Cambridge Consultants, a global product development and technology consultancy firm, and French startup Neuro Engineering Technologies Research Institute (NETRI) have achieved a brain-on-a-chip technology and lensless imaging approach that detects the activity of neurons in brain tissue. The technology uses a simulation of organ function on a chip. Cambridge Consultants was able to accelerate the processing of individual images by over three orders of magnitude, moving from approximately 20 minutes to process an image to hundreds of milliseconds. The researchers expect the technology to reduce the time and cost of testing new therapies for safety and efficacy. Brain-on-a-chip technologies seek to apply this approach to the neural circuitry of the brain, the most complex organ in the human body. NETRI’s research works with brain-on-a-chip technology and lensless microscopy to record the activity of millions of connected neurons, mimicking the neural circuits implicated in neurological disorders. The company’s approach generates an enormous amount of data, though, requiring several hours of computation effort in order to fully reconstruct the spatio-temporal map of neuron communication. The imaging system runs at approximately 1000 frames per second, the baseline algorithm taking an average of 18 minutes to process a single image on a desktop PC. Without improvement, the researchers say a single second of recording can take 12 days to process. A scientific imaging team was set to work within NETRI’s Data Lab, an on-site computer infrastructure, allowing rapid exploration of data-heavy approaches, such as high-definition imaging and deep learning. Cambridge Consultants employed the NVIDIA DGX POD architecture for the AI infrastructure, deploying the NetApp ONTAP AI solution that combines NVIDIA DGX-1 with NetApp ONTAP storage and network fabric. This system was able to process a frame in an average of 0.3 seconds, around 3000 times quicker than the original approach. This acceleration was achieved through a series of optimizations including the design and application of mathematical and algorithmic improvements, leveraging NumPY GPU-accelerated with RAPIDS (CuPy), and exploiting the sheer power of the DGX-1 system. The combined result enabled NETRI to completely reimagine its approach and to set its sights on developing a fully scalable and real-time medical service for hospitals and pharmaceutical industries to perform both in vitro diagnostics and personalized treatment for patients suffering from a neurological condition. “Lensless imaging replaces traditional optics with computation, creating a new set of optimization challenges that our team was excited to address,” said Sally Epstein, head of strategic technology at Cambridge Consultants. “We’re proud to be at the leading-edge of developments in brain-on-a-chip technology and neural imaging, at the point where radical improvements can be unlocked by those with the right combination of vision, experience, and compute power.” The consulting firm says the faster processing power will support the development of novel treatments for conditions such as Parkinson’s and Alzheimer’s diseases. “By combining the expertise of Cambridge Consultants with NVIDIA-based computational power, the real-time processing of neural communications becomes possible,” said Thibault Honegger, NETRI’s president and chief scientific officer. “This can mark a paradigm shift in assessing the functional aspects of in vitro neural networks. With this level of resolution, we will be able to accurately measure the wellness of the network, in relation to neurological conditions and potential recovery.”