Tag: Featured
-
AI detects pneumonia from chest X-rays
Andrew Ng and Stanford colleagues used AI to detect pneumonia from x-rays with similar accuracy to trained radiologists. The CheXNet model analyzed 112,200 frontal-view X-ray images of 30,805 unique patients released by the NIH (ChestX-ray14.) Deep Learning algorithms also detected14 diseases including fibrosis, hernias, and cell masses, with fewer false positives and negatives than NIH…
-
Researchers claim to improve human memory with implanted electrodes
In a small study, USC’s Dong Song demonstrated the efficacy of an implantable “memory prosthesis.” Dr. Song presented his work at the Society for Neuroscience conference in Washington this week. 20 volunteers had the device implanted at the same time as electrodes for epilepsy treatment, a procedure which they had already planned. The “prosthesis” collected brain…
-
Optogenetic technique controls single neurons
MIT’s Ed Boyden and Paris Descartes University’s Valentina Emiliani have developed a new optogenetic technique, combined with new opsins, that stimulates individual cells with precise control over both the timing and location of the activation. This will allow the study of how individual cells, and connections among those cells, generate specific behaviors such as initiating a movement or…
-
Video: John Rogers on soft electronics for the human body
Recorded at ApplySci’s Wearable Tech + Digital Health + Neurotech Boston conference on September 19th at the MIT Media Lab. Join ApplySci at Wearable Tech + Digital Health + Neurotech Silicon Valley on February 26-27, 2018 at Stanford University. Speakers include: Vinod Khosla – Justin Sanchez – Brian Otis – Bryan Johnson – Zhenan Bao…
-
Silicon probes record hundreds of neurons simultaneously
Neuropixels, developed by HHMI’s Tim Harris, are electrodes that record brain activity from hundreds of neurons. Previously, it was not possible to measure the joint activity of individual neurons distributed across brain regions. Recording methods could either resolve the activity of individual neurons or monitor multiple brain regions. UCL, Allen Institute for Brain Science, IMEC researchers collaborated on…
-
Phone camera measures wound depth, severity
AutoDepth by Swift Medical uses a phone’s camera to understand a wound’s depth and severity. Algorithms process dynamic changes over time. Depth can indicate whether a wound is healing properly. The system is noninvasive, and can be widely accessible to clinicians. In addition to gauging the wound healing process, it can be used for measuring the…
-
AI detects suicidal thoughts from brain scans in small study
David Brent and PIttsburgh and Carnegie Mellon colleagues used machine learning to identify suicidal thoughts in subjects based on fMRI scans. In a recent study, 18 suicidal participants and 18 members of a control group were presented with three lists of 10 words related to suicide, positive, or negative effects. Previously mapped neural signatures showing…
-
Weather, activity, sleep, stress data used to predict migraines
Migraine Alert by Second Opinion Health uses machine learning to analayze weather, activity, sleep, and stress, to determine if a user will have a migraine headache. The company claims that the algorithm is effective after 15 episodes are logged. They have launched a multi patient study with the Mayo Clinic, in which subjects use a phone and…
-
Video: Ed Boyden on technologies for analyzing & repairing the brain
Recorded at ApplySci’s Wearable Tech + Digital Health + Neurotech conference on September 19th at the MIT Media Lab. Join ApplySci at Wearable Tech + Digital Health + Neurotech Silicon Valley on February 26-27, 2018 at Stanford University. Speakers include: Vinod Khosla – Justin Sanchez – Brian Otis – Bryan Johnson – Zhenan Bao –…
-
AI detects bowel cancer in less than 1 second in small study
Yuichi Mori and Showa University colleagues haved used AI to identify bowel cancer by analyzing colonoscopy derived polyps in less than a second. The system compares a magnified view of a colorectal polyp with 30,000 endocytoscopic images. The researchers claimed 86% accuracy, based on a study of 300 polyps. While further testing the technology, Mori said that…
-
3D neuron reconstruction reveals electrical behavior
Christof Koch and Allen Institute colleagues have created 3D computer reconstructions of living human brain cells using discarded surgical tissue. As the tissue is still alive when it reaches the lab, the virtual cells are able to capture electrical signals, in addition to cell shape and anatomy. This is the first time that scientists have been able…
-
Machine learning improves breast cancer detection
MIT’s Regina Barzilay has used AI to improve breast cancer detection and diagnosis. Machine learning tools predict if a high-risk lesion identified on needle biopsy after a mammogram will upgrade to cancer at surgery, potentially eliminating unnecessary procedures. In current practice, when a mammogram detects a suspicious lesion, a needle biopsy is performed to determine if…