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: Nov 11, 2025

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

8.5K

Predicting treatment response from longitudinal images using multi-task deep learning.

Cheng Jin1, Heng Yu1, Jia Ke2,3

  • 1Department of Radiation Oncology, Stanford University School of Medicine, Stanford, CA, USA.

Nature Communications
|March 26, 2021
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

A Case-Based Guide: Demonstrating the Reirradiation Collaborative Group (ReCOG) Consensus for Dosimetric Assessment and Reporting in Reirradiation.

Practical radiation oncology·2026
Same author

Advancing radiation oncology care in Ukraine during the war: impact of international observerships on professional development and clinical practice.

Frontiers in oncology·2026
Same author

PKM2 Lactylation Promotes Colorectal Cancer Vasculogenic Mimicry and Bevacizumab Resistance by Facilitating FOSL1 Super-enhancer Formation.

Cancer research·2026
Same author

Neoadjuvant Chemotherapy With CAPOX Versus Chemoradiation for Locally Advanced Rectal Cancer With Uninvolved Mesorectal Fascia (CONVERT): Final Results of a Phase III Trial.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·2026
Same author

AI-enabled virtual spatial proteomics from histopathology for interpretable biomarker discovery in lung cancer.

Nature medicine·2026
Same author

Database-calibrated toxicity values for human health assessment based on existing toxicology data for one thousand chemicals.

Journal of toxicology and environmental health. Part B, Critical reviews·2025
Same journal

Chlorinated VSLSs Surpass HCFCs in CFC-11-Equivalent Emissions for Ozone Layer Depletion in China.

Nature communications·2026
Same journal

Author Correction: Charge transfer in triphenylamine-tetrazine covalent organic frameworks for solar-driven hydrogen peroxide production.

Nature communications·2026
Same journal

Vegetation browning patterns under compound soil and atmospheric dryness in northern permafrost ecosystems.

Nature communications·2026
Same journal

Voltage imaging of CA1 pyramidal cells and SST+ interneurons reveals stability and plasticity mechanisms of spatial firing.

Nature communications·2026
Same journal

Radical-omics reveals the hydrogen-abstraction pathway of isoprene oxidation.

Nature communications·2026
Same journal

Toughening elastomer via sequentially activated multi-pathway energy dissipation.

Nature communications·2026
See all related articles
This summary is machine-generated.

This study introduces a deep learning model for predicting rectal cancer treatment response using MRI scans. The AI model accurately predicts pathologic complete response, improving upon current imaging metrics.

Area of Science:

  • Oncology
  • Radiology
  • Artificial Intelligence

Background:

  • Radiographic imaging is standard for assessing solid tumor treatment response, but current metrics often fail to predict biological response accurately.
  • Predicting pathologic complete response (pCR) in rectal cancer after neoadjuvant chemoradiotherapy (nCRT) is crucial for guiding treatment decisions.

Purpose of the Study:

  • To develop and validate a multi-task deep learning (MTDL) approach for simultaneous tumor segmentation and response prediction from medical imaging.
  • To improve the prediction accuracy of pathologic complete response in rectal cancer patients undergoing nCRT.

Main Methods:

  • A novel MTDL framework utilizing Siamese subnetworks was designed for integrated analysis of pre- and post-treatment magnetic resonance imaging (MRI) scans.
  • The model was trained on 2568 MRI scans from 321 rectal cancer patients and validated across multiple institutions.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.1K

Related Experiment Videos

Last Updated: Nov 11, 2025

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

8.5K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.1K
  • The approach integrates multi-scale feature representations for in-depth comparison of longitudinal imaging data.

    • Main Results:

    • The imaging-based MTDL model achieved high prediction accuracy, with Area Under the Curve (AUC) of 0.95 and 0.92 in two independent validation cohorts.
    • Integration of the imaging model with blood-based tumor markers further enhanced prediction accuracy to an AUC of 0.97.
    • The model demonstrated robust performance in predicting pathologic complete response after neoadjuvant chemoradiotherapy.

    Conclusions:

    • The developed MTDL approach effectively captures dynamic information from longitudinal imaging for accurate treatment response prediction in rectal cancer.
    • This AI-driven method shows potential for broad applications in cancer screening, treatment monitoring, and surveillance.
    • The study highlights the power of deep learning in integrating imaging and clinical data for improved oncologic outcomes.