Integrated AI-enabled platform for adaptive radiotherapy dose planning
Lead Participant:
MIRADA MEDICAL LIMITED
Abstract
"External Beam Radiotherapy (RT) is a cornerstone of modern cancer treatment, utilized on its own or in combination with surgery and/or chemotherapy. During RT, high energy radiation, generated within a linear accelerator, is directed at a tumour, thereby destroying it, but also inevitably irradiating nearby healthy tissue. It is therefore necessary to carefully plan any RT to maximise the tumour dose while minimising the dose to the healthy tissue. In this process, known as RT planning, teams of clinical experts spend a great deal of time developing a treatment plan prior to its administration.
Typically, a course of therapy lasts 4-6 weeks during which the patient's anatomy may change significantly rendering the plan sub-optimal. Indeed, such changes might result in either too little radiation being delivered to the tumour and/or too much to surrounding tissue. Ideally, the validity of the treatment plan is monitored during therapy and the plan changed as required; this concept is known as Adaptive Radiotherapy (ART).
Multiple studies have demonstrated the clinical benefits of ART, but it is rarely performed in routine clinical practice due to associated increased workload. The latest radiotherapy treatment machines can perform 3D imaging for each daily fraction of the treatment. While today such imaging is predominately used to ensure correct patient positioning there is an increasing desire to fully exploit this capability for monitoring for ART.
The challenge to overcome is how to use this information efficiently. Manual review of the imaging is too labour intensive for clinical implementation. Therefore, there is a need for a system to automatically review all available imaging and identify those patients who may benefit from adaptive re-planning.
This project seeks to develop a proof-of-concept to demonstrate that a substantially automated ART monitoring system is practical for clinical use while also demonstrating integration with market-leading clinical solutions for dose calculation and personalized treatment planning."
Typically, a course of therapy lasts 4-6 weeks during which the patient's anatomy may change significantly rendering the plan sub-optimal. Indeed, such changes might result in either too little radiation being delivered to the tumour and/or too much to surrounding tissue. Ideally, the validity of the treatment plan is monitored during therapy and the plan changed as required; this concept is known as Adaptive Radiotherapy (ART).
Multiple studies have demonstrated the clinical benefits of ART, but it is rarely performed in routine clinical practice due to associated increased workload. The latest radiotherapy treatment machines can perform 3D imaging for each daily fraction of the treatment. While today such imaging is predominately used to ensure correct patient positioning there is an increasing desire to fully exploit this capability for monitoring for ART.
The challenge to overcome is how to use this information efficiently. Manual review of the imaging is too labour intensive for clinical implementation. Therefore, there is a need for a system to automatically review all available imaging and identify those patients who may benefit from adaptive re-planning.
This project seeks to develop a proof-of-concept to demonstrate that a substantially automated ART monitoring system is practical for clinical use while also demonstrating integration with market-leading clinical solutions for dose calculation and personalized treatment planning."
Lead Participant | Project Cost | Grant Offer |
|---|---|---|
| MIRADA MEDICAL LIMITED | £773,466 | £ 386,733 |
People |
ORCID iD |
| Mark Gooding (Project Manager) |