Health Life

Deep learning accurately stains digital biopsy slides

Activation maps of neural network model for digital staining of tumors. Credit: Massachusetts Institute of Technology

Tissue biopsy slides stained using hematoxylin and eosin (H&E) dyes are a cornerstone of histopathology, especially for pathologists needing to diagnose and determine the stage of cancers. A research team led by MIT scientists at the Media Lab, in collaboration with clinicians at Stanford University School of Medicine and Harvard Medical School, now shows that digital scans of these biopsy slides can be stained computationally, using deep learning algorithms trained on data from physically dyed slides.

Pathologists who examined the computationally stained H&E images in a blind study could not tell them apart from traditionally stained slides while using them to accurately identify and grade prostate cancers. What’s more, the slides could also be computationally “de-stained” in a way that resets them to an original state for use in future studies, the researchers conclude in their May 20 study published in JAMA Network Open.

This process of computational digital staining and de-staining preserves small amounts of tissue biopsied from cancer patients and allows researchers and clinicians to analyze slides for multiple kinds of diagnostic and prognostic tests, without needing to extract additional tissue sections.

“Our development of a de-staining tool may allow us to vastly expand our capacity to perform research on millions of archived slides with known clinical outcome data,” says Alarice Lowe, an associate professor of pathology and director of the Circulating Tumor Cell Lab at Stanford University, who was a co-author on the paper. “The possibilities of applying this work and rigorously validating the findings are really limitless.”

The researchers also analyzed the steps by which the deep learning neural networks stained the slides, which is key for clinical translation of these deep learning systems, says Pratik Shah, MIT

Health article

Mind and Body Practices for Older Adults

In 2012, the American College of Rheumatology issued recommendations for using pharmacologic and nonpharmacologic approaches for osteoarthritis (OA) of the hand, hip, and knee. The guidelines conditionally recommend tai chi, along with other non-drug approaches such as manual therapy, walking aids, and self-management programs, for managing knee OA. Acupuncture is also conditionally recommended for those who have chronic moderate-to-severe knee pain and are candidates for total knee replacement but are unwilling or unable to undergo surgical repair.

Current clinical practice guidelines from the American Academy of Sleep Medicine recommend psychological and behavioral interventions, such as stimulus control therapy or relaxation therapy, or cognitive behavioral therapy for insomnia (CBT-I), in the treatment of chronic primary and secondary insomnia for adults of all ages, including older adults. 

Overall, research suggests that some mind and body approaches, such as yoga, tai chi, and meditation-based programs may provide some benefit in reducing common menopausal symptoms.

There have only been a few studies on the effects of tai chi on cell-mediated immunity to varicella zoster virus following vaccination, but the results of these studies have shown some benefit.

There is evidence that tai chi may reduce the risk of falling in older adults. There is also some evidence that tai chi may improve balance and stability with normal aging and in people with neuro-degenerative conditions, including mild-to-moderate Parkinson’s disease and stroke.

There is some evidence that suggests mind-and-body exercise programs such as tai chi and yoga may have the potential to provide modest enhancements of cognitive function in older adults without cognitive impairment.

Source link

Health Life

AI tool gives doctors a new look at the lungs in treating COVID-19

Princeton researchers have developed a diagnostic tool that uses AI to analyze chest X-rays for COVID-19 lung damage. The tool could help doctors triage patients and better allocate scarce resources. Credit: Princeton University

Spurred by the COVID-19 pandemic, Princeton researchers have developed a diagnostic tool to analyze chest X-rays for patterns in diseased lungs. The new tool could give doctors valuable information about a patient’s condition, quickly and cheaply, at the point of care.

Jason Fleischer, professor of electrical engineering and the project’s principal investigator, said he was inspired to create the tool after reading about COVID-19’s devastating range of attacks. As hospitals have been overrun with patients, doctors have observed two basic types of lung damage, one more immediately life-threatening than the other. Treatment can differ between the types, so distinguishing the two could improve care and better allocate scarce resources.

While current differentiation methods involve expensive and time-consuming procedures, such as computed tomography (CT) scans, Fleischer’s machine learning model looks at a simple X-ray image and finds patterns that are too subtle even for the expert human eye. This tool would give doctors a new measure for determining the type and severity of COVID-19 pneumonia. And the process, on the ground, is simple.

“Importantly, there is no change in practice,” Fleischer said. “The technician doesn’t have to do anything differently. Hospitals don’t have to do any new procedure. With the X-rays they already have—and routinely take—we can give them this extra information.”

Fleischer and graduate student Mohammad Tariqul Islam posted a paper detailing their work on medrxiv (pronounced med archive), a server for scientists to share results in the form of early drafts while a paper undergoes the formal editorial process. At the time of this writing, Fleischer’s paper “Distinguishing L and H phenotypes of COVID-19 using a

Health article

Heat Stroke and Hot Cars

Since 2017, the total number of children in the US that died from heatstroke after being left in a car is 72. Most of these children are under three years of age.   

As an emergency physician practicing in Florida, I’ve seen the devastating impact of heatstroke countless times. The loss of these children’s lives is tragic but avoidable. 

Florida ranked second to Texas with 72 deaths recorded from 1998-2015. When adjusted for per capita (population per one million), Florida is the fifth-worst state in the nation.

This mind staggering research comes directly from Mr. Jan Null, CCM, of the Department of Meteorology and Climate Science at San Jose University. “This danger exists despite public education, efforts, and lobbying for laws against leaving children unattended in vehicles,” Null said.

Consider the human science: What is heatstroke? Heatstroke is defined as a condition by which the body develops hyperthermia (fever), during which the body experiences a failure of the thermoregulatory system.   

We manage heat exposure by way of the brain, circulatory system, and skin – in a way similar to a cooling system of a car.  Humans cool by ways of convection and evaporation of sweat.  Severe hyperthermia is defined as prolonged exposure to a body temperature of 104° F (40° C) or higher.  

During this syndrome, the body first develops thirst, dehydration, and perspires. As the temperature of the infant raises above 104° F, it can lead to the inability to perspire, confusion, mental agitation, and eventual coma. The body’s maximum temperature before protein starts to break down and organ failure ensues is approximately 106° F.  

Children and infants are more susceptible to heat illness due to their innate inability to regulate heat when compared to adults. The important point is that the danger is a function of not only the