Lifeboat Foundation

An important #AI report for breast cancer leading to the potential of sparing chemotherapy for many. The 1st comprehensive analysis of both cancerous and non-cancerous tissue in hundreds of thousands of patient tissues->HiPS score https://nature.com/articles/s41591-023-02643-7

Deep learning enables comprehensive and interpretable scoring for breast cancer prognosis prediction, outperforming pathologists in multicenter validation and providing insight on prognostic biomarkers.

Optothermal nanotweezers are an innovative optical design method that has revolutionized classical optical techniques to capture a broad range of nanoparticles. While the optothermal temperature field can be employed for in situ regulation of nanoparticles, challenges remain in identifying their potential for regulating bionanoparticles.

To observe the synergistic effects of optothermal manipulation and Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-based biodetection, the researchers developed a combination of CRISPR-powered optothermal nanotweezers abbreviated as CRONT.

In a new report in Light: Science & Applications, Jiajie Chen and a research team in optoelectronics engineering, biomedical engineering, and physics, accomplished this by harnessing diffusiophoresis and thermo-osmotic flows for optothermal excitation by successfully enriching DNA functionalized gold nanoparticles, CRISPR-associated proteins, and DNA strands.

AI startup Hoppr teamed up with AWS to launch a new foundation model to help bring more generative AI solutions into medical imaging, the companies announced on Sunday at RSNA 2023, the annual radiology and medical imaging conference in Chicago.

The new product, named Grace, is a B2B model designed to help application developers build better AI solutions for medical images — and to build them more quickly. Along with the launch of Grace, Hoppr also announced that it received “a multi-million dollar investment” from Health2047, the American Medical Association’s venture studio.

Continue reading “AWS, Hoppr Launch Model to Accelerate Generative AI Tools in Medical Imaging” »

As boosters say AI is primed to conquer entire sectors, from military to medicine, a significant portion of the tech world is surprisingly unconvinced by its utility, according to a new survey from software development business Retool.

In the survey of 1,500 people working in tech, Retool found that a startling 51.6 percent of people think AI is overrated, while 25.1 percent think it’s underrated, and another 23.4 percent think it’s fairly rated. The people surveyed include executives, software engineers, designers, and other positions in different industries.

Particularly striking was that workers in executive roles had a more favorable view of AI while people in the technical side “skewed a little more toward overrated” — perhaps not a surprise, since many business leaders have been crowing about the potential cost savings of AI and how it could generate more revenue.

A research team led by Professor Sei Kwang Hahn and Dr. Tae Yeon Kim from the Department of Materials Science and Engineering at Pohang University of Science and Technology (POSTECH) used gold nanowires to develop an integrated wearable sensor device that effectively measures and processes two bio-signals simultaneously. Their research findings were featured in Advanced Materials.

Wearable devices, available in various forms like attachments and patches, play a pivotal role in detecting physical, chemical, and electrophysiological signals for disease diagnosis and management. Recent strides in research focus on devising wearables capable of measuring multiple bio-signals concurrently.

However, a major challenge has been the disparate materials needed for each signal measurement, leading to interface damage, complex fabrication, and reduced device stability. Additionally, these varied signal analyses require further signal processing systems and algorithms.

Easy navigation in a rugged fitness landscape.

In a recent study published in the journal Scientific Reports, researchers compare whether insulin-and non-insulin-based insulin resistance (IR) markers could predict the risk of non-alcoholic fatty liver disease (NAFLD) in obese and non-obese individuals with no history of diabetes or hepatitis.

Study: Markers of insulin resistance associated with non-alcoholic fatty liver disease in non-diabetic population. Image Credit: Jo Panuwat D / Shutterstock.com.

About 10–15% of pregnancies fail after conception has been recognized, amounting to 23 million losses a year. Chromosomal anomalies underlie many embryonic and fetal losses, but their exact frequency and localization to the embryo or placenta are still unclear. A new study published in Nature Medicine reports on a chromosomal analysis of over 1,700 spontaneous early miscarriages.

The most common period of pregnancy loss is before the ninth week, though many may occur earlier and pass unrecognized. While about 11% of women have at least one miscarriage, the proportion goes down with two or three, at 2% and 0.7. respectively.

Implants and tiny machines could eventually be working inside our bodies to help treat disease or monitor activity, but letting them communicate is tricky. Now scientists at EPFL have developed a system whereby devices can communicate by releasing molecules into a patient’s bloodstream.

Biomedical implants play a key role in healthcare, monitoring activity in organs like the heart or brain, while recent research is investigating how nanoscale robots might one day swim or crawl through the body to fight disease. But these systems have a communication issue.

Running wires through the body is not only impractical, it’s an infection risk. And wireless technologies like radio, light and Bluetooth don’t travel through human tissue very efficiently, drastically limiting their range.