Prototype microscope teaches itself the best illumination settings for diagnosing malaria
Engineers at Duke University have developed a microscope that adapts its lighting angles, colors and patterns while teaching itself the optimal settings needed to complete a given diagnostic task.
In the initial proof-of-concept study, the microscope simultaneously developed a lighting pattern and classification system that allowed it to quickly identify red blood cells infected by the malaria parasite more accurately than trained physicians and other machine learning approaches.
The results appear online on November 19 in the journal Biomedical Optics Express.
“A standard microscope illuminates a sample with the same amount of light coming from all directions, and that lighting has been optimized for human eyes over hundreds of years,” said Roarke Horstmeyer, assistant professor of biomedical engineering at Duke.
“But computers can see things humans can’t,” Hortmeyer said. “So not only have we redesigned the hardware to provide a diverse range of lighting options, we’ve allowed the microscope to optimize the illumination for itself.”
Rather than diffusing white light from below to evenly illuminate the slide, the engineers developed a bowl-shaped light source with LEDs embedded throughout its surface. This allows samples to be illuminated from different angles up to nearly 90 degrees with different colors, which essentially casts shadows and highlights different features of the sample depending on the pattern of LEDs used.
The researchers then fed the microscope hundreds of samples of malaria-infected red blood cells prepared as thin smears, in which the cell bodies remain whole and are ideally spread out in a single layer on a microscope slide. Using a type of machine learning algorithm called a convolutional neural network, the microscope learned which features of the sample were most important for diagnosing malaria and how best to highlight those features.
The algorithm eventually landed on a ring-shaped LED pattern of different colors coming from relatively high angles. While the resulting images are noisier than a regular microscope image, they highlight the malaria parasite in a bright spot and are correctly classified about 90 percent of the time. Trained physicians and other machine learning algorithms typically perform with about 75 percent accuracy.
“The patterns it’s picking out are ring-like with different colors that are non-uniform and are not necessarily obvious,” said Horstmeyer. “Even though the images are dimmer and noisier than what a clinician would create, the algorithm is saying it’ll live with the noise, it just really wants to get the parasite highlighted to help it make a diagnosis.”
Horstmeyer then sent the LED pattern and sorting algorithm to another collaborator’s lab across the world to see if the results were translatable to different microscope setups. The other laboratory showed similar successes.
“Physicians have to look through a thousand cells to find a single malaria parasite,” said Horstmeyer. “And because they have to zoom in so closely, they can only look at maybe a dozen at a time, and so reading a slide takes about 10 minutes. If they only had to look at a handful of cells that our microscope has already picked out in a matter of seconds, it would greatly speed up the process.”
The researchers also showed that the microscope works well with thick blood smear preparations, in which the red blood cells form a highly non-uniform background and may be broken apart. For this preparation, the machine learning algorithm was successful 99 percent of the time.
According to Horstmeyer, the improved accuracy is expected because the tested thick smears were more heavily stained than the thin smears and exhibited higher contrast. But they also take longer to prepare, and part of the motivation behind the project is to cut down on diagnosis times in low-resource settings where trained physicians are sparse and bottlenecks are the norm.
With this initial success in hand, Horstmeyer is continuing to develop both the microscope and machine learning algorithm.
A group of Duke engineering graduate students has formed a startup company SafineAI to miniaturize the reconfigurable LED microscope concept, which has already earned a $120,000 prize at a local pitch competition.
Meanwhile, Horstmeyer is working with a different machine learning algorithm to create a version of the microscope that can adjust its LED pattern to any specific slide it’s trying to read.
“We’re basically trying to impart some brains into the image acquisition process,” said Horstmeyer. “We want the microscope to use all of its degrees of freedom. So instead of just dumbly taking images, it can play around with the focus and illumination to try to get a better idea of what’s on the slide, just like a human would.”
The Latest on: Machine learning microscope
- Seoul National University Working on Creating Synergy by Combining Artificial Intelligence with Various Studieson October 6, 2020 at 7:41 pm
Park Jung-won, who is a professor at Seoul National University’s School of Chemical and Biological Engineering, materialized 2D images obtained from transmission electron microscope, which is the bes ...
- Combining AI and Nanotechnology to Create Robot-Assisted Molecular Manipulationon October 5, 2020 at 5:06 am
While using scanning tunneling microscopes have proved efficient in moving molecules ... which facilities the movement of a diverse range of molecules. A specific type of machine learning, known as ...
- Utah County-based company Pollen Sense providing real-time data for seasonal allergy suffererson September 29, 2020 at 10:41 am
“I almost went blind staring into a microscope counting pollen one ... the air and get the focusing right, and they used machine-learning algorithms to differentiate between pollen particles ...
- Utah County-based company Pollen Sense providing real-time data for seasonal allergy suffererson September 29, 2020 at 7:52 am
Those with seasonal allergies no longer have to be left in the dust, according to one Utah company. While anyone can find hour-by-hour weather updates and forecasts with the swipe of a screen, data ...
- Global 3D Machine Vision Market By Offering, By Product, By Application, By Industry Vertical, By Region, Industry Analysis and Forecast, 2020 - 2026on September 28, 2020 at 4:10 pm
Additionally, it is possible to develop machine learning solutions on embedded ... launched the world’s first 4K ultra-high accuracy microscope, the VHX-7000. This has been marked as the 5th ...
- AI learns to trace neuronal pathwayson September 28, 2020 at 8:15 am
Harbor Laboratory scientists dramatically improved the efficiency of automated methods for tracing neuronal connections. They taught a computer to recognize different parts of neurons, then used the ...
- Nav, a Machine Learning enhanced Financing Platform for SMEs, Adds Real-Time Business Data Analytics, Other Major Updateson September 24, 2020 at 10:08 am
As explained in the release, the new capabilities have been developed to enhance the firm’s “intelligent” machine learning or ML technology ... problem that’s currently under a “national microscope in ...
via Bing News
The Latest on: Smart microscope
- Android Camera Bug Under the Microscopeon October 5, 2020 at 2:25 pm
Critical Android vulnerability CVE-2019-2234 could enable attackers to take control of a victim's camera and take photos, record videos, and learn location.
- Law and older: Veteran murder investigator puts police past and present under the microscopeon October 4, 2020 at 6:00 am
The two big questions arising from that investigation is that many police forces are not that good at collaborating with other police forces. “There are often too many big egos involved, or ...
- Take 5 with Chris Gasper: Time for Ainge and the Celtics to try a changeupon October 2, 2020 at 11:23 am
But it's time for him to try one. In an NBA playoffs unlike any other, the Celtics had an ending just like several other in recent years, an exit in the Eastern Conference Finals. It’s the third time ...
- True Digital Surgery’s Robotic Digital Microscopy: Interview with Chairman and CEO Aidan Foleyon October 1, 2020 at 1:40 pm
The Aesculap Aeos Robotic Digital Microscope from True Digital Surgery and Aesculap is now available in the United States. The system consists of a robotic arm and digital displays, and the ...
- 4K Microscope To Expand From Hamilton County Schools To Other Gigabit Communitieson September 28, 2020 at 5:00 pm
The expansion of the 4K Microscope program will be possible because of a $30,000 grant that US Ignite recently awarded to Chattanooga through its National Science Foundation-funded Smart Gigabit ...
- Global 3D Machine Vision Market By Offering, By Product, By Application, By Industry Vertical, By Region, Industry Analysis and Forecast, 2020 - 2026on September 28, 2020 at 4:12 pm
Reportlinker.com announces the release of the report "Global 3D Machine Vision Market By Offering, By Product, By Application, By Industry Vertical, By Region, Industry Analysis and Forecast, 2020 - ...
- USTR puts Russia's WTO commitments under the microscopeon September 28, 2020 at 7:07 am
WTO members hope to make some progress on tough agricultural issues by their ministerial conference next year, but a big, big deal remains far on the horizon. — Xi Jinping’s “dual circulation strategy ...
- Make your smartphone a microscope with this device — Future Blinkon September 27, 2020 at 5:00 pm
is a global, multi-platform media and entertainment company. Powered by its own proprietary technology, Mashable is the go-to source for tech, digital culture and entertainment content for its ...
via Bing News