London (Parliament Politic Magazine) – Artificial intelligence demonstrates a significant enhancement in evaluating the aggressiveness of a rare form of cancer from scans, as indicated by a recent study. AI, with its capability to discern subtle details imperceptible to the human eye, achieved an accuracy rate of 82%, surpassing the 44% accuracy of conventional laboratory analysis.
Scientists affiliated with the Royal Marsden Hospital and Institute of Cancer Research believe that this advancement holds the potential to enhance treatment outcomes, benefiting a substantial number of patients annually. Moreover, they express enthusiasm about AI’s prospects in the early detection of various other forms of cancer.
Microscopic Examination of Cancerous Tissue
AI is already demonstrating immense potential in the diagnosis of breast cancer and streamlining treatment timelines. Through the ingestion of extensive data, computers can be educated to discern underlying patterns, enabling them to offer predictions, address challenges, and further refine their capabilities by learning from their errors.
Professor Christina Messiou, who serves as a consultant radiologist at The Royal Marsden NHS Foundation Trust and holds the position of professor specializing in personalized oncology imaging at The Institute of Cancer Research in London, made this statement. “We’re incredibly excited by the potential of this state-of-the-art technology.” “It could lead to patients having better outcomes, through faster diagnosis and more effectively personalized treatment.”
The researchers, as reported in Lancet Oncology, employed a method known as radiomics to uncover imperceptible indicators of retroperitoneal sarcoma, a type of cancer that originates in the connective tissue at the rear of the abdomen. They analyzed scans from 170 patients to identify these markers.
Subsequently, the AI algorithm utilized this data to evaluate the aggressiveness of tumors in 89 additional patients from hospitals in Europe and the United States. The AI’s accuracy in this evaluation surpassed that of biopsies, which involve microscopic examination of a small section of cancerous tissue.
When Tina McLaughlan, a dental nurse, received her sarcoma diagnosis in June of the previous year after experiencing stomach pain, medical professionals employed computerized-tomography (CT) scan images to identify the issue. Due to potential risks, they opted against a needle biopsy. Tina, aged 65 and residing in Bedfordshire, underwent a surgical procedure to remove the tumor and presently undergoes scans at the Royal Marsden every three months. Although she was not part of the AI trial, she expressed to BBC News her belief that the technology would be beneficial for other patients.
“You go in for the first scan and they can’t tell you what it is – they didn’t tell me through all my treatment, until the histology, post-op, so it would be really useful to know that straight away,” Miss McLaughlan said. “Hopefully, it would lead to a quicker diagnosis.” Soft tissue sarcoma arises within the body’s connective tissues, including fat, muscles, and blood vessels. This condition is relatively uncommon, with approximately 4,295 new cases reported annually in England, encompassing over 50 different subtypes.
Approximately 4,300 individuals in England receive a diagnosis of this particular cancer annually. Professor Messiou envisions a future where this technology can be applied globally, allowing high-risk patients to receive targeted treatment while sparing those at low risk from unnecessary treatments and follow-up scans.
Dr. Paul Huang, associated with the Institute of Cancer Research in London, emphasized the transformative potential of this technology for sarcoma patients. He highlighted the capacity for personalized treatment plans tailored to the unique biological characteristics of each patient’s cancer. He believes “It’s great to see such promising findings.”
The commercial sectors, especially the healthcare technology industry, stand to gain significant benefits from this breakthrough. By integrating fast and non-invasive diagnostic tools like this into healthcare systems, it becomes possible to reduce costs and elevate the quality of patient care.
The study featured in The Lancet Oncology highlights the AI algorithm’s superior accuracy, which is double that of traditional biopsy methods for grading the aggressiveness of certain sarcomas. It’s worth noting that biopsies, while the standard approach, can be invasive and may not consistently provide a completely accurate assessment. This innovation not only accelerates the diagnosis of specific sarcoma subtypes but also offers customized treatment options based on the severity and subtype of the disease.