A groundbreaking study suggests that brain cancer could finally be cured with the help of artificial intelligence.
Scientists have developed a powerful tool that decodes the DNA of tumours while patients are undergoing surgery.
This game-changing breakthrough opens the door to tailored treatments for one of the most lethal forms of the disease.
Dr Kun-Hsing Yu, a leading researcher from Harvard Medical School, said: “Right now, even state-of-the-art clinical practice cannot profile tumours molecularly during surgery.
“Our tool overcomes this challenge by extracting thus-far untapped biomedical signals from frozen pathology slides.”
The breakthrough could significantly boost the survival rates of individuals battling the deadliest brain cancer known as glioblastoma.
READ MORE: AI tipped to transform how meteorologists make weather forecasts
Currently, the vital information undergoes laboratory testing, which often takes weeks to complete.
However, knowing a tumour’s molecular type enables neurosurgeons to make immediate decisions, such as whether to administer drugs directly to the brain during surgery.
Dr Yu said: “The ability to determine intraoperative molecular diagnosis in real time, during surgery, can propel the development of real-time precision oncology.”
The standard approach used now involves freezing brain tissue for microscopic examination. However, this alters cell appearance, impacting clinical evaluation accuracy. Additionally, even with advanced scanners, the human eye struggles to detect subtle genomic variations on a slide.
The promising AI device, called CHARM (Cryosection Histopathology Assessment and Review Machine) holds the potential to address these challenges.
Once validated through clinical testing in real-world settings, the team hopes that the device will obtain approval from the US Food and Drug Administration for hospital use.
In the UK, there are approximately 2,500 diagnosed cases each year. Tragically, the majority of patients do not survive beyond two years, with only a small number living beyond five years. This statistic has shown no improvement for decades.
Scientists have already designed AI models to profile bowel, lung and breast. Glioblastomas have remained particularly challenging due to their molecular complexity.
Dr Yu said: “Just like human clinicians who must engage in ongoing education and training, AI tools must keep up with the latest knowledge to remain at peak performance.”
CHARM is described in the journal Med.
We use your sign-up to provide content in ways you’ve consented to and to improve our understanding of you. This may include adverts from us and 3rd parties based on our understanding. You can unsubscribe at any time. More info
Source: Read Full Article