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 Experiment Video

Updated: Jul 15, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

Multicenter Validation of an Integrated DCE-MRI Radiomics, Deep Learning, and S-II Model for Predicting Axillary

Xinxin Lu1, Mengshen Wang2, Xiaohua Liu3

  • 1Department of Oncology, Maternal and Child Hospital, Ganzhou, Jiangxi Province, 341000, People's Republic of China.

Journal of Multidisciplinary Healthcare
|July 14, 2026
PubMed
Summary

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

Interpretable Dynamic MRI-ITH Model for Predicting Neoadjuvant Chemotherapy Response in Breast Cancer: A Multicenter Study.

Journal of multidisciplinary healthcare·2026
Same author

Thyroid dysfunction and risk of atrial fibrillation in patients with hypertrophic obstructive cardiomyopathy: a multicenter cohort study.

Frontiers in endocrinology·2026
Same author

Machine learning-based risk stratification identifies heart failure with preserved ejection fraction as an independent predictor of adverse outcomes in hypertrophic cardiomyopathy.

Scientific reports·2026
Same author

Spatiotemporal patterns and drivers of population and transport coordination in the Pearl River Delta.

Scientific reports·2025
Same author

Empirical research of urban land use eco-efficiency in the Pearl River Delta urban agglomeration.

Scientific reports·2025
Same author

IBSP Promotes Breast Cancer Bone Metastasis and Proliferation via BMP-SMAD Signaling Pathway.

Cancer reports (Hoboken, N.J.)·2024

This study developed an integrated model combining clinical data, imaging, and inflammation markers to predict breast cancer axillary lymph node metastasis (ALNM) preoperatively. The model demonstrated high accuracy and generalizability, aiding in non-invasive ALNM risk stratification.

Area of Science:

  • Oncology
  • Radiology
  • Medical Imaging

Background:

  • Accurate preoperative prediction of axillary lymph node metastasis (ALNM) is crucial for breast cancer staging and treatment planning.
  • Current methods for ALNM assessment often involve invasive procedures with potential complications.

Purpose of the Study:

  • To develop and validate an integrated, non-invasive model for predicting preoperative ALNM in breast cancer patients.
  • To combine clinical variables, systemic immune-inflammation index (SII), DCE-MRI radiomics score (RadScore), and deep learning score (DLScore) for enhanced prediction.

Main Methods:

  • A retrospective dual-center study included 212 patients (training) and 121 (validation).
  • DCE-MRI data were analyzed for radiomic features, and deep learning models were employed.
Keywords:
Breast canceraxillary lymph node metastasisdeep learningdynamic contrast-enhanced magnetic resonance imagingsystemic immune-inflammation index

Related Experiment Videos

Last Updated: Jul 15, 2026

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

  • An integrated model incorporating clinical data, SII, RadScore, and DLScore was developed and evaluated using ROC analysis, calibration, and decision curve analysis.

    • Main Results:

    • The integrated model achieved high predictive performance with an AUC of 0.972 (training) and 0.942 (validation).
    • The model demonstrated good calibration and superior net benefit compared to single-modality approaches.
    • Combining DCE-MRI phenotypes with systemic inflammatory status significantly improved predictive accuracy and external generalizability.

    Conclusions:

    • The integrated multimodal model offers a promising non-invasive tool for preoperative ALNM risk stratification in breast cancer.
    • This approach can aid in individualized preoperative axillary assessment, potentially reducing the need for invasive procedures.
    • Further prospective validation and interpretability analysis are recommended for clinical implementation.