Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 27, 2026

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

Foundation Model-Driven Regions of Interest Classification and Renaming in Cancer Radiotherapy: A Customizable,

Dong Yang^1,2, Mingjun Lei³, Qiangxing Yang⁴

¹Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai, China.

JCO Clinical Cancer Informatics

|June 25, 2026

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

Visit-to-Visit Blood Pressure Variability and Cerebral White Matter Lesion Progression: A Pooled Individual Patient Data Analysis of 2 Trials.

Neurology·2026

Same author

Dual-Pathway Catalytic Proton Exchange in Water Distillation Enables Record Detritiation of Tritiated Water.

Environmental science & technology·2026

Same author

Analysis of clinical characteristics of 38 patients with dextrocardia: An observational study.

Medicine·2026

Same author

Blood Pressure Variability and Outcomes Across Antihypertensive Regimens.

Hypertension (Dallas, Tex. : 1979)·2026

Same author

A precision tumor growth model integrating time-resolved flow cytometry: predicting fractionation efficacy and immunotherapy scheduling.

Physics in medicine and biology·2026

Same author

Two distinct patterns of progression of sporadic cerebral small vessel disease.

International journal of stroke : official journal of the International Stroke Society·2026

This study developed an automated workflow using AI to standardize cancer radiotherapy region naming, improving accuracy and interoperability across institutions. The system achieved high accuracy in classifying and renaming regions, enhancing clinical workflows.

Area of Science:

Medical Physics
Artificial Intelligence in Healthcare
Radiotherapy Oncology

Background:

Inconsistent naming of regions of interest (ROIs) in radiotherapy planning hinders interoperability and automation.
Standardization is crucial for reproducible and efficient cancer treatment workflows.

Purpose of the Study:

To develop and evaluate a foundation model-based workflow for automated ROI classification and standardization.
To align ROI nomenclature with AAPM Task Group 263 (TG-263) standards while allowing institutional customization.

Main Methods:

A four-stage pipeline integrating large language models (LLMs) and a Contrastive Language-Image Pretraining (CLIP) model was created.
The workflow performs anatomic site classification, ROI type classification, standardization, and laterality verification.

More Related Videos

Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources

Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources

Published on: October 6, 2023

Related Experiment Videos

Last Updated: Jun 27, 2026

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources

Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources

Published on: October 6, 2023

Evaluated on 600 patients across three institutions and five disease sites using DICOM RTSTRUCT and CT data.

Main Results:

Achieved 99.12% accuracy for ROI type classification and 97.92% for renaming.
High performance was consistent across institutions and disease sites.
CLIP-based laterality verification successfully corrected all errors in targeted testing.

Conclusions:

Foundation language models and vision-language modules can automate ROI classification and naming in radiotherapy.
The proposed workflow is retraining-free, customizable, and robust for standardizing cancer radiotherapy.
This approach enhances clinical workflow efficiency and reduces ambiguity in radiotherapy planning.