AI-Based Radiotherapy Planning Evaluated Across Multiple Countries
A multinational study has demonstrated the potential of an artificial intelligence (AI) tool to automate key stages of radiotherapy planning for cervical and prostate cancer, according to results presented at the European Society for Radiotherapy and Oncology (ESTRO 2026) congress in Stockholm.
The study, known as ARCHERY, was led by researchers from University College London (UCL) and the London School of Hygiene & Tropical Medicine (LSHTM). It evaluated whether AI-generated radiotherapy treatment plans could meet international clinical standards across a range of healthcare settings.
Radiotherapy planning is a complex and time-intensive process that typically requires input from radiation oncologists and medical physicists. The challenge is particularly acute in low- and middle-income countries, where workforce shortages and limited radiotherapy capacity can delay treatment.
Automating Key Planning Tasks
The AI software was designed to automate two critical components of radiotherapy planning:
- Identification of treatment target structures on CT scans
- Optimization of radiation beam configurations
These processes traditionally require significant specialist input and can take many hours over several weeks to complete. According to the researchers, the technology aims to accelerate treatment preparation while maintaining clinically acceptable plan quality.
Results from the ARCHERY Trial
The ARCHERY trial enrolled more than 1,000 patients with cervical, prostate, and head and neck cancers at hospitals in:
- India
- South Africa
- Jordan
- Malaysia
Researchers assessed whether AI-generated plans met predefined quality standards suitable for routine clinical use.
The results showed:
- High-quality plans in more than 95% of cervical cancer cases
- High-quality plans in 85% of prostate cancer cases
- Head and neck cancer results are expected later in 2026
The study findings suggest that automated planning may be applicable across a variety of healthcare environments, including resource-constrained settings.
Addressing Global Radiotherapy Challenges
The researchers highlighted the particular relevance of the technology for cervical cancer treatment. According to the study, 94% of cervical cancer deaths occur in low- and middle-income countries, where access to radiotherapy remains limited. The investigators noted that only 10% of patients requiring radiotherapy receive it in low-income countries and approximately 40% in middle-income countries.
The study team reported that the AI platform reduced radiotherapy planning time to just over one hour.
“These results show that for cervical cancer, this AI technology achieves a very high standard, supporting its routine use in hospitals globally. In doing so, it can help meet the World Health Organization's cervical cancer elimination initiative for treatment. It can also be used to support the delivery of prostate cancer treatments in any country setting,” said Professor Ajay Aggarwal, chief investigator, London School of Hygiene & Tropical Medicine and Guy's & St Thomas' NHS Trust, London.
“In a usual workflow, planning radiotherapy can take many hours over several weeks, as it depends on the availability of specialized staff. This AI technology can reduce that time to just over an hour. This is important as it has the potential to reduce waiting times and widen access to this life-saving treatment,” Professor Aggarwal added.
The researchers believe the technology could help address workforce shortages and improve access to radiotherapy services worldwide.
Source: University College London
