Toggle light / dark theme

The number of AI and, in particular, machine learning (ML) publications related to medical imaging has increased dramatically in recent years. A current PubMed search using the Mesh keywords “artificial intelligence” and “radiology” yielded 5,369 papers in 2021, more than five times the results found in 2011. ML models are constantly being developed to improve healthcare efficiency and outcomes, from classification to semantic segmentation, object detection, and image generation. Numerous published reports in diagnostic radiology, for example, indicate that ML models have the capability to perform as good as or even better than medical experts in specific tasks, such as anomaly detection and pathology screening.

It is thus undeniable that, when used correctly, AI can assist radiologists and drastically reduce their labor. Despite the growing interest in developing ML models for medical imaging, significant challenges can limit such models’ practical applications or even predispose them to substantial bias. Data scarcity and data imbalance are two of these challenges. On the one hand, medical imaging datasets are frequently much more minor than natural photograph datasets such as ImageNet, and pooling institutional datasets or making them public may be impossible due to patient privacy concerns. On the other hand, even the medical imaging datasets that data scientists have access to could be more balanced.

In other words, the volume of medical imaging data for patients with specific pathologies is significantly lower than for patients with common pathologies or healthy people. Using insufficiently large or imbalanced datasets to train or evaluate a machine learning model may result in systemic biases in model performance. Synthetic image generation is one of the primary strategies to combat data scarcity and data imbalance, in addition to the public release of deidentified medical imaging datasets and the endorsement of strategies such as federated learning, enabling machine learning (ML) model development on multi-institutional datasets without data sharing.

Tohid Didar and Jeff Weitz had a solution, but they also had a problem.

Didar, an associate professor of engineering and Weitz, a hematologist, professor of medicine and executive director of the Thrombosis & Atherosclerosis Research Institute, had collaborated to create a novel and highly promising material to improve the success of vascular grafts, but they needed a better way to test how well it worked.

Their revolutionary idea was an engineered non-stick surface combined with biological components that can repel all but a targeted group of cells — those that form the natural lining of the body’s veins and arteries.

Today, Deep Longevity, a company will launch its new software as a service (SaaS) antiaging platform, SenoClock. The culmination of years of biogerontological research, SenoClock will host all of Deep Longevity’s patented aging clocks that may be used in clinical practice and other healthcare-adjacent industries.

Aging clocks available on the platform will allow its users to receive comprehensive and actionable pace of aging reports based on various data types, such as blood tests, psychological surveys, gut flora composition and more.

Longevity. Technology: Hospitals and clinics are mostly reactive when it comes to treatment, a practice that is partly due to infrastructure and partly due to human nature. However, as we discussed in our interview with Sir John Bell earlier this week, prevention must be the new paradigm and its one that better serves individuals, healthcare systems and populations as a whole. Deep Longevity’s new product SenoClock unlocks a preventive, longevity-focused mode of healthcare; a new SaaS platform, SenoClock offers physicians a single portal in which to track the aging rate of their patients, enabling them to generate personalised health plans.

The idea that life’s deepest, oldest roots were laid down by RNA molecules that evolved ever more complexity has dominated the origins-of-life field for the past few decades, reigning over competing theories that started instead with peptides or DNA.

But recently, the field has shifted toward theories that include more than one protagonist. One that’s gained particular momentum is the idea that RNAs and peptides coevolved complexity, and that their intermingling sparked life as we know it.

Now, a study published in Nature breathes fire into an “RNA-peptide world” by suggesting a plausible pathway for how early RNA molecules may have enabled peptides to grow directly on them, like mushrooms growing on a tree. Those peptides may in turn have stabilized the RNA molecules, allowing them space to complexify. This coevolution of two of life’s key players as a single mixed, “chimeric” molecule may have been the very start of protein production, and a step toward a primitive version of a ribosome.

“Colorado voters saw the benefit of regulated access to natural medicines, including psilocybin, so people with PTSD, terminal illness, depression, anxiety and other mental health issues can heal,” co-proponents, Kevin Matthews and Veronica Lightening Horse Perez said in emailed statement Wednesday evening.”


Ten years after legalizing the use and sale of marijuana, Colorado became only the second state in the U.S. to legalize the use of psilocybin mushrooms.

The ballot measure, Proposition 122, squeaked across the finish line as ballots were tallied the day after Election Day, receiving 51% of the vote.

Proponents called it a “truly historic moment.”

Summary: Using monoclonal antibodies instead of conventional immunosuppressant drugs preserves stem cells in mouse brains.

Source: University of Michigan.

A new approach to stem cell therapy that uses antibodies instead of traditional immunosuppressant drugs robustly preserves cells in mouse brains and has potential to fast-track trials in humans, a Michigan Medicine study suggests.

Vibrating tiny robots could revolutionize research.

Individual robots can work collectively as to create major advances in everything from construction to surveillance, but microrobots’ small scale is ideal for drug delivery, disease diagnosis, and even surgeries.

Despite their potential, microrobots’ size often means they have limited sensing, communication, motility, and computation abilities, but new research from the Georgia Institute of Technology enhances their ability to collaborate efficiently. The work offers a new system to control swarms of 300 3-millimeter microbristle robots’ (microbots) ability to aggregate and disperse controllably without onboard sensing.

All they need is electrical stimulation, and once activated, they re-establish the lost connection between different regions of the spinal cord.

Imagine you are stuck inside a room, you want to get out, but your body is not moving. No matter how hard you try, you are unable to move your body parts. You are not even able to move your finger, how would you feel? Well, that’s what chronic paralysis feels like.

Unfortunately, there is no known permanent cure for this neurological disorder, and this is what makes the situation worse. The physical and mental struggle that a patient with chronic paralysis goes through is unimaginable.


Ozgu Arslan/iStock.

However, a team of international researchers has recently made nine patients with severe spinal cord injuries (SCIs) walk again. They claim to have identified neurons that can restore mobility in patients with SCI. This new and interesting development raises great hopes for people suffering from chronic paralysis.