For centuries, scientists have trained themselves to look through microscopes and carefully study their structural and molecular features. But those long hours bent over a microscope poring over microscopic images could be less necessary in the years ahead. The job of analyzing cellular features could one day belong to specially trained computers.
In a new study published in the journal Cell, researchers trained computers by feeding them paired sets of fluorescently labeled and unlabeled images of brain tissue millions of times in a row . This allowed the computers to discern patterns in the images, form rules, and apply them to viewing future images. Using this so-called deep learning approach, the researchers demonstrated that the computers not only learned to recognize individual cells, they also developed an almost superhuman ability to identify the cell type and whether a cell was alive or dead. Even more remarkable, the trained computers made all those calls without any need for harsh chemical labels, including fluorescent dyes or stains, which researchers normally require to study cells. In other words, the computers learned to “see” the invisible!
Posted In: News
Tags: Alzheimer's disease, brain, Brain Bot, cell biology, cells, computer learning, computers, deep learning, Google, machine learning, microscopy, neurology, neuroscience, Parkinson's disease, schizophrenia
Credit: Wellcome Centre for Human Neuroimaging, University College London.
In recent years, researchers fueled by the BRAIN Initiative and many other NIH-supported efforts have made remarkable progress in mapping the human brain in all its amazing complexity. Now, a powerful new imaging technology promises to further transform our understanding . This wearable scanner, for the first time, enables researchers to track neural activity in people in real-time as they do ordinary things—be it drinking tea, typing on a keyboard, talking to a friend, or even playing paddle ball.
This new so-called magnetoencephalography (MEG) brain scanner, which looks like a futuristic cross between a helmet and a hockey mask, is equipped with specialized “quantum” sensors. When placed directly on the scalp surface, these new MEG scanners can detect weak magnetic fields generated by electrical activity in the brain. While current brain scanners weigh in at nearly 1,000 pounds and require people to come to a special facility and remain absolutely still, the new system weighs less than 2 pounds and is capable of generating 3D images even when a person is making motions.
Tags: 3D printing, Autism Spectrum Disorder, brain, brain imaging, BRAIN Initiative, cerebral cortex, diagnostics, functional brain imaging, magnetic field sensor, magnetic fields, magnetoencephalography, MEG brain scanner, Parkinson's disease, primary motor cortex, quantum sensors, QuSpin, wearable devices
After a challenging day at work or school, sometimes it may seem like you are down to your last brain cell. But have no fear—in actuality, the brains of humans and other mammals have the potential to produce new neurons throughout life. This remarkable ability is due to a specific type of cell—adult neural stem cells—so beautifully highlighted in this award-winning micrograph.
Here you see the nuclei (purple) and arm-like extensions (green) of neural stem cells, along with nuclei of other cells (blue), in brain tissue from a mature mouse. The sample was taken from the subgranular zone of the hippocampus, a region of the brain associated with learning and memory. This zone is also one of the few areas in the adult brain where stem cells are known to reside.
Considering all the recent advances in mapping the complex circuitry of the human brain, you’d think we’d know all there is to know about the brain’s basic anatomy. That’s what makes the finding that I’m about to share with you so remarkable. Contrary to what I learned in medical school, the body’s lymphatic system extends to the brain—a discovery that could revolutionize our understanding of many brain disorders, from Alzheimer’s disease to multiple sclerosis (MS).
Researchers from the National Institute of Neurological Disorders and Stroke (NINDS), the National Cancer Institute (NCI), and the University of Virginia, Charlottesville made this discovery by using a special MRI technique to scan the brains of healthy human volunteers . As you see in this 3D video created from scans of a 47-year-old woman, the brain—just like the neck, chest, limbs, and other parts of the body—possesses a network of lymphatic vessels (green) that serves as a highway to circulate key immune cells and return metabolic waste products to the bloodstream.
Tags: Alzheimer’s disease, black-blood imaging, brain, brain imaging, brain scans, cerebral spinal fluid, gadobutrol, immunology, inflammatory brain diseases, lymph system, lymphatic system, lymphatic vessels, lymphatics, magnetic resonance imaging, meninges, MRI, MS, multiple sclerosis, neuroimaging, neurology, Parkinson's disease, stroke