Published: 01 November 2023
Artificial intelligence is almost twice as accurate as a biopsy at grading the aggressiveness of some sarcomas, according to research part-funded by the NIHR’s Biomedical Research Centre at The Royal Marsden.
What is sarcoma?
Soft tissue sarcoma is a type of cancer that develops in the body’s tissues including:
- Fat
- Muscles
- Nerves
- Blood
- Lymph vessels
Each year approximately 4,000 people in England are told they have sarcoma cancer. There are 50 different types of sarcoma. The study focused on retroperitoneal sarcoma which develops in the back of the abdomen and is hard to diagnose and treat.
What did the researchers do?
Researchers used the CT scans of 170 Royal Marsden patients with the two most common forms of retroperitoneal sarcoma. They created an algorithm, which was then tested on 90 patients from centres across Europe and the US.
It was a retrospective study meaning the researchers looked at patients who they had already treated to build the model and then looked at past patients to see how effective the technology would have been. The technology is capable of analysing differences in the medical images which the human eye can not see.
What were the results?
The AI and the biopsy predicted how aggressive a tumour was likely to be. The researchers looked at the actual patient outcomes and found:
- 82% of the tumours analysed by AI were accurately graded
- 44% were correctly graded using a biopsy.
There are two different types of retroperitoneal sarcoma. The researchers looked at how effective the AI was at distinguishing the difference.
- The AI was 84% accurate at predicting the type
- The radiologists were 65% accurate at predicting the type
Read more about the classification model used and results in The Lancet.
What are the benefits of this approach?
The normal approach - a biopsy - is an invasive procedure so using this new technology could mean:
- quicker diagnosis
- more accurate diagnosis
- effective way of grading tumours
- diagnose of subtypes of the disease
- tailoring treatment to the patient’s disease
- improve management of the disease
- better outcomes for patients
The tool could help doctors:
- identify high-risk patients and amplify treatment
- spare low-risk patients unnecessary treatments, reducing the need for follow-up scans and hospital visits
Because sarcomas are relatively rare the tool could help to support doctors who may not have much experience of the disease. The results are exciting because researchers believe the technique could be applied to other cancer types.
The Royal Marsden NHS Foundation Trust and The Institute of Cancer Research (ICR) ran the study. It was funded by the NIHR Biomedical Research Centre at The Royal Marsden and the ICR, Wellcome Trust, the EORTC Soft Tissue and Bone Sarcoma Group, and with support from The Royal Marsden Cancer Charity.
First author Dr Amani Arthur, Registrar at The Royal Marsden NHS Foundation Trust and Clinical Research Fellow at The ICR, London, said:
“There is an urgent need to improve the diagnosis and treatment of patients with retroperitoneal sarcoma, who currently have poor outcomes. The disease is very rare - clinicians may only see one or two cases in their career – which means diagnosis can be slow. This type of sarcoma is also difficult to treat as it can grow to large sizes and, due to the tumour’s location in the abdomen, involve complex surgery.
“Through this early research, we’ve developed an innovative AI tool using imaging data that could help us more accurately and quickly identify the type and grade of retroperitoneal sarcomas than current methods. This could improve patient outcomes by helping to speed up diagnosis of the disease, and better tailor treatment by reliably identifying the risk of each patient’s disease.
“In the next phase of the study, we will test this model in clinic on patients with potential retroperitoneal sarcomas to see if it can accurately characterise their disease and measure the performance of the technology over time.”
Health and Social Care Secretary Steve Barclay said:
“AI has the potential to revolutionise cancer care by ending invasive procedures and speeding up diagnoses and treatment, which could be the difference between life and death.
“The government is investing more than £1.2 billion a year into research to unlock the next generation of treatments and diagnostic tools, and it’s fantastic to see this ground breaking technology being embraced and benefitting NHS patients.”
Study lead Professor Christina Messiou, Digital Theme lead at the NIHR BRC at The Royal Marsden and the ICR and Consultant Radiologist at The Royal Marsden NHS Foundation Trust and Professor in Imaging for Personalised Oncology at The Institute of Cancer Research, London, said:
“This is the largest and most robust study to date that has successfully developed and tested an AI model aimed at improving the diagnosis and grading of retroperitoneal sarcoma using data from CT scans. Due to the rarity of the disease, this was a global effort and I’m immensely proud and thankful to the team.
“We’re incredibly excited by the potential of this state-of-the-art technology, which could lead to patients having better outcomes through faster diagnosis and more effectively personalised treatment. As patients with retroperitoneal sarcoma are routinely scanned with CT, we hope this tool will eventually be used globally, ensuring that not just specialist centres – who see sarcoma patients every day – can reliably identify and grade the disease.
“In the future, this approach may help characterise other types of cancer, not just retroperitoneal sarcoma. Our novel approach used features specific to this disease, but by refining the algorithm, this technology could one day improve the outcomes of thousands of patients each year.”
Find out more about the work of NIHR The Royal Marsden Biomedical Research Centre