New AI tool can predict where glioblastoma is most likely to return after initial surgery
A new AI-based model can predict where glioblastoma is most likely to return after initial surgery, potentially giving doctors a chance to treat it before it becomes visible on MRI.
Researchers at UC San Francisco and the University of Michigan have developed an AI system that can predict where glioblastoma, the most lethal malignant brain tumor, is likely to recur after initial surgery. The AI approach, which uses stimulated Raman histology (SRH) to produce microscopic images of fresh tissue, outperformed conventional pathology in identifying areas where the cancer is most likely to return.
The AI system, FastGlioma, scores tissue based on tumor infiltration and, when combined with clinical, imaging and molecular data in machine-learning models, significantly improves the prediction of recurrence sites. The model also performs well at pinpointing the location of recurrence within 5-10 millimeters of the sampled tissue.
Early detection through this predictive AI could enable targeted treatments, such as additional tissue removal during surgery or focal radiation, to delay the first recurrence and potentially extend patient survival.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
