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 4, 2026

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

Early Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer using a Longitudinal

Tian Jiang1, Xin Li2, Jiafei Shen3

  • 1Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou 310022, China (T.J., D.X., L.Z., D.O., L.W.).

Academic Radiology
|July 2, 2026
PubMed

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

Transrectal biplane ultrasound-guided transperineal biopsy for rectal and peri-rectal lesions: an 18-year retrospective analysis.

Quantitative imaging in medicine and surgery·2026
Same author

Multifocality as a marker of aggressiveness in medullary thyroid carcinoma: a retrospective cohort analysis of lymph node metastasis and recurrence.

The oncologist·2026
Same author

Prediction of HER2 changes post-neoadjuvant therapy based on fusion of ultrasound radiomics and clinicopathological features empowered by explainable AI: A multicenter study.

European journal of cancer (Oxford, England : 1990)·2025
Same author

BreastUS-Net: An Attention-Guided Dual-Branch Network With Feature Fusion for Fine-Grained Breast Tumor Classification in Ultrasound Imaging.

IEEE journal of biomedical and health informatics·2025
Same author

New Thyroid Imaging Reporting and Data System (TIRADS) Based on Ultrasonography Features for Follicular Thyroid Neoplasms: A Multicenter Study.

Ultrasound in medicine & biology·2025
Same author

Multimodal GPT model for assisting thyroid nodule diagnosis and management.

NPJ digital medicine·2025
Summary

A new ultrasound-based model accurately predicts pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer. This AI tool also enhances diagnostic accuracy for radiologists of all experience levels.

Area of Science:

  • Oncology
  • Radiology
  • Artificial Intelligence

Background:

  • Neoadjuvant chemotherapy (NAC) is a standard treatment for breast cancer.
  • Accurate early prediction of pathological complete response (pCR) to NAC is crucial for treatment optimization.
  • Current methods for assessing treatment response can be invasive or lack precision.

Purpose of the Study:

  • To evaluate a longitudinal ultrasound (US)-based deep learning (DL) stack-model for early pCR prediction in breast cancer patients undergoing NAC.
  • To assess the model's practicality in assisting radiologists of varying experience levels.
  • To investigate the combined performance of US imaging features and clinical factors for pCR prediction.

Main Methods:

  • Retrospective analysis of 974 breast cancer patients who received NAC across three institutions.
Keywords:
Breast cancerDeep learningNeoadjuvant chemotherapyUltrasound

Related Experiment Videos

Last Updated: Jul 4, 2026

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

  • US imaging performed before and after two cycles of NAC.
  • Development and testing of five DL models, including a combined model with clinical factors, using training (n=653) and testing (n=321) datasets.

    • Main Results:

    • The Swin Transformer model using stacked US features achieved high diagnostic performance (AUC).
    • The combined model integrating US features and clinical factors demonstrated superior pCR prediction performance with an AUC of 0.935.
    • Radiologists at all experience levels showed improved diagnostic performance when assisted by the combined model.

    Conclusions:

    • A longitudinal US-based DL model enables non-invasive, early prediction of pCR to NAC in breast cancer.
    • The developed model significantly enhances diagnostic assistance for radiologists, improving their ability to predict treatment response.
    • This approach offers a practical tool for optimizing breast cancer treatment strategies.