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

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

Towards Superhuman Imitation Learning for Sequential Head-and-Neck Cancer Treatment Decisions.

Filippo Corna1,2, Xinhua Zhang1, Guadalupe Canahuate3

  • 1Department of Computer Science, University Illinois Chicago, Chicago, Illinois, USA.

Proceedings of the ... Symposium on Applied Computing. Symposium on Applied Computing
|July 3, 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

Effect of perioperative targeted therapy duration on prognosis in patients with gastrointestinal stromal tumors undergoing neoadjuvant imatinib therapy: A nationwide retrospective study.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2026
Same author

Molecular classification identifies aggressive gastrointestinal stromal tumor subtype targetable by PARP inhibitors.

Cellular oncology (Dordrecht, Netherlands)·2026
Same author

Satellite-based analysis of precipitation across algeria's hydrographic watersheds (1983-2022) and their relationship with climate indices.

Scientific reports·2026
Same authorSame journal

Advancing Normal Tissue Complication Probability Modeling with Supervised Contrastive Learning for Predicting Osteoradionecrosis.

Proceedings of the ... Symposium on Applied Computing. Symposium on Applied Computing·2026
Same author

A competitive endogenous RNA network involving RiLinc6978 and miR9474-5p regulates fruit softening in tomato.

The Plant cell·2026
Same author

MMP7-Triggered mitophagy by regulating parkin-mediated ubiquitination of VDAC1 confers anoikis resistance in the epithelium of hyperplastic prostate.

Cell death & disease·2026
This summary is machine-generated.

This study introduces a new AI method for head and neck cancer treatment decisions. It uses a simulator and rewards AI policies for improving patient outcomes over expert performance.

Area of Science:

  • Oncology
  • Artificial Intelligence
  • Medical Informatics

Background:

  • Sequential treatment decisions in head and neck cancer are complex.
  • Current imitation learning approaches may simply replicate expert actions without optimizing outcomes.

Purpose of the Study:

  • To design a simulator-driven imitation learning approach for sequential treatment decisions in head and neck cancer.
  • To develop a method that optimizes clinical outcomes beyond expert performance.

Main Methods:

  • Utilized Superhuman Policy Gradient Optimization (SPGO) for policy learning.
  • Employed a clinical simulator to generate patient trajectories.
  • Incorporated an inverse-reinforcement-learning-inspired loss function to reward superior performance on clinical outcomes.
Keywords:
Head and Neck CancerHealthcare AIImitation LearningReinforcement LearningSubdominance Loss

Related Experiment Videos

Last Updated: Jul 4, 2026

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
10:25

Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation

Published on: September 2, 2025

Main Results:

  • The approach trains policies to outperform expert performance in a simulated environment.
  • The method focuses on improving key clinical outcomes like relapse rates and long-term toxicities.

Conclusions:

  • Simulator-driven imitation learning with outcome-based rewards offers a promising direction for optimizing cancer treatment strategies.
  • This approach has the potential to enhance patient care by developing AI that surpasses current expert decision-making in complex scenarios.