The signals that drive lots of the brain and body’s most essential functions — consciousness, sleep, respiration, heart rate, and motion — course through bundles of “white matter” fibers within the brainstem, but imaging systems thus far have been unable to finely resolve these crucial neural cables. That has left researchers and doctors with little capability to evaluate how they’re affected by trauma or neurodegeneration.
In a brand new study, a team of MIT, Harvard University, and Massachusetts General Hospital researchers unveil AI-powered software able to routinely segmenting eight distinct bundles in any diffusion MRI sequence.
Within the open-access study, published Feb. 6 within the the research team led by MIT graduate student Mark Olchanyi reports that their BrainStem Bundle Tool (BSBT), which they’ve made publicly available, revealed distinct patterns of structural changes in patients with Parkinson’s disease, multiple sclerosis, and traumatic brain injury, and make clear Alzheimer’s disease as well. Furthermore, the study shows, BSBT retrospectively enabled tracking of bundle healing in a coma patient that reflected the patient’s seven-month road to recovery.
“The brainstem is a region of the brain that is actually not explored since it is hard to image,” says Olchanyi, a doctoral candidate in MIT’s Medical Engineering and Medical Physics Program. “People don’t really understand its makeup from an imaging perspective. We want to know what the organization of the white matter is in humans and the way this organization breaks down in certain disorders.”
Adds Professor Emery N. Brown, Olchanyi’s thesis supervisor and co-senior writer of the study, “the brainstem is one in every of the body’s most vital control centers. Mark’s algorithms are a major contribution to imaging research and to our ability to the understand regulation of fundamental physiology. By enhancing our capability to image the brainstem, he offers us recent access to vital physiological functions reminiscent of control of the respiratory and cardiovascular systems, temperature regulation, how we stay up throughout the day and the way sleep at night.”
Brown is the Edward Hood Taplin Professor of Computational Neuroscience and Medical Engineering in The Picower Institute for Learning and Memory, the Institute for Medical Engineering and Science, and the Department of Brain and Cognitive Sciences at MIT. He can also be an anesthesiologist at MGH and a professor at Harvard Medical School.
Constructing the algorithm
Diffusion MRI helps trace the long branches, or “axons,” that neurons extend to speak with one another. Axons are typically clad in a sheath of fat called myelin, and water diffuses along the axons inside the myelin, which can also be called the brain’s “white matter.” Diffusion MRI can highlight this very directed displacement of water. But segmenting the distinct bundles of axons within the brainstem has proved difficult, because they’re small and masked by flows of brain fluids and the motions produced by respiration and heart beats.
As a part of his thesis work to higher understand the neural mechanisms that underpin consciousness, Olchanyi desired to develop an AI algorithm to beat these obstacles. BSBT works by tracing fiber bundles that plunge into the brainstem from neighboring areas higher within the brain, reminiscent of the thalamus and the cerebellum, to provide a “probabilistic fiber map.” A man-made intelligence module called a “convolutional neural network” then combines the map with several channels of imaging information from inside the brainstem to differentiate eight individual bundles.
To coach the neural network to segment the bundles, Olchanyi “showed” it 30 live diffusion MRI scans from volunteers within the Human Connectome Project (HCP). The scans were manually annotated to show the neural network methods to discover the bundles. Then he validated BSBT by testing its output against “ground truth” dissections of post-mortem human brains where the bundles were well delineated via microscopic inspection or very slow but ultra-high-resolution imaging. After training, BSBT became proficient in routinely identifying the eight distinct fiber bundles in recent scans.
In an experiment to check its consistency and reliability, Olchanyi tasked BSBT with finding the bundles in 40 volunteers who underwent separate scans two months apart. In each case, the tool was in a position to find the identical bundles in the identical patients in each of their two scans. Olchanyi also tested BSBT with multiple datasets (not only the HCP), and even inspected how each component of the neural network contributed to BSBT’s evaluation by hobbling them one after the other.
“We put the neural network through the wringer,” Olchanyi says. “We desired to ensure that it’s actually doing these plausible segmentations and it’s leveraging each of its individual components in a way that improves the accuracy.”
Potential novel biomarkers
Once the algorithm was properly trained and validated, the research team moved on to testing whether the flexibility to segment distinct fiber bundles in diffusion MRI scans could enable tracking of how each bundle’s volume and structure varied with disease or injury, making a novel sort of biomarker. Although the brainstem has been difficult to look at intimately, many studies show that neurodegenerative diseases affect the brainstem, often early on of their progression.
Olchanyi, Brown and their co-authors applied BSBT to scores of datasets of diffusion MRI scans from patients with Alzheimer’s, Parkinson’s, MS, and traumatic brain injury (TBI). Patients were in comparison with controls and sometimes to themselves over time. Within the scans, the tool measured bundle volume and “fractional anisotropy,” (FA) which tracks how much water is flowing along the myelinated axons versus how much is diffusing in other directions, a proxy for white matter structural integrity.
In each condition, the tool found consistent patterns of changes within the bundles. While just one bundle showed significant decline in Alzheimer’s, in Parkinson’s the tool revealed a discount in FA in three of the eight bundles. It also revealed volume loss in one other bundle in patients between a baseline scan and a two-year follow-up. Patients with MS showed their best FA reductions in 4 bundles and volume loss in three. Meanwhile, TBI patients didn’t show significant volume loss in any bundles, but FA reductions were apparent in the vast majority of bundles.
Testing within the study showed that BSBT proved more accurate than other classifier methods in discriminating between patients with health conditions versus controls.
BSBT, due to this fact, could be “a key adjunct that aids current diagnostic imaging methods by providing a fine-grained assessment of brainstem white matter structure and, in some cases, longitudinal information,” the authors wrote.
Finally, within the case of a 29-year-old man who suffered a severe TBI, Olchanyi applied BSBT to a scans taken throughout the man’s seven-month coma. The tool showed that the person’s brainstem bundles had been displaced, but not cut, and showed that over his coma, the lesions on the nerve bundles decreased by an element of three in volume. As they healed, the bundles moved back into place as well.
The authors wrote that BSBT “has substantial prognostic potential by identifying preserved brainstem bundles that may facilitate coma recovery.”
The study’s other senior authors are Juan Eugenio Iglesias and Brian Edlow. Other co-authors are David Schreier, Jian Li, Chiara Maffei, Annabel Sorby-Adams, Hannah Kinney, Brian Healy, Holly Freeman, Jared Shless, Christophe Destrieux, and Hendry Tregidgo.
Funding for the study got here from the National Institutes of Health, U.S. Department of Defense, James S. McDonnell Foundation, Rappaport Foundation, American SidS Institute, American Brain Foundation, American Academy of Neurology, Center for Integration of Medicine and Progressive Technology, Blueprint for Neuroscience Research, and Massachusetts Life Sciences Center.
