Artificial Intelligence Enhances Brain Activity Scans

Johns Hopkins biomedical engineers have developed an artificial intelligence (AI) training strategy to capture images of mouse brain cells in action. The engineers say the AI system and specialized ultra-small microscopes make it possible to find precisely where and when cells are activated during movement, learning, and memory.

"When a mouse's head is restrained for imaging, its brain activity may not truly represent its neurological function," says research leader Xingde Li in a press release issued by Johns Hopkins. "To map brain circuits that control daily functions in mammals, we need to see precisely what is happening among individual brain cells and their connections, while the animal is freely moving around, eating and socializing."

Previously, the engineers developed ultra-small microscopes that the mice can wear on the top of their head. These microscopes measure only a couple of millimeters in diameter, which limits the imaging technology they can carry on board. Therefore, the frame rate that the miniature microscopes can achieve is lower than the 20 frames per second that would be needed to eliminate all the disturbances from the motion of a freely moving mouse.

To solve this problem, the engineers reduced the resolution (number of pixels) of the microscopes and trained an AI program based on deep learning and deep neural networks to recognize and restore the missing points, enhancing the images to a higher resolution. Video-rate imaging was achieved by increasing the scanning speed and decreasing the scanning density during data acquisition in conjunction with the assistance of deep neural networks.

The engineers developed a two-stage training strategy, described in a research paper published in Nature Communications. First, they began training the AI to identify the building blocks of the brain from images of fixed samples of mouse brain tissue. Then, they trained the AI to recognize these building blocks in a head-restrained living mouse under their ultra-small microscope. This step trained the AI to recognize brain cells with natural structural variation and a small bit of motion caused by the movement of the mouse's breathing and heartbeat.

"The hope was that whenever we collect data from a moving mouse, it will still be similar enough for the AI network to recognize," explains Li.

The engineers adapted an open-source, deep learning platform distributed via Github to recover image quality. The engineers found that the AI could adequately restore the image quality up to 26 frames per second.

"We could never have seen this information at such high resolution and frame rate before," says Li. "This development could make it possible to gather more information on how the brain is dynamically connected to action on a cellular level."