Cancer Cervix, Cancer Head Neck, Cancer of Prostate
Conditions
Brief summary
The aim of this study is to look at whether an Artificial Intelligence (AI) based computer program can automate two components of the radiotherapy treatment pathway to a sufficient quality standard to enable its routine clinical use. The two components include the delineation (outlining) of anatomical areas that are at risk of tumour spread and at risk of radiation damage, and the definition of the position, size and shape of the radiation beams. The AI-based computer programs have been developed to perform tasks that would normally require direct human involvement by oncologists and medical physicists. Proposed advantages include improved treatment accuracy, as well as a reduction in the time (from weeks to minutes) and human resources needed to deliver radiotherapy, which this study will test.
Interventions
OTHERA web-based artificial intelligence (AI) auto-planning tool
The CT scan taken at the time of treatment planning is uploaded to a web server called the Radiotherapy planning assistant which automates the contouring of target organs and areas of high-risk disease as well as defining the size, shape and number of radiotherapy beams to treat the cancer. The final plan is downloaded to the local treatment planning system where the doses are recalculated and clinical peer review is undertaken before the plan can be used clinically. In this study patients will not be treated with the AI tool but the manual plan created by the local teams.
Sponsors
University College, London
National Institutes of Health (NIH)
Rising Tide Foundation
Medical Research Council
Tata Memorial Hospital
Tata Memorial Centre
University of Stellenbosch
King Hussein Cancer Center
University of Malaya
University Ghent
M.D. Anderson Cancer Center
Mount Vernon Cancer Centre at Mount Vernon Hospital
University of Cape Town
National Cancer Institute (NCI)
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
1. Consecutive patients with histologically confirmed head and neck cancers of the oropharynx, larynx, hypopharynx and nasopharynx (Stage I-III) that have given consent for radical radiotherapy. 2. Consecutive histologically confirmed primary cervical cancer patients (Stage IB-IIIB including pelvic node positive) that have given consent for radical radiotherapy. 3. Consecutive histologically confirmed primary prostate cancer patients (T1-4N0M0) that have given consent for radical radiotherapy. 4. Mental capacity to understand and consent to participate in the study. 5. Patients aged ≥18years.
Exclusion criteria
1. Patients requiring radiotherapy after curative surgery or surgery that is intended to remove as much of the tumour as possible. 2. Patients receiving palliative radiotherapy 3. Patients aged \< 18years.
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Proportion of radiotherapy treatment plans that have contours and dosimetry that meet pre-defined criteria for clinical acceptability | Prior to first treatment |
Secondary
| Measure | Time frame |
|---|---|
| comparison of time and human resource requirements between producing automated radiotherapy treatment plans using artificial intelligence and producing treatment plans using the standard manual pathway | radiotherapy plan preparation process pre treatment |
| Comparison of radiotherapy treatment costs using the artificial intelligence automated pathway and standard manual planning pathway | radiotherapy treatment plan preparation process and treatment interval |
Countries
India, Jordan, Malaysia, South Africa
Outcome results
None listed