Ultra-fast deep-learned pediatric CNS tumor classification during surgery

A major challenge in the treatment of central nervous system (CNS) cancer is that taking a biopsy is often not possible. Therefore the precise tumor type is often unknown at the time of surgery, while a choice must be made between radical and conservative resection. Rapid histological analysis is currently the only option to determine the surgical strategy. After surgery, a molecular classification is made to determine the exact cancer type based on the methylome of the tumor. In a number of cases, the molecular diagnosis differs from the histological assessment: this means that either an additional and more radical surgery is needed; or it reveals that the resection was too radical and side-effects of the surgery could have been avoided.

Download the PDF