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

White matter microstructural abnormalities in neurological poste-acute sequelae of coronavirus disease: Imaging signatures consistent with persistent neuroinflammation.

Brain, behavior, & immunity - health·2026
Same author

Analysis of factors affecting lesion or HPV clearance rate after photodynamic therapy of persistent cervical intraepithelial neoplasia grade 1.

Photodiagnosis and photodynamic therapy·2026
Same author

Lipemic Aqueous Humor in Hyperlipidemia and Diabetes Mellitus: A Case Report.

Case reports in ophthalmological medicine·2026
Same author

Assessing glymphatic-associated fluid dynamics in psychiatric disorders: evidence from neuroimaging - a review.

Psychoradiology·2025
Same author

Effects of Gossypol Exposure on Ovarian Reserve Function: Comprehensive Risk Assessment Based on TRAEC Strategy.

Toxics·2025
Same author

Cross-field strength and multi-vendor reliability of MagDensity for MRI-based quantitative breast density analysis.

PloS one·2025

Related Experiment Video

Updated: Oct 1, 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

7.0K

Preoperative prediction of lymph node metastasis using deep learning-based features.

Renee Cattell1,2, Jia Ying1, Lan Lei3,4

  • 1Department of Biomedical Engineering, Stony Brook University, NY, 11794, Stony Brook, USA.

Visual Computing for Industry, Biomedicine, and Art
|March 7, 2022
PubMed
Summary

Deep learning-based (DLB) features show improved prediction of breast cancer sentinel lymph node metastasis compared to conventional radiomics. DLB models demonstrate better generalizability, especially on images with different resolutions, aiding in cancer staging.

Keywords:
Breast cancerDeep learningLymph node metastasisPrediction modelRadiomics

More Related Videos

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

225
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

8.4K

Related Experiment Videos

Last Updated: Oct 1, 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

7.0K
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

225
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

8.4K

Area of Science:

  • Medical Imaging
  • Oncology
  • Artificial Intelligence

Background:

  • Lymph node involvement is a key predictor of breast cancer recurrence.
  • Accurate, non-invasive assessment of nodal status is crucial for cancer staging and treatment planning.
  • Radiomics shows promise for pre-operative prediction of sentinel lymph node (SLN) metastasis but can be sensitive to image acquisition parameters.

Purpose of the Study:

  • To develop and compare a deep learning-based (DLB) prediction model against conventional radiomics (CR) for pre-operative SLN metastasis detection.
  • To evaluate the generalizability of DLB features versus CR features on an independent test set with dissimilar image resolution.

Main Methods:

  • Utilized dynamic contrast-enhancement MRI from 198 patients (67 with positive SLNs).
  • Compared two methods: conventional radiomics (CR) and DLB features using pre-trained VGG-16.
  • Assessed model performance on validation and independent test sets with varying in-plane resolutions (0.7x0.7 mm² vs 0.78x0.78 mm²).

Main Results:

  • In the validation set (similar resolution), the DLB model achieved 83% accuracy versus 80% for CR.
  • In the independent test set (dissimilar resolution), the DLB model significantly outperformed CR with 77% accuracy compared to 71%.

Conclusions:

  • Deep learning-based features demonstrate superior predictive performance for SLN metastasis compared to conventional radiomics.
  • DLB models exhibit enhanced generalizability, particularly across datasets with varying image resolutions, suggesting potential for more robust clinical application.