Using brain scans and direct neuron recording from macaque monkeys, the team found specialized "face patches" that respond to specific combinations of facial features. In the early 2000s, while recording from epilepsy patients with electrodes implanted into their brains, Quian Quiroga and colleagues found that face cells are particularly picky. In a stroke of luck, Tsao and team blew open the "black box" of facial recognition while working on a different problem: how to describe a face mathematically, with a matrix of numbers. In macaque monkeys with electrodes implanted into their brains, the team recorded from three "face patches"--brain areas that respond especially to faces--while showing the monkeys the computer-generated faces.
That's what inspired Stanford University neurosurgeon Dr. Kai Miller to team up with Microsoft to offer the inaugural Cortana Intelligence Competition: Decoding Brain Signals. The Decoding Brain Signals competition allowed machine learning experts and data scientists from around the world to test their skills while helping further the cause of neuroscience research. The contest asked participants to build intelligent models to decode electrical brain signals that were gathered from Dr. Miller's research with epilepsy patients. The winning contestant to Cortana Intelligence's inaugural competition was Alexandre Barachant from France.
A new smartphone app called myCareCentric Epilepsy has been successfully piloted at Poole Hospital to help those with epilepsy and medical staff to monitor the condition. The drug used to treat epilepsy Trobalt, also called retigabine, will be discontinued and will no longer be available after June 2017. This comes after safety issues were announced in 2013 – the drug could cause skin to turn blue and result in problems with the eyes. As a result of these safety issues and the decline in new epilepsy patients being prescribed Trobalt, the decision was made to permanently discontinue the drug.
A project using wearable devices and machine learning could help people with epilepsy to monitor their condition better. The initiative, called myCareCentric, combines wearable technologies, shared care records, machine learning, and data analysis tools. The project is using the Microsoft Band as part of the initiative, which Denley said was chosen because it has an API that you can control "and we wanted to be able to control things like battery life, triggering events, and so on". "Then we have been taking this massive stream of data and, together with the University of Kent, using machine learning to monitor the data," Denley said.
During the study, researchers led by Dr Carole Lartizien, from the University of Lyon, developed a complex system that is able learn features associated with healthy brain MRI scans. These are the presence of grey matter within the white matter (heterotopia), and a blurred junction between grey and white matter. Dr Lartizien and her team tested the performance of the system on brain MRI images from 11 people with drug-resistant epilepsy, who had a total of 13 lesions in their brains, and 77 healthy volunteers. They found that the system was able to detect all of the lesions in the MRI positive cases (where the lesions on MRI images were detectable by experts) and 70% of lesions in MRI negative cases (where the lesions weren't visible to experts).
In the video, Dr Kai Miller, Neurosurgery Resident at Stanford University, described an ingenious experiment designed to link brain activity to perception. The goal is to be able to create a model from the brain sensor data that can accurately predict what the patients is seeing: a face or a house. You can try creating such a model yourself in the Azure Machine Learning competition, Decoding Brain Signals. To enter the competition, you'll need to train a model on the competition data, and have it accurately predict the images seen by other patients in the study (whose data remains hidden from all participants).