Holographic Imaging Technique Diagnoses Malaria Automatically, Accurately

A quantitative phase spectroscopy (QPS) system that incorporates digital holography has been used to spot malaria-infected cells from a simple, untouched blood sample without any help from a human. The technique employs machine learning algorithms and has been shown accurate in detecting malaria infection 97 to 100 percent of the time. The research could form the basis of a fast, reliable test for malaria that could be given by most anyone, anywhere in the field.

In the QPS-based system, a laser sweeps through the visible spectrum, and sensors capture how each discrete light frequency interacts with a sample of red blood cells (RBCs). The resulting data is captured in a holographic image that provides information indicating whether a malarial infection is present.

Four cells as seen under a microscope in different stages of infection from a malarial parasite. The first image is uninfected, but as the parasite matures in the images from left to right, the cell deforms. Courtesy of Adam Wax, Duke University.
Researchers at Duke University segmented RBCs using optical phase thresholds, and refocused the samples to enable quantitative comparison of phase images. Refocused images were analyzed to extract 23 morphological descriptors based on the phase information.

To improve automated analysis of RBCs, the researchers constructed machine learning algorithms using the morphological descriptors of each cell taken from the quantitative phase images.

"We identified 23 parameters that are statistically significant for spotting malaria," said researcher Han Sang Park. "However, none of the parameters were reliable more than 90 percent of the time on their own, so we decided to use them all," said Park.

"To be adopted, any new diagnostic device has to be just as reliable as a trained field worker with a microscope," said professor Adam Wax. "Otherwise, even with a 90 percent success rate, you'd still miss more than 20 million cases a year."

The algorithms combine all of the calculated physical parameters to distinguish cells more effectively. They enable identification of malaria infection with a high level of accuracy and provide the ability to discriminate between stages of the infection.

Four cells in different stages of infection from a malarial parasite as analyzed by a new algorithm. As the parasite matures in the images from left to right, the cell deforms, as indicated by the analysis. The algorithm uses various measures of the cell's physical characteristics to determine whether or not it is infected. Courtesy of Adam Wax, Duke University.

Overall, this methodology points to a significant clinical potential of using quantitative phase imaging to detect and stage malaria infection without staining or expert analysis.

"With this technique, the path is there to be able to process thousands of cells per minute," said Wax. "That's a huge improvement to the 40 minutes it currently takes a field technician to stain, prepare and read a slide to personally look for infection."

Wax and Park are looking to develop the technology into a diagnostic device through a startup company called M2 Photonics Innovations. They hope to show that a device based on this technology would be accurate and cost-efficient enough to be useful in the field.

The research was published in PLOS ONE (doi: 10.1371/journal.pone.0163045).