This website is intended for healthcare professionals


AI successfully used to grade rare cancer

Cancer Diagnosis
A new study has found that artificial intelligence (AI) could be twice as accurate in grading some sarcomas as a biopsy

A new study has found that artificial intelligence (AI) could be twice as accurate in grading some sarcomas as a biopsy. It is hoped that the findings mean AI could be used to help tailor treatment for patients with the rare cancers, which develop in the bones and soft tissue. Team Leader of the Molecular and Systems Oncology Team at The Institute of Cancer Research, Dr Paul Huang said, ‘this kind of technology has the potential to transform the lives of people with sarcoma - enabling personalised treatment plans tailored to the specific biology of their cancer.’

The study from The Royal Marsden NHS Foundation Trust and The Institute of Cancer Research focused on retroperitoneal sarcoma, which develops in the soft tissue of the back of the abdomen. The AI model accurately graded the aggressiveness of 82% of the tumours analysed, significantly better than a biopsy, which only graded 44% correctly. ‘One in six people with sarcoma cancer wait more than a year to receive an accurate diagnosis,’ said Sarcoma UK Chief Executive Richard Davidson. ‘The results of this study look very promising and we look forward to see how this research develops.’

Currently around 4,295 people in England are diagnosed with one of the 50 types of sarcoma each year. This means that diagnosis and treatment can be difficult, as clinicians may only see a handful of cases in their career. Richard Davidson said Sarcoma UK has long called for more research into the rare form of cancer to better diagnose and treat patients. He said, ‘people are more likely to survive sarcoma if their cancer is diagnosed early - when treatments can be effective and before the sarcoma has spread to other parts of the body.’

Through more effective diagnosis, researchers believe the AI technology will improve management of the disease. Consequently, it could be used as a tool to ensure high risk patients are identified and receive prioritised treatment. It is also hoped the technique could eventually be applied to more cancer types globally. However first author of the study, Dr Amani Arthur, explained this is only the start. ‘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.’