Artificial Intelligence has reached in almost every profession including brain operation to assist the doctors. In the Netherlands, scientists are reportedly taking help of Artificial Intelligence in making smart and better decisions while operating a brain tumor. A surgeon goes through a lot of mental stress while operating a brain surgery and with the help of AI it is believed better decisions could be made with the human skills of a doctor.
In a journal article, Nature, the author has mentioned the method of utilising computer scanning to determine a detailed diagnosis of the type and even subtype of the brain tumor.The computer studies the DNA to give instant results which used to take days before.
According to the researchers, early-stage identification can aid surgeons in determining how aggressively to operate throughout a lengthy procedure. The approach could eventually direct medical professionals toward therapies designed specifically for a given tumor subtype.
The professor, Jeroen de Ridder, of Center for Molecular Medicine at UMC Utrecht, Netherlands has said, “It’s imperative that the tumor subtype is known at the time of surgery.” He is one of the doctors who helped in achieving this study as he added, “What we have now uniquely enabled is to allow this very fine-grained, robust, detailed diagnosis to be performed already during the surgery.”
As per the journal, the deep learning system is called Sturgeon and it was first tested on frozen tumor samples from prior brain cancer procedures. Within 40 minutes of beginning the genetic sequencing, 45 of 50 cases were correctly diagnosed. It did not provide a diagnosis in the remaining five cases because the data was ambiguous.
The Sturgeon system underwent various tests to finally decide its value. The technique was subsequently put to the test during 25 real brain operations, most of which were performed on young patients, along with the conventional procedure of evaluating tumor samples under a microscope. As a result, The new method produced 18 accurate diagnoses but failed to meet the required level of confidence in seven additional cases. The study found that it completed its diagnostics in less than 90 minutes, which is just enough time for it to guide choices made during a surgery.
The technology proved to be efficient but not every hospital can access it. According to Dr. Alan Cohen, the director of the Johns Hopkins Division of Pediatric Neurosurgery and a cancer specialist, it can take several weeks to get the correct result for a hospital to function.
