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.”
Learn more: Machine Learning Microscope Adapts Lighting to Improve Diagnoses
The Latest on: Machine learning microscope
- The researchers, with Google and other partners, spent a decade deciphering 1 cubic millimeter of tissue.on May 13, 2024 at 7:24 am
About 10 years ago, a small piece of human brain arrived in the lab of Dr. Jeff Lichtman at Harvard. It came directly from an operating room of a nearby hospital, where it was excised from an epilepsy ...
- Harvard and Google unveil groundbreaking brain mapon May 12, 2024 at 9:31 am
The collaboration between scientists from Harvard and artificial intelligence experts from Google has led to the most sophisticated neuron mapping study to date, marking a significant milestone in the ...
- MIT Technology Reviewon May 9, 2024 at 4:20 pm
A small brain sample was sliced into 5,000 pieces, and machine learning helped stitch it back together.
- Scientists find 57,000 cells and 150m neural connections in tiny sample of human brainon May 9, 2024 at 11:01 am
Harvard researchers teamed up with Google to analyse the makeup of the brain, much of which is not yet understood ...
- See the most detailed map of human brain matter ever createdon May 9, 2024 at 11:01 am
All that complexity is on display in a study documenting the construction of this bit of comprehensive brain map or “connectome,” published May 9 in the journal Science. The first connectome was of a ...
- UChicago scientists use machine learning to turn cell snapshots dynamicon May 2, 2024 at 5:00 am
Pritzker School of Molecular Engineering study hopes to use machine learning to boost cancer, immunology research ...
- AI-Powered Microscope Revolutionizes Material Analysison April 25, 2024 at 6:57 am
This microscope uses AI and automation to analyze ... imaging without requiring constant operator interaction. Using machine learning integration to create functional relationships between ...
- An optical brain-machine interface through the development of protein, microscope, and deep learning toolson March 26, 2024 at 12:00 am
Our work focuses on developing an optical brain-machine interface capable ... read and write neural activity, optical microscopes that can record neural activity from large volumes of brain tissue, ...
- Artificial Intelligence and Machine Learning – News and Featureson August 19, 2023 at 10:53 am
Engineers at Duke University have developed a microscope that adapts its lighting angles ... to recognize and treat the very first cellular changes. Researchers used a machine-learning approach to ...
- electron microscopeon May 31, 2023 at 5:01 pm
When all you’ve got is a hammer, everything looks like a nail. And when you’ve got a scanning electron microscope, everything must look like a sample that would be really, really interesting ...
via Bing News
The Latest on: Smart microscope
- People horrified after seeing what a maggot looks like under a microscopeon May 10, 2024 at 4:54 am
Some people feel uneasy just thinking about maggots - so it's no surprise many have been left 'horrified' after seeing what they look like under a microscope. Despite their "ugly" appearance ...
- ‘Mathematical microscope’ could diagnose Alzheimer’s disease earlyon May 9, 2024 at 9:46 am
Researchers uncover a mechanism behind 'working memory' – the brain's short-term storage – and its potential decline in Alzheimer's.
- Mathematical microscope sheds light on efficient memory formation even during sleepon May 8, 2024 at 10:27 pm
UCLA Health researchers have discovered a mechanism that creates memories while reducing metabolic cost, even during sleep.
- 'Mathematical microscope' reveals novel, energy-efficient mechanism of working memory that works even during sleepon May 8, 2024 at 8:13 am
M. Keck Center for Neurophysics and the Center for Physics of Life at UCLA. To crack this problem, Mehta and his coauthors devised a novel approach: a "mathematical microscope." In the world of ...
- Explore the hidden world with the PhoneMicro5 portable phone microscopeon May 6, 2024 at 4:59 pm
You can transform your smart phone camera into a powerful microscope, enabling you to explore the hidden wonders of the world at any time. With the PhoneMicro5 portable phone microscope is ...
- 'Hacks' Season 3 will make you miss 'The Other Two'on May 2, 2024 at 2:00 am
Whatever you want to call it, it's how I feel about Hacks Season 3. Ever since Hacks' first season, I thought it was hysterical. I loved Deborah and Ava's generational sparring, especially their love ...
- Purdue-created technology makes 3D microscopes easier to use, less expensive to manufactureon April 30, 2024 at 11:10 am
Liming Chen, who will earn his PhD in mechanical engineering from Purdue in May 2024, operates a 3D microscope, which uses an optical technique called fringe projection to create a high-resolution 3D ...
- News tagged with scanning electron microscopeon April 29, 2024 at 5:00 pm
Scientists have found a way to transform metal waste into a highly efficient catalyst to make hydrogen from water, a discovery that could make hydrogen production more sustainable. An ...
- The best microscopes for students in 2024on April 10, 2024 at 1:00 pm
Here are the microscopes to help them get started. This classic microscope is made with students’ needs in mind. It can connect to a laptop or other screen for group viewing, helping large ...
- Exploring the Unseen The Best Microscopes for Kids in 2024on March 4, 2024 at 2:32 am
Popular Science Smartphone Microscope (Age 6+): Embrace the power of technology with the Popular Science Smartphone Microscope, suitable for children aged 6 and above. By harnessing the camera ...
via Bing News