Related Experiment Video
Updated: Jul 4, 2026
05:18
Radiation Planning Assistant - A Web-based Tool to Support High-quality Radiotherapy in Clinics with Limited Resources
Published on: October 6, 2023
Artificial Intelligence for Prognostic Modelling and Adaptive Treatment Monitoring in Radiation Oncology
Krishna Chidrawar1, Sandeep Kaur Toor2, Shubham Gupta3
1Department of Radiology, Durga Diagnostic Centre, Maharashtra University of Health Sciences, Nashik, IND.
Cureus
|July 3, 2026
Summary
Artificial intelligence (AI) enhances radiation oncology by improving outcome prediction and treatment monitoring. Wider adoption requires robust validation and standardized clinical integration for AI decision support.
Area of Science:
- Oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Artificial intelligence (AI) shows promise in radiation oncology for predicting patient outcomes and monitoring treatment response.
- Clinical integration of AI is limited due to inconsistent studies, lack of standardized methods, and insufficient real-world validation.
Purpose of the Study:
- To review the current applications of AI in radiation oncology, including prognosis, adaptive radiotherapy, treatment response assessment, and toxicity prediction.
- To explore AI's role in supporting areas like cancer screening and radiological diagnosis that inform treatment decisions.
Main Methods:
- A structured literature search from 2015 to 2025 was conducted across major biomedical databases.
- Focus on radiomics, machine learning, deep learning, response modeling, and adaptive treatment planning.
- Studies were evaluated based on design, validation methods, and clinical outcomes.
Main Results:
- AI demonstrates potential to enhance risk prediction, automate tumor segmentation, monitor treatment changes, and detect toxicity earlier than conventional methods.
- Current evidence indicates a need for external validation and multicenter data for many AI models.
- Challenges include AI model interpretability and integration with existing clinical systems.
Conclusions:
- AI can personalize radiation dose, facilitate timely treatment adjustments, and optimize resource allocation.
- Further improvements in prediction can be achieved by integrating imaging, genomic, and radiation dose data.
- Wider AI adoption necessitates stronger validation, standardized workflows, and clear governance, positioning AI as a clinical decision-support tool.
