One of the hallmarks of Alzheimer’s disease is beta amyloid plaque – clumps of protein that builds up in the brain and destroys neuron cell connections. Now, researchers at UC Davis Health and UC San Francisco have developed a machine learning tool that can detect if a sample of brain tissue has one type of amyloid plaque or another, and do it very quickly.
This is a proof of concept for a machine-learning approach to distinguishing critical markers of the disease.
The findings suggest that machine learning can add to the expertise and analysis of a neuropathologist. The tool allows them to analyze thousands of times more data and ask new questions otherwise impossible with the limited data processing capabilities of highly trained human experts, reports UC Davis.
“We still need the pathologist,” said Brittany N. Dugger, an assistant professor in the UC Davis Department of Pathology and Laboratory Medicine and lead author of the study. “This is a tool, like a keyboard is for writing. As keyboards help writing workflows, digital pathology paired with machine learning helps with neuropathology workflows.”
Another researcher in this project Michael J. Keiser, an assistant professor in UCSF’s Institute for Neurodegenerative Diseases and Department of Pharmaceutical Chemistry, designed a “convolutional neural network” (CNN), a computer program designed to recognize patterns based on thousands of human-labeled examples.
To teach the CNN algorithm how Dugger analyzes brain tissue, the researchers devised a method that allowed her to rapidly label tens of thousands of images from a collection of half a million taken from 43 healthy and diseased brain samples.
This database labeled example images was used by the UCSF team to train their CNN machine-learning algorithm to identify different types of brain changes seen in Alzheimer’s disease. This includes discriminating between so-called cored and diffuse plaques and identifying abnormalities in blood vessels. The researchers showed that their algorithm could process an entire whole-brain slice slide with 98.7% accuracy. They confirmed the computer’s identification skills were biologically accurate.
“If we can better characterize what we are seeing, this could provide further insights into the diversity of dementia,” Dugger said. “It opens the door to precision medicine for dementias.” She added, “These projects are phenomenal examples of cross-disciplinary translational science; neuropathologists, a statistician, a clinician, and engineers coming together, forming a dialogue and working together to solve a problem.”
The findings of the study were published in the journal Nature Communications.
WT | Wearable Technologies Conference in San Francisco on July 9-10
The most innovative wearables event will be back on July 9-10 in beautiful San Francisco at SEMICON West to celebrate the 34th edition of the WT | Wearable Technologies Conference Series. Topics include data analytics in professional sports, prevention, treatment and rehabilitation with wearables, the future of digital health, medication and adherence, smart patches, workflow optimization and workforce safety and much more – featuring international leaders and experts of the wearables industry´s biggest names including Abbott, Autodesk, Datwyler, Kopin, Maxim Integrated, Multek, NFLPA, Omron, SharkDreams, Qualcomm, and many more. Register now to be part of #WTUS19