Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. Histopathologic Image-based Deep Learning Classifier For Predicting Platinum-based Treatment Responses In High-grade Serous Ovarian Cancer.
  1. Home
  3. Histopathologic Image-based Deep Learning Classifier For Predicting Platinum-based Treatment Responses In High-grade Serous Ovarian Cancer.

Related Experiment Video

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Histopathologic image-based deep learning classifier for predicting platinum-based treatment responses in high-grade

Byungsoo Ahn1, Damin Moon2, Hyun-Soo Kim3

  • 1Department of Pathology, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea.

Nature Communications
|May 18, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

A new tool, the Pathologic Risk Classifier for High-Grade Serous Ovarian Carcinoma (PathoRiCH), predicts patient response to platinum chemotherapy using histopathology images. This classifier offers improved prediction over existing molecular biomarkers for ovarian cancer treatment.

More Related Videos

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

6.8K
Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts
10:27

Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts

Published on: July 25, 2020

7.2K

Related Experiment Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
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

6.8K
Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts
10:27

Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts

Published on: July 25, 2020

7.2K

Area of Science:

  • Oncology
  • Pathology
  • Biomarker Development

Background:

  • Platinum-based chemotherapy is a primary treatment for high-grade serous ovarian carcinoma (HGSOC).
  • Predicting patient response to platinum chemotherapy is crucial for effective treatment selection.
  • Currently, no reliable biomarkers exist for predicting platinum-based treatment response in HGSOC.

Purpose of the Study:

  • To develop and validate a novel histopathology image-based classifier, Pathologic Risk Classifier for HGSOC (PathoRiCH), for predicting treatment response in HGSOC patients.
  • To evaluate the performance of PathoRiCH compared to existing molecular biomarkers.
  • To explore the integration of PathoRiCH with molecular biomarkers for enhanced risk stratification.

Main Methods:

  • Development of PathoRiCH, a classifier trained on histopathologic images from an in-house cohort (n=394).
  • Validation of PathoRiCH on two independent external cohorts (n=284 and n=136).
  • Assessment of PathoRiCH's predictive performance using platinum-free intervals and comparison with molecular biomarkers. Visualization and transcriptomic analysis were used to explain model decisions.

    • Main Results:

    • PathoRiCH successfully stratified patients into favorable and poor response groups with significantly different platinum-free intervals across all three cohorts.
    • PathoRiCH demonstrated superior predictive performance compared to current molecular biomarkers.
    • Combining PathoRiCH with molecular biomarkers further improved patient risk stratification.

    Conclusions:

    • PathoRiCH is a reliable and effective histopathology-based tool for predicting platinum chemotherapy response in HGSOC.
    • This novel classifier has the potential to transform the diagnostic pipeline for ovarian cancer.
    • PathoRiCH offers a promising foundation for developing innovative tools for personalized HGSOC treatment.