An AI-powered algorithm shows promise in diagnosing and treating rare cancers swiftly, potentially outpacing traditional biopsies, according to a recent study. The research, a collaboration between the Royal Marsden NHS Foundation Trust and the Institute of Cancer Research in London, focused on leveraging AI to assess the aggressiveness of certain sarcomas.
Sarcoma is a rare cancer type originating in the body’s connective tissues, including fat, muscle, and nerves. In England alone, there are approximately 4,300 new cases each year, with retroperitoneal sarcoma being one of the challenging subtypes to diagnose and treat due to its location in the back of the abdomen.
The study employed AI to grade the aggressiveness of retroperitoneal sarcomas, comparing its performance to biopsies. The AI algorithm, developed from CT scans of 170 patients, was tested on 89 individuals from various centers in Europe and the US. The AI accurately assessed tumor aggressiveness 82% of the time, outperforming biopsies, which achieved 44% accuracy. Additionally, the AI distinguished between different sarcoma subtypes with an 84% accuracy rate, while radiologists managed only 35%.
The next stage of the research will involve applying the AI technology to patients with potential retroperitoneal sarcomas, with hopes for broader application in other cancer types.
The potential of this technology to expedite diagnoses and enable more personalized treatment is a cause for excitement, noted study lead Christina Messiou, a consultant radiologist at the Royal Marsden and professor in imaging for personalized oncology at the Institute of Cancer Research.
The research findings, published in The Lancet Oncology, open the door to the possibility of this approach benefiting various cancer types in the future. The study received funding from multiple organizations, including the Royal Marsden Cancer Charity and the Wellcome Trust.
Sarcoma UK’s chief executive, Richard Davidson, expressed optimism about the promising results, emphasizing the importance of early diagnosis for improving sarcoma survival rates. The UK Health and Social Care Secretary, Steve Barclay, highlighted the potential of AI in revolutionizing cancer care by expediting diagnoses and treatments.
The study’s findings align with Prime Minister Rishi Sunak’s announcement of a £100 million fund to advance AI-driven research into previously incurable diseases, aiming to address significant societal challenges, such as dementia and cancer vaccines.
Check out the latest news in our Global News section
Stay updated on environmental data and insights by following KI Data on Twitter