Machine learning microscope adapts lighting to improve diagnosis

November 20, 2019

DURHAM, N.C. -- 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."
"Learned Sensing: Jointly Optimized Microscope Hardware for Accurate Image Classification," Alex Muthumbi, Amey Chaware, Kanghyun Kim, Kevin C. Zhou, Pavan Chandra Konda, Richard Chen, Benjamin Judkewitz, Andreas Erdmann, Barbara Kappes, and Roarke Horstmeyer. Biomedical Optics Express, Vol. 10, No. 11, 1 November 2019. DOI: 10.1364/BOE.10.006351

Duke University

Related Malaria Articles from Brightsurf:

Clocking in with malaria parasites
Discovery of a malaria parasite's internal clock could lead to new treatment strategies.

Breakthrough in malaria research
An international scientific consortium led by the cell biologists Volker Heussler from the University of Bern and Oliver Billker from the UmeƄ University in Sweden has for the first time systematically investigated the genome of the malaria parasite Plasmodium throughout its life cycle in a large-scale experiment.

Scientists close in on malaria vaccine
Scientists have taken another big step forward towards developing a vaccine that's effective against the most severe forms of malaria.

New tool in fight against malaria
Modifying a class of molecules originally developed to treat the skin disease psoriasis could lead to a new malaria drug that is effective against malaria parasites resistant to currently available drugs.

Malaria expert warns of need for malaria drug to treat severe cases in US
The US each year sees more than 1,500 cases of malaria, and currently there is limited access to an intravenously administered (IV) drug needed for the more serious cases.

Monkey malaria breakthrough offers cure for relapsing malaria
A breakthrough in monkey malaria research by two University of Otago scientists could help scientists diagnose and treat a relapsing form of human malaria.

Getting to zero malaria cases in zanzibar
New research led by the Johns Hopkins Center for Communication Programs, Ifakara Health Institute and the Zanzibar Malaria Elimination Program suggests that a better understanding of human behavior at night -- when malaria mosquitoes are biting -- could be key to preventing lingering cases.

Widely used malaria treatment to prevent malaria in pregnant women
A global team of researchers, led by a research team at the Liverpool School of Tropical Medicine (LSTM), are calling for a review of drug-based strategies used to prevent malaria infections in pregnant women, in areas where there is widespread resistance to existing antimalarial medicines.

Protection against Malaria: A matter of balance
A balanced production of pro and anti-inflammatory cytokines at two years of age protects against clinical malaria in early childhood, according to a study led by ISGlobal, an institution supported by ''la Caixa'' Foundation.

The math of malaria
A new mathematical model for malaria shows how competition between parasite strains within a human host reduces the odds of drug resistance developing in a high-transmission setting.

Read More: Malaria News and Malaria Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to