An emerging artificial intelligence-powered tool, known as Sturgeon, successfully diagnosed 45 out of 50 frozen brain tumor samples in a matter of just 40 minutes. In living patients, the tool was capable of accurately diagnosing 18 out of 25 cases, according to a study published Oct. 11 in Nature.
Brain cancer is notorious for being complex, and the surgeons removing tumors are often choosing between clearing out all cancerous cells and cutting into a portion of healthy tissue, or possibly leaving some of those cells behind, but leaving the tissue intact, The New York Times reported.
The tool was designed to be "fully compatible with the surgical timeline, to guide the surgeon on how to proceed with the procedure," study authors wrote.
Historically, this process has relied on preoperative imaging and intraoperative histological analysis, but now surgeons may be able to utilize the technology in the operating room to help classify tumors and improve surgical decision-making, and as a result — patient outcomes.
Sturgeon, according to the study authors, is "not patient-specific and can be used universally without retraining, mitigating the need to have access to privacy-sensitive training data at the site of deployment. As a result, limited computational resources are required during surgery."