New Algorithm Predicts Alzheimer’s with 99% accuracy

Researchers from Kaunas universities in Lithuania developed a deep learning-based method that can predict the possible onset of Alzheimer’s disease from brain images with an accuracy of over 99 per cent. The method was developed while analysing functional MRI images obtained from 138 subjects and performed better in terms of accuracy, sensitivity and specificity than previously developed methods.

According to World Health Organisation, Alzheimer’s disease is the most frequent cause of dementia, contributing to up to 70 per cent of dementia cases. Worldwide, approximately 24 million people are affected, and this number is expected to double every 20 years. Owing to societal ageing, the disease will become a costly public health burden in the years to come.

Medical professionals all over the world attempt to raise awareness of an early Alzheimer’s diagnosis, which provides the affected with a better chance of benefiting from treatment. This was one of the most important issues for choosing a topic for Modupe Odusami, a PhD student from Nigeria”, says Rytis Maskeliūnas, a researcher at the Department of Multimedia Engineering, Faculty of Informatics, Kaunas University of Technology (KTU), Odusami’s PhD supervisor. One of the possible Alzheimer’s first signs is mild cognitive impairment (MCI), which is the stage between the expected cognitive decline of normal ageing and dementia. Based on the previous research, functional magnetic resonance imaging (fMRI) can be used to identify the regions in the brain which can be associated with the onset of Alzheimer’s disease, according to Maskeliūnas. The earliest stages of MCI often have almost no clear symptoms, but in quite a few cases can be detected by neuroimaging.

However, although theoretically possible, manual analysing of fMRI images attempting to identify the changes associated with Alzheimer’s not only requires specific knowledge but is also time-consuming – application of Deep learning and other AI methods can speed this up by a significant time margin. Finding MCI features does not necessarily mean the presence of illness, as it can also be a symptom of other related diseases, but it is more of an indicator and possible helper to steer toward an evaluation by a medical professional.

Modern signal processing allows delegating the image processing to the machine, which can complete it faster and accurately enough. Of course, we don’t dare to suggest that a medical professional should ever rely on any algorithm one-hundred-per cent. Think of a machine as a robot capable of doing the most tedious task of sorting the data and searching for features. In this scenario, after the computer algorithm selects potentially affected cases, the specialist can look into them more closely, and at the end, everybody benefits as the diagnosis and the treatment reaches the patient much faster”, says Maskeliūnas, who supervised the team working on the model.

Source: https://en.ktu.edu/

How To Detect Very Small Tumors

Early detection of tumors is extremely important in treating cancer. A new technique developed by researchers at the University of California, Davis, (UC Davis) offers a significant advance in using magnetic resonance imaging (MRI) to pick out even very small tumors from normal tissue.

Chemical probes that produce a signal on magnetic resonance imaging, or MRI, can be used to target and image tumors. The new research is based on a phenomenon called magnetic resonance tuning that occurs between two nanoscale magnetic elements. One acts to enhance the signal, and the other quenches it. Previous studies have shown that quenching depends on the distance between the magnetic elements. This opens new possibilities for noninvasive and sensitive investigation of a variety of biological processes by MRI.

The UC Davis team created a probe that generates two magnetic resonance signals that suppress each other until they reach the target, at which point they both increase contrast between the tumor and surrounding tissue. They call this two-way magnetic resonance tuning, or TMRET. Combined with specially developed imaging analysis software, the double signal enabled researchers to pick out brain tumors in a mouse model with greatly increased sensitivity.

It’s a significant advance,” said senior author Yuanpei Li, associate professor of biochemistry and molecular medicine at the UC Davis School of Medicine and Comprehensive Cancer Center. “This could help detect very small early-stage tumors.”

The probe developed by the UC Davis team contains two components: nanoparticles of superparamagnetic iron oxide, or SPIO, and pheophorbide a–paramagnetic manganese, or P-Mn, packaged together in a lipid envelope. SPIO and P-Mn both give strong, separate signals on MRI, but as long as they are physically close together those signals tend to cancel each other out, or quench. When the particles enter tumor tissue, the fatty envelope breaks down, SPIO and P-Mn separate, and both signals appear.

Li’s laboratory focuses on the chemistry of MRI probes and developed a method to process the data and reconstruct images, which they call double-contrast enhanced subtraction imaging, or DESI. But for expertise in the physical mechanisms, they reached out to professors Kai Liu and Nicholas Curro at the UC Davis Department of Physics (Liu is now at Georgetown University). The physicists helped elucidate the mechanism of the TMRET method and refine the technique.

The researchers tested the method in cultures of brain and prostate cancer cells and in mice. For most MRI probes, the signal from the tumor is up to twice as strong as from normal tissue – a “tumor to normal ratio” of 2 or less. Using the new dual-contrast nanoprobe, Li and colleagues could get a tumor-to-normal ratio as high as 10.

The findings are published in the journal Nature Nanotechnology.

Source: https://www.ucdavis.edu/

The Science Of BioPrinting a Human Heart

A company called Biolife4D has developed the technology to print human cardiac tissue by collecting blood cells from a patient and converting these cells to a type of stem cell called Induced Pluripotent Stem (iPS) cells. The technology could eventually be used to create thousands of much-needed hearts for transplantation.

What we’re working on is literally bioprinting a human heart viable for transplantation out of a patient’s own cells, so that we’re not only addressing the problem with the lack of [organ] supply, but by bioengineering the heart out of their own cells, we’re eliminating the rejection,Biolife4D CEO Steven Morris said during an appearance on Digital Trends Live, referring to the body’s impulse to reject a transplanted organ.

It starts with a patient’s own cells and ends with a 3D bioprinted heart that’s a precise fit and genetic match. The BIOLIFE4D bioprinted organ replacement process begins with a magnetic resonance imaging (MRI) procedure used to create a detailed three-dimensional image of a patient’s heart. Using this image, a computer software program will construct a digital model of a new heart for the patient, matching the shape and size of the original.

A “bio-ink” is created using the specialized heart cells combined with nutrients and other materials that will help the cells survive the bioprinting processHearts created through the BIOLIFE4D bioprinting process start with a patient’s own cells. Doctors safely take cells from the patient via a blood sample, and leveraging recent stem cell research breakthroughs, BIOLIFE4D plans to reprogram those blood cells and convert them to create specialized heart cells.

Bioprinting is done with a 3D bioprinter that is fed the dimensions obtained from the MRI. After printing, the heart is then matured in a bioreactor, conditioned to make it stronger and readied for patient transplant.

Source: https://biolife4d.com/

Geno-Economics

Biologists don’t understand the link between genes and behavior, so why should economists? Many outside critics of economics complain that it’s not a science. In response, most economists have steadily improved the quality of their empirical methods. But a few economists are taking a different tack by borrowing from natural science. Neuroeconomists, for example, have put experimental subjects in MRI machines to measure how their brains behave when they’re making economic decisions, in order to search for clues to the mechanisms behind everyday behavior. Recently, a few economists have sought to use genetics to augment their understanding of economic outcomes. This has become possible thanks to the advent of cheap genome sequencing and widely available databases of human genetic information. But there are a number of reasons this line of research is likely to do more harm than good, at least until biologists better understand the ways that genes affect human development.

One major foray into the field of geno-economics came from Quamrul Ashraf of Williams College and Oded Galor of Brown University. In a 2013 paper published in the American Economic Review — arguably the most prestigious journal in economics — Ashraf and Galor argue that genetic diversity exerts a big influence on economic developmentToo much diversity, they argue, and people don’t trust each other. Too little diversity, and original ideas are hard to come by. Thus, the optional amount of diversity is a happy medium — a population homogeneous enough to cooperate, but diverse enough to have originality. Looking at genetic data, they found that Europe and East Asia tend to have a medium range of genetic diversity, with Africa on the high end and the indigenous populations of the Americas and Oceania on the low end. Since Europe and East Asia contain the most industrialized nations, Ashraf and Galor concluded that the data supported their hypothesis. Another geno-economics paper was recently published in the Journal of Public Economics — also a top journal — by economists Daniel Barth, Nicholas Papageorge and Kevin Thom. Rather than tackling the broad sweep of international development as Ashraf and Galor did, Barth et al. tried to use genetics to explain differences in individual wealth, using the Health and Retirement Study, which measures wealth and various other financial information. For each individual, they obtained a polygenic score — a number that represents statistical differences in a large set of genes — that tends to be correlated with educational attainment. Restricting their analysis only to people of European descent, Barth et al. then showed that this genetic statistic is correlated with more success in investing, even after controlling for things like income and education. They concluded that genetic endowments help some people invest more successfully, leading them to build up wealth over time.

Source: https://www.bloomberg.com/

Telepathy For Real Within 8 Years

Imagine if telepathy were real. If, for example, you could transmit your thoughts to a computer or to another person just by thinking them. In just eight years it will be, says Openwater founder Mary Lou Jepsen, thanks to technology her company is working on.

Jepsen is a former engineering executive at Facebook, Oculus, Google[x] (now called X) and Intel. She’s also been a professor at MIT and is an inventor on over 100 patents. And that’s the abbreviated version of her resume. Jepsen left Facebook to found Openwater in 2016. The San Francisco-based start-up is currently building technology to make medical imaging less expensive.

I figured out how to put basically the functionality of an M.R.I. machine — a multimillion-dollar M.R.I. machine — into a wearable in the form of a ski hat,” Jepson said, though she does not yet have a prototype completed.

Current M.R.I. technology can already see your thoughts: “If I threw [you] into an M.R.I. machine right now … I can tell you what words you’re about to say, what images are in your head. I can tell you what music you’re thinking of,” says Jepsen. “That’s today, and I’m talking about just shrinking that down.”

One day Jepsen’s tech hat could “literally be a thinking cap,” she says. Jepsen explains the goal is for the technology to be able to both read and to output your own thoughts, as well as read the thoughts of others. In iconic Google vocabulary, “the really big moonshot idea here is communication with thought — with telepathy,”adds Jepsen.