Duke Engineers have developed a new type of microscope that uses a bowl studded with LED lights of various colors and lighting schemes produced by machine learning
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.
The new microscope taught itself the best way to light up red blood cells to spot malaria parasites within. Compared to a traditional microscope (top), the red blood cell images created by the new microscope (bottom) contain more noise, but the malaria parasites are lit up by bright patches due to the lighting conditions.
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
- Breakthrough in prostate cancer researchon August 3, 2022 at 6:54 am
Researchers from the CHUM Research Centre and the Polytechnique Montreal have discovered a new technique to detect an aggressive form of prostate cancer.
- Scaling up cell imagingon August 3, 2022 at 5:24 am
Scientists have learned a lot about human biology by looking at cells under a microscope, but they might not notice tiny differences between cells or even know what they're looking for. Researchers at ...
- Trying Out A 3D Printed Microscope Lens Adapteron August 1, 2022 at 5:00 pm
If you want to take pictures of tiny things close up, you need a macro lens. Or a microscope. [Nicholas Sherlock] thought “Why not both?” He designed a 3D-printed microscope lens adapter that ...
- Can AI help Congress legislate more efficiently?on July 29, 2022 at 4:08 pm
Lawmakers on the House Select Committee on the Modernization of Congress are interested in exploring just what AI might be able to help them accomplish.
- Automating A Microscope For CNC Micrographson July 25, 2022 at 5:00 pm
He needed a new microscope, one designed for photography, that had a scanning stage, and ideally one that was cheap. He ended up choosing a microscope from the 80s. Did it meet all his qualifications?
- European or not, make sure your AI business sticks to EU data lawson July 25, 2022 at 6:38 am
As we enter a new era defined by artificial intelligence and machine learning, the very foundation of many modern technologies is being put under a microscope by policymakers. That foundation?
- Finding Features from Microscopes to Simulations Via Ensemble Learning and Atomic Manipulationon July 21, 2022 at 5:00 pm
Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, TN, USA Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA ...
- News tagged with laser beamson July 14, 2022 at 5:01 pm
Shiqi Zhang spent many months sitting alone in a dark room, staring intently into the lens of a confocal microscope as ... have developed a new machine-learning platform that makes the algorithms ...
- Tissue Analyzer 3Scan Builds Out Machine Learning With $14M Series Bon July 10, 2022 at 5:00 pm
The device, called a knife edge scanning microscope, creates three-dimensional ... Now, 3Scan plans to apply machine learning to its automated process, helping potentially deliver more accurate ...
- Microscope News and Researchon July 5, 2022 at 5:00 pm
How do cancer cells differ from healthy cells? A new machine learning algorithm called "ikarus" knows the answer, reports a team led by MDC bioinformatician Altuna Akalin in the journal Genome ...
via Bing News
The Latest on: Smart microscope
- How can managed service providers remain competitive?on August 3, 2022 at 2:56 am
Computer hardware, for example, can be ready for collection from a centrally located “smart locker” in as little as 60 seconds (a current real-world average of 45 minutes), representing an ...
- Arrow Smart Terms aims to protect partner liquidityon August 1, 2022 at 11:30 pm
Changing demands on partners and growing fears of inflation have led the distributor to come up with its own solution.
- TikToker allegedly gets a good look at McDonald's water under a microscope: 'Kind of expected'on August 1, 2022 at 10:52 am
TikToker @closeintel, aka the “Micro Man”, is famous for viewing random things from hot dogs to Chick-fil-A under his microscope. In one video, he alleged he picked up a cup of ice water from ...
- Using Your Phone As A Microscope On The Electronics Workbenchon July 30, 2022 at 5:00 pm
I’m guessing that almost any smartphone made over the last few ... so why does a real 2D LCD microscope not have this problem? I am theorising when I say this, but I suspect that the solution ...
- Smart Laboratories - The Future of the Labon July 30, 2022 at 3:29 am
When Dutch optometrist Zacharias Janssen invented the first microscope in the 16th century, it transformed the face of science. Since then, technology has advanced in leaps and bounds. Over the ...
- Veterinary Microscopes Market 2022 Analysis | Trends, Size, Share, Company Overview, Growth and Forecast by 2028 Latest Research Reporton July 24, 2022 at 10:25 pm
Besides, this new smart report on global and regional industry ... This report focuses on global Veterinary Microscopes Market Share, also covers the segmentation data of other regions in regional ...
- Best digital microscopeon July 8, 2022 at 2:22 am
What you’ll love: This affordable device can connect to your personal computer, Mac or smartphone and is powerful enough for 1,000x magnification. The microscope includes eight LEDs and a knob ...
via Bing News