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

Identification of ischemic stroke risk in patients with left ventricular non-compaction using echocardiography, deep learning, and radiomics.

BMC medical imaging·2026
Same author

Predictive value of real-time shear wave elastography combined with serum thyroglobulin in thyroid cancer.

Cancer imaging : the official publication of the International Cancer Imaging Society·2026
Same author

Echocardiography Combined With Radiomics and Deep Transfer Learning to Diagnose Hypertrophic Cardiomyopathy and Other Etiologies of Left Ventricular Hypertrophy: A Multicenter Study Comparing the Performance With Echocardiologists.

Reviews in cardiovascular medicine·2025
Same author

Prediction of Major Adverse Cardiovascular Events in Patients with Hypertrophic Cardiomyopathy by Deep Learning and Radiomics.

Cardiology·2025
Same author

Clinical Study of Post-Chemotherapy Cardiotoxicity in Breast Cancer Patients Based on Ultrasound Radiomics.

Echocardiography (Mount Kisco, N.Y.)·2025
Same author

Analysis of Factors Related to Arteriovenous Fistula Expansion in Non-Diabetic Maintenance Hemodialysis Patients Based on Vascular Ultrasound.

Alternative therapies in health and medicine·2025

Related Experiment Video

Updated: Jul 18, 2026

Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound
12:23

Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound

Published on: August 14, 2012

Establishing a Multimodal Model for Predicting Lymphovascular Invasion in Breast Cancer Using Deep Transfer Learning

Miaomiao He, Feifei Zhu, Feng Jiang

    Oncology Research and Treatment
    |July 10, 2026
    PubMed
    Summary

    This study developed a multimodal model using ultrasound and DCE-MRI to predict lymphovascular invasion (LVI) in breast cancer, achieving high accuracy in external validation. The model shows promise for improving diagnostic accuracy in clinical practice.

    Keywords:
    Breast cancerDeep Transfer LearningLymphovascular InvasionUltrasound Magnetic Resonance Imaging.

    More Related 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

    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

    Related Experiment Videos

    Last Updated: Jul 18, 2026

    Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound
    12:23

    Multi-modal Imaging of Angiogenesis in a Nude Rat Model of Breast Cancer Bone Metastasis Using Magnetic Resonance Imaging, Volumetric Computed Tomography and Ultrasound

    Published on: August 14, 2012

    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

    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

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence in Medicine
    • Oncology

    Background:

    • Lymphovascular invasion (LVI) is a critical prognostic factor in breast cancer.
    • Accurate prediction of LVI is essential for guiding treatment decisions.

    Purpose of the Study:

    • To develop and validate a multimodal deep transfer learning (DTL) model integrating ultrasound (US) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting LVI in breast cancer.
    • To assess the diagnostic performance and clinical utility of the proposed multimodal model.

    Main Methods:

    • A retrospective study of 326 breast cancer patients utilizing preoperative US and DCE-MRI data.
    • A multimodal fusion feature set was created from intratumoral regions using DTL.
    • A Multi-Layer Perceptron (MLP) classifier, optimized with LASSO feature selection, was developed and validated internally and externally.

    Main Results:

    • The multimodal MLP model achieved high AUC values: 0.987 (training), 0.967 (internal validation), and 0.942 (external validation).
    • The model significantly outperformed models based on single imaging modalities (US or DCE-MRI alone).
    • SHapley Additive exPlanations (SHAP) were used for model interpretability.

    Conclusions:

    • Multimodal models integrating DTL features from US and DCE-MRI can accurately predict LVI in breast cancer.
    • The developed model demonstrates significant potential for enhancing diagnostic accuracy and robustness in clinical LVI assessment.