (VDS) and 100% (DL) of cases.
    • Automated methods yielded higher mean Ki67 PIs (38.3-39.6%) than manual consensus (28.8%).
    • High correlations were observed: manual vs. VDS (r=0.90) and manual vs. DL (r=0.95).

    Conclusions:

    • Automated Ki67 hotspot detection and analysis strongly correlate with manual scoring.
    • Deep learning (DL) algorithms show superior clinical applicability and correlation compared to VDS.
    • DL-based algorithms may enhance Ki67 PI cutoff clarity and clinical usability.
    hotspot