Summary:
In a recent study published in the journal Nature, scientists in the Netherlands have harnessed artificial intelligence (AI) to assist surgeons in making critical decisions during brain tumor surgeries. When faced with the dilemma of whether to remove some healthy brain tissue to ensure the complete removal of a tumor or avoid healthy tissue and risk leaving dangerous cells behind, AI technology can provide valuable insights.
The method involves a computer scanning segments of a brain tumor’s DNA and identifying specific chemical modifications that yield a detailed diagnosis of the tumor’s type and subtype. This diagnosis, generated early in the surgical procedure, can guide surgeons in deciding how aggressively to operate and may also direct them towards tailored treatments for specific tumor subtypes.
The AI system, called Sturgeon, was initially tested on frozen tumor samples from past brain cancer surgeries, accurately diagnosing 45 out of 50 cases within 40 minutes of beginning genetic sequencing. During 25 live brain surgeries, including surgeries on children, Sturgeon provided 18 correct diagnoses within 90 minutes, making it feasible to impact decisions during surgery.
This AI-driven diagnostic approach can be particularly useful for hospitals that lack access to comprehensive genetic sequencing technology, as obtaining such results can take several weeks. The technology has the potential to improve the precision and effectiveness of brain tumor surgeries while minimizing damage to healthy brain tissue.
Article written by Benjamin Mueller| Image by Unspalsh
11/10/2023
Source:
Thge New York Time’s
https://www.nytimes.com/2023/10/11/health/ai-tumor-diagnosis-brain-cancer.html#:~:text=Their%20deep%20learning%20system%2C%20called,because%20the%20information%20was%20unclear.