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

Impact of Large Language Model Assistance on Radiologists' Diagnostic Performance for Brain Tumors by Experience Level.

Journal of clinical medicine·2026
Same author

Automated disc device for multiplexed extracellular vesicle isolation and labelling from liquid biopsies in cancer diagnostics.

Nature biomedical engineering·2026
Same author

Artificial intelligence-assisted automated measurement of maximum aortic diameter in the Korean national lung cancer screening CT program.

The British journal of radiology·2025
Same author

Explainable Machine Learning for Heat-Related Illness Prediction: An XGBoost-SHAP Approach Using Korean Meteorological Data.

Bioengineering (Basel, Switzerland)·2025
Same author

Hyperpolarized Carbon-13 Metabolic Imaging Differentiates Distinctive Molecular Phenotypes in Diffuse Midline Gliomas.

Molecules (Basel, Switzerland)·2025
Same author

Beyond the Image: How Acquisition Parameters Influence AI and Radiologists in Screening Mammography.

Radiology. Artificial intelligence·2025

Related Experiment Video

Updated: Aug 14, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

171

Predicting Underestimation of Invasive Cancer in Patients with Core-Needle-Biopsy-Diagnosed Ductal Carcinoma In Situ

Luu-Ngoc Do1, Hyo-Jae Lee2, Chaeyeong Im3

  • 1Department of Radiology, Chonnam National University, 42 Jebong-ro, Dong-gu, Gwangju 61469, Republic of Korea.

Tomography (Ann Arbor, Mich.)
|January 17, 2023
PubMed
Summary

Deep learning models can predict if ductal carcinoma in situ (DCIS) has an occult invasive component. This AI tool aids in distinguishing pure DCIS from upgraded DCIS, improving personalized treatment strategies.

Keywords:
deep learningductal carcinoma in situmachine learningmagnetic resonance imagingunderestimation of invasive cancer

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

6.9K
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

8.3K

Related Experiment Videos

Last Updated: Aug 14, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

171
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
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

8.3K

Area of Science:

  • Radiology
  • Oncology
  • Artificial Intelligence

Background:

  • Accurate preoperative differentiation between pure ductal carcinoma in situ (DCIS) and DCIS with an occult invasive component is crucial for appropriate patient treatment.
  • Histologic upgrade rates after initial diagnosis of DCIS by core-needle biopsy necessitate reliable predictive tools.

Purpose of the Study:

  • To evaluate the efficacy of deep learning models in differentiating pure DCIS from upgraded DCIS using preoperative MRI data.
  • To assess the potential of artificial intelligence in improving diagnostic accuracy for DCIS staging.

Main Methods:

  • Utilized preoperative axial dynamic contrast-enhanced magnetic resonance imaging (MRI) data from 352 DCIS lesions.
  • Trained, validated, and tested three distinct deep learning models, including a Recurrent Residual Convolutional Neural Network (RRCNN).
  • Focused analysis on Regions of Interest (ROIs) within the MRI scans.

Main Results:

  • The Recurrent Residual Convolutional Neural Network (RRCNN) achieved the highest performance.
  • Achieved an accuracy of 75.0% and an area under the receiver operating characteristic curve (AUC) of 0.796.
  • Demonstrated the potential of deep learning in predicting histologic upgrade.

Conclusions:

  • Deep learning models show promise as an assistive tool for predicting DCIS upgrade to invasive cancer.
  • This approach may facilitate personalized treatment strategies for patients with potentially underestimated invasive disease.
  • AI-powered image analysis can enhance preoperative assessment in breast cancer management.