by A breakthrough in AI technology has enabled neurosurgeons to accurately identify the type of brain tumor during surgery, providing critical information in just 1.5 hours. Traditionally, this process takes up to a week, leaving surgeons without precise knowledge of the tumor type and its level of aggressiveness. The development, conducted by researchers from UMC Utrecht, Princess Máxima Center for pediatric oncology, and Amsterdam UMC, has been published in the esteemed scientific journal Nature.
In the Netherlands, approximately 1,400 adults and 150 children are diagnosed with brain or spinal cord tumors every year. Surgery is often the first step in treatment, but without prior knowledge of the tumor type, the surgical strategy cannot be tailored to the specific case. The exact diagnosis usually becomes available only after one week, after the tumor tissue has been analyzed visually and molecularly by a pathologist.
To address this issue, researchers from UMC Utrecht developed a deep-learning algorithm, a form of artificial intelligence, capable of significantly expediting the diagnosis process. Leading the project was Bastiaan Tops, in charge of the Pediatric Oncology Laboratory at the Princess Máxima Center. The algorithm was trained and tested using the extensive biobank maintained by the Máxima Center, which stores tissue samples from children with brain tumors.
The new technology has been successfully tested during real brain surgeries conducted by neurosurgeons in both Utrecht and Amsterdam. The entire process, from extracting tissue samples in the operating room to determining the tumor type, took between 60 to 90 minutes. The Princess Máxima Center has already adopted the technique for children whose surgical strategy depends on the outcome. Amsterdam UMC will also integrate the technology into their daily practice to expedite diagnosis.
The implications of DNA analysis during surgery are vast, according to Eelco Hoving, a pediatric neurosurgeon and clinical director of neuro-oncology at the Máxima Center. By identifying the tumor type during the initial surgery, the risk of additional surgeries to remove remaining aggressive tumors can be minimized. This not only reduces stress and risks for patients and their families but also optimizes the outcome of brain tumor surgery, as noted by Jeroen de Ridder, one of the researchers involved in the project.
While the initial results of the technique have been promising, more research is needed to expand its utility. Adding more tumor types to the algorithm will enable international standards and facilitate data comparison. Comparative research between the new AI-based method and the current lengthier approach will also shed light on the long-term benefits for patients’ quality of life. The collaboration between researchers, pathologists, and surgeons has set the stage for further advancements in brain tumor treatment and surgery.
*Note:
1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it
