System Bits: Nov. 21

Lamborghini-MIT hypercar; algorithm out-diagnoses radiologists; cellphone-based microscope.


MIT-Lamborghini to develop electric car
Members of the MIT community were recently treated to a glimpse of the future as they passed through the Stata Center courtyard as the Lamborghini Terzo Millenio (Third Millennium) was in view, which is an automobile prototype for the third millennium.

Lamborghini is relying on MIT to make its cars of the future operate on electricity, while maintaining the aesthetic standards and high-powered mechanical elements that make operating these luxurious sports cars so thrilling. Pictured is the Terzo Millenio, or Third Millennium, concept car from Lamborghini marks an ambitious collaboration between the Italian automaker and researchers at MIT.
Source: MIT

The ability to deliver high peak power and regenerate kinetic energy, all while ensuring the ability to release and harvest electric power, can be attributed to the work of MIT associate professor of chemistry Mircea Dinca, MIT reported.
The Terzo Millenio aims to be self-healing and electric — concepts that today seem about as far-fetched as the hovercrafts in “Back to the Future II”’s imagining of 2015. However, in reality, this technology is as attainable as it is visionary.

“The new Lamborghini collaboration allows us to be ambitious and think outside the box in designing new materials that answer energy storage challenges for the demands of an electric sport vehicle,” Dinca said.

Lamborghini said it is relying on MIT to make its cars of the future operate on electricity, while maintaining the aesthetic standards and high-powered mechanical elements that make operating these luxurious sports cars so thrilling for those who drive them.

To this end, in October 2016, Automobili Lamborghini began a three-year partnership with MIT that will grant Lamborghini exclusive rights to emerging research related to battery storage and materials science.

Lamborghini said it’s mission for the partnership is to rewrite the rules on super sports cars by addressing energy storage systems, innovative materials, propulsion systems, visionary design, and ‘emotion.’ By incorporating research from Dinca and John Hart, associate professor of mechanical engineering, who will investigate new carbon fiber and composite materials that could enable the complete body of the car to somehow be used as a battery system, the hope is that this ambitious, visually stunning prototype will become a reality.

The researchers expect the collaboration to lead to new technologies in the fields of the energy accumulation systems, materials science, and manufacturing, and MIT students will have the opportunity to perform research at Automobili Lamborghini.

Diagnosing pneumonia better than radiologists
According to Stanford University researchers, a deep learning algorithm has been developed that evaluates chest X-rays for signs of disease. In just over a month of development, they are reporting that the algorithm outperformed expert radiologists at diagnosing pneumonia.

The algorithm can diagnose up to 14 types of medical conditions and is able to diagnose pneumonia better than expert radiologists working alone.

Radiologist Matthew Lungren, left, meets with graduate students Jeremy Irvin and Pranav Rajpurkar to discuss the results of detections made by the algorithm. A tool the researchers developed along with the algorithm produced these images, which are similar to heat maps and show the areas of the X-ray most indicative of pneumonia. Source: Stanford University

Pranav Rajpurkar, a graduate student in the Stanford Machine Learning Group and co-lead author of a paper on the algorithm said, “Interpreting X-ray images to diagnose pathologies like pneumonia is very challenging, and we know that there’s a lot of variability in the diagnoses radiologists arrive at. We became interested in developing machine learning algorithms that could learn from hundreds of thousands of chest X-ray diagnoses and make accurate diagnoses.”

The work uses a public dataset initially released by the National Institutes of Health Clinical Center on Sept. 26. That dataset contains 112,120 frontal-view chest X-ray images labeled with up to 14 possible pathologies. It was released in tandem with an algorithm that could diagnose many of those 14 pathologies with some success, designed to encourage others to advance that work. As soon as they saw these materials, the Machine Learning Group – a group led by Andrew Ng, adjunct professor of computer science – knew it had found its next research direction.

The researchers, working with Matthew Lungren, an assistant professor of radiology, had four Stanford radiologists independently annotate 420 of the images for possible indications of pneumonia. The researchers have chosen to focus on this disease, which brings 1 million Americans to the hospital each year, according to the Centers for Disease Control and Prevention, and is especially difficult to spot on X-rays, the researchers said. In the meantime, the Machine Learning Group team got to work developing an algorithm that could automatically diagnose the pathologies.

Within a week the researchers had an algorithm that diagnosed 10 of the pathologies labeled in the X-rays more accurately than previous state-of-the-art results. In just over a month, their algorithm could beat these standards in all 14 identification tasks. In that short time span, CheXNet also outperformed the four Stanford radiologists in diagnosing pneumonia accurately.

Cellphone-based microscope helps treat river blindness
A smartphone-based microscope technology developed by UC Berkeley researchers has been used to help treat river blindness, a debilitating disease caused by parasitic worms. The technology, called LoaScope, uses video from a smartphone-connected microscope to automatically detect and quantify infection by parasitic worms in a drop of blood. 

River blindness is a disease caused by a parasitic worm found primarily in Africa. The worm (Onchocerca volvulus) is transmitted to humans through bites of infected black flies. Left untreated, infections in the eye can lead to blindness. Complicating matters, the medication to treat the infection, ivermectin, can be fatal when a patient also has high blood levels of another parasitic worm, called Loa loa. 

In a paper published in the New England Journal of Medicine, scientists describe how the LoaScope can provide fast and effective testing for Loa loa parasites in the blood. Using the LoaScope to analyze the blood of volunteers from villages in Cameroon, doctors were able to successfully treat more than 15,000 patients with ivermectin without serious complications.

Study co-author and Berkeley bioengineering professor Daniel Fletcher, whose lab invented the technology said, “This is not just a step forward for efforts to eliminate river blindness, but it is a demonstration that mobile microscopy — based on a mobile phone — can safely and effectively expand access to healthcare. This work sets the stage for expanding the use of mobile microscopy to improve diagnosis and treatment of other diseases, both in low-resource areas and eventually back in the U.S.”

An adult Loa loa worm.
Source: UC Berkeley

Leave a Reply

(Note: This name will be displayed publicly)