Goto

Collaborating Authors

Pathology AI: Deep Learning vs Decision Trees - Flagship Biosciences

#artificialintelligence

February 19, 2019 – Machine learning, which provides the ability to learn a task from data (without the need of being programmed explicitly), is a key component of any Pathology AI (Artificial Intelligence) system. There are many different approaches in machine learning, reaching from simple decision trees to complex deep learning, each with its advantages and disadvantages. Deep learning, which allows to learn highly complex visual features, has created a hype about Artificial Intelligence (AI) and Healthcare AI, as is was able to solve complex computer vision problems that we believed out-of-reach just a few years ago. As pathology is a visual task it is understandable that academia and "pure" technology companies are now working heavily on deep learning approaches for pathology.The key problem for any Pathology AI system are the variations between different patient types. In a disease state, no two patient samples look identical.


CRISPR And Spit Might Be Keys To Faster, Cheaper, Easier Tests For The Coronavirus

NPR Technology

Mammoth Biosciences and researchers at the University of California, San Francisco are working on a coronavirus test that could run multiple samples at once, with results in 35-40 minutes. Even better, they say, it doesn't require the sophisticated, expensive equipment used in other tests for the virus. Mammoth Biosciences and researchers at the University of California, San Francisco are working on a coronavirus test that could run multiple samples at once, with results in 35-40 minutes. Even better, they say, it doesn't require the sophisticated, expensive equipment used in other tests for the virus. Being able to test for coronavirus infections is a critical component to reopening society -- even a little bit -- after the initial wave of COVID-19.


InterVenn Biosciences Releases First-Ever Software for AI-Enabled Mass Spec Analysis

#artificialintelligence

The announcement was made at BioData World Congress 2019, taking place this week in Basel, Switzerland. This AI-based software is accessed via the Google Cloud Platform and has demonstrated over 99 percent concordance with human peak selection. A publication detailing the specific neural network architecture is currently undergoing peer review. Interested scientists may access the OpenPIP platform at https://openpip.intervenn.bio. "By sharing with the greater mass spec community one component of the powerful platform we have built, we are hopeful to inspire collaborations that can find new solutions to some of the biggest challenges we are facing in diseases like cancer," said Aldo Carrascoso, chief executive officer of InterVenn BioSciences.


Zika could infect more fetuses than previously thought

Daily Mail - Science & tech

Zika could be more dangerous to unborn babies than previously thought, a new study suggests. Tests on pregnant monkeys infected with the virus found that every single fetus had picked up some trace of Zika. Taking a closer look, the researchers at the University of Wisconsin-Madison saw how the infection passed seamlessly through the mother's tissues into the fetus's nervous system. While not all of the babies were born with typical Zika symptoms such as shrunken heads or microcephaly, some had other problems - particularly an unusual inflammation of the eyes - which they could only trace back to Zika. The researchers warn that their findings will likely also apply to humans, given that these monkeys (rhesus macaques) are so similar to humans in their genetic makeup.


Spheroids: Research in 3D - Reveal Biosciences

#artificialintelligence

A spheroid is a small, spherical cluster of cells that acts as a 3D cell culture. The term "organoid" is also used interchangeably with "spheroid", although the former specifically refers to a 3D cluster of organ-specific cells. Spheroids and organoids can be artificially assembled through different methods, including the use of centrifugal force or gravity. As the spheroid forms, cells will sort themselves into different regions and layers of the cluster, mimicking natural processes. Cells adhere to each other and exhibit an organic cell shape and architecture.