When a brain tumor left Pat Long with persistent déjà vu, he began to question the very nature of reality. On encountering déjà vu, the brain runs a sort of sense check, searching for objective evidence of the prior experience and then disregarding it as the illusion that it is. Professor Chris Moulin, one of the foremost experts on the déjà experience, describes a patient he encountered while working at a memory clinic at a hospital in Bath, England. After his first encounter with AKP, Moulin began to become interested in the causes of déjà vu and how subjective feelings can interfere with day-to-day memory processes.
In their experiments on more than 100 brain tissue samples, the researchers used deep learning to detect the presence of a tumor and classify it into one of several broad categories. "Helping patients get diagnosed more quickly means patients spend less time in the operating room, which decreases the risks associated with surgery," said Orringer, a practicing neurosurgeon. Accuracy rates on 30 tissue samples tested were 90 percent, compared with neuropathologists' accuracy rates of 90-95 percent in clinical practice, said Orringer. By enabling prompt, consistent and accurate tissue diagnosis during surgery, deep learning could help fix the problem of variability among pathologists' diagnoses, Orringer said.