American scientists recently published significant research findings in the journal Nature: the artificial intelligence model FastGlioma, jointly developed by the University of Michigan and the University of California, San Francisco, can quickly assess the presence of cancerous tumor residue within ten seconds during brain tumor surgeries, bringing a revolutionary breakthrough to neurosurgery. This innovation combines microscopic optical imaging with AI foundational models. The research team utilized over 11,000 surgical samples and 4 million microscopic images for pre-training, employing the University of Michigan's self-developed stimulated Raman tissue imaging technology.

Dutch researchers have developed an algorithm called Sturgeon that can identify the type of brain tumor within 90 minutes. The algorithm relies on nanopore sequencing technology, enabling real-time reading of DNA sample base sequences. After training and testing, the algorithm was able to correctly identify 18 cases of brain tumor types in 40 minutes. By identifying the subtypes of brain tumors, surgeons can adjust their surgical strategies. Researchers hope to further validate the technology and compare it with standard methods.