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

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 multicenter retrospective analysis of canine idiopathic epilepsy in China.

Frontiers in veterinary science·2026

Same author

Functionalized Fluorescent Nanodiamonds Reveal Therapeutic Protein Clearance Through ENDOTAC Linked to AUTOTAC.

Advanced healthcare materials·2026

Same author

Efficacy of NEPA for prevention of chemotherapy induced nausea and vomiting in head and neck cancer patients receiving cisplatin-based chemotherapy.

European journal of clinical pharmacology·2026

Same author

A glimpse into the future of model-informed drug discovery and development.

Advanced drug delivery reviews·2026

Same author

Individualized Prediction of Radiation Pneumonitis Using RP-GAN: Leveraging Global Lung Features and Explainable Artificial Intelligence.

Technology in cancer research & treatment·2026

Same author

The Emerging Role of N-Lactoyl-Phenylalanine (Lac-Phe) in Metabolic Regulation and Disease: From Exercise-Induced Metabolite to Therapeutic Candidate.

Antioxidants (Basel, Switzerland)·2026

Search research articles

Related Experiment Video

Updated: Jan 9, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Dose-Guided Hybrid AI Model with Deep and Handcrafted Radiomics for Explainable Radiation Dermatitis Prediction in

Tsair-Fwu Lee^1,2,3, Ling-Chuan Chang-Chien¹, Lawrence Tsai¹

¹Medical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan.

|December 11, 2025

Summary

This summary is machine-generated.

A new hybrid AI model accurately predicts radiation dermatitis in breast cancer patients undergoing VMAT. This approach integrates deep learning radiomics, clinical data, and dose metrics for improved risk stratification and personalized prevention.

Keywords:

breast cancer deep learning radiomics ensemble learning explainable artificial intelligence radiation dermatitis volumetric modulated arc therapy

More Related Videos

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

Related Experiment Videos

Last Updated: Jan 9, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Using Computer-based Image Analysis to Improve Quantification of Lung Metastasis in the 4T1 Breast Cancer Model

Published on: October 2, 2020

Area of Science:

Oncology
Medical Imaging
Artificial Intelligence

Background:

Radiation dermatitis (RD) is a common side effect of breast cancer radiotherapy.
Accurate prediction of RD risk is crucial for personalized prevention strategies.
Volumetric Modulated Arc Therapy (VMAT) is a widely used radiotherapy technique.

Purpose of the Study:

To develop and validate a hybrid artificial intelligence (AI) model for predicting Grade ≥ 2 radiation dermatitis (RD) in breast cancer patients treated with VMAT.
To integrate deep learning radiomics (DLR), handcrafted radiomics (HCR), clinical features, and dose-volume histogram (DVH) parameters for enhanced prediction accuracy.
To improve early identification of high-risk individuals for personalized prevention.

Main Methods:

A retrospective analysis of 148 breast cancer patients treated with VMAT.
Extraction of HCR features using PyRadiomics and DLR features from CT images using a VGG16 network.
Development of predictive models using logistic regression, random forest, gradient boosting, and stacking ensemble (SE) methods.
Assessment of model explainability using SHapley Additive exPlanations (SHAPs) and gradient-weighted class activation mapping (Grad-CAM).

Main Results:

The hybrid AI model integrating DLR, clinical, and DVH features achieved the highest predictive performance (AUC = 0.76).
Deep learning radiomics models outperformed handcrafted radiomics models (AUC = 0.72 vs. 0.66).
Stacking ensemble methods consistently improved performance over single classifiers.
SHAP analysis identified DLR features as key predictors, and Grad-CAM highlighted high-dose subcutaneous regions.

Conclusions:

The proposed hybrid AI framework provides accurate and explainable predictions of Grade ≥ 2 RD after VMAT.
The model facilitates reliable high-risk stratification for breast cancer patients.
This approach holds potential clinical utility for personalized radiotherapy treatment planning and prevention.