User login
Image by Peter H. Seeberger
Scientists say they have devised a technique that can be used to diagnose malaria quickly and with clinically relevant accuracy.
The technique involves using computer deep learning and light-based, holographic scans to spot malaria-infected cells from an untouched blood sample without any help from a human.
The scientists believe this could form the basis of a fast, reliable malaria test that could be given by most anyone, anywhere in the field.
The team described the method in PLOS ONE.
“With this technique, the path is there to be able to process thousands of cells per minute,” said study author Adam Wax, PhD, of Duke University in Durham, North Carolina.
“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.”
The new technique is based on a technology called quantitative phase spectroscopy. As a laser sweeps through the visible spectrum of light, sensors capture how each discrete light frequency interacts with a sample of blood.
The resulting data captures a holographic image that provides a wide array of information that can indicate a malaria infection.
“We identified 23 parameters that are statistically significant for spotting malaria,” said study author Han Sang Park, a doctoral student in Dr Wax’s lab.
For example, as the disease progresses, red blood cells decrease in volume, lose hemoglobin, and deform as the parasite within grows larger. This affects features such as cell volume, perimeter, shape, and center of mass.
“However, none of the parameters were reliable more than 90% of the time on their own,” Park said. “So we decided to use them all.”
“To be adopted, any new diagnostic device has to be just as reliable as a trained field worker with a microscope,” Dr Wax said. “Otherwise, even with a 90% success rate, you’d still miss more than 20 million [malaria] cases a year.”
To get a more accurate reading, Dr Wax and his colleagues turned to deep learning—a method by which computers teach themselves how to distinguish between different objects.
Feeding data on healthy and diseased cells into a computer enabled the deep learning program to determine which sets of measurements at which thresholds most clearly distinguished healthy cells from diseased cells.
When the scientists put the resulting algorithm to the test with hundreds of cells, the algorithm was able to correctly spot malaria more than 95% of the time—a number the team believes will increase as more cells are used to train the program.
The team noted that, because the technique breaks data-rich holograms down to just 23 numbers, tests can be easily transmitted in bulk. They said this is important for locations that often do not have reliable, fast internet connections.
Dr Wax and his colleagues are now 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.
Dr Wax has also received funding to begin exploring the use of the technique for spotting cancerous cells in blood samples. 
Image by Peter H. Seeberger
Scientists say they have devised a technique that can be used to diagnose malaria quickly and with clinically relevant accuracy.
The technique involves using computer deep learning and light-based, holographic scans to spot malaria-infected cells from an untouched blood sample without any help from a human.
The scientists believe this could form the basis of a fast, reliable malaria test that could be given by most anyone, anywhere in the field.
The team described the method in PLOS ONE.
“With this technique, the path is there to be able to process thousands of cells per minute,” said study author Adam Wax, PhD, of Duke University in Durham, North Carolina.
“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.”
The new technique is based on a technology called quantitative phase spectroscopy. As a laser sweeps through the visible spectrum of light, sensors capture how each discrete light frequency interacts with a sample of blood.
The resulting data captures a holographic image that provides a wide array of information that can indicate a malaria infection.
“We identified 23 parameters that are statistically significant for spotting malaria,” said study author Han Sang Park, a doctoral student in Dr Wax’s lab.
For example, as the disease progresses, red blood cells decrease in volume, lose hemoglobin, and deform as the parasite within grows larger. This affects features such as cell volume, perimeter, shape, and center of mass.
“However, none of the parameters were reliable more than 90% of the time on their own,” Park said. “So we decided to use them all.”
“To be adopted, any new diagnostic device has to be just as reliable as a trained field worker with a microscope,” Dr Wax said. “Otherwise, even with a 90% success rate, you’d still miss more than 20 million [malaria] cases a year.”
To get a more accurate reading, Dr Wax and his colleagues turned to deep learning—a method by which computers teach themselves how to distinguish between different objects.
Feeding data on healthy and diseased cells into a computer enabled the deep learning program to determine which sets of measurements at which thresholds most clearly distinguished healthy cells from diseased cells.
When the scientists put the resulting algorithm to the test with hundreds of cells, the algorithm was able to correctly spot malaria more than 95% of the time—a number the team believes will increase as more cells are used to train the program.
The team noted that, because the technique breaks data-rich holograms down to just 23 numbers, tests can be easily transmitted in bulk. They said this is important for locations that often do not have reliable, fast internet connections.
Dr Wax and his colleagues are now 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.
Dr Wax has also received funding to begin exploring the use of the technique for spotting cancerous cells in blood samples.
Image by Peter H. Seeberger
Scientists say they have devised a technique that can be used to diagnose malaria quickly and with clinically relevant accuracy.
The technique involves using computer deep learning and light-based, holographic scans to spot malaria-infected cells from an untouched blood sample without any help from a human.
The scientists believe this could form the basis of a fast, reliable malaria test that could be given by most anyone, anywhere in the field.
The team described the method in PLOS ONE.
“With this technique, the path is there to be able to process thousands of cells per minute,” said study author Adam Wax, PhD, of Duke University in Durham, North Carolina.
“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.”
The new technique is based on a technology called quantitative phase spectroscopy. As a laser sweeps through the visible spectrum of light, sensors capture how each discrete light frequency interacts with a sample of blood.
The resulting data captures a holographic image that provides a wide array of information that can indicate a malaria infection.
“We identified 23 parameters that are statistically significant for spotting malaria,” said study author Han Sang Park, a doctoral student in Dr Wax’s lab.
For example, as the disease progresses, red blood cells decrease in volume, lose hemoglobin, and deform as the parasite within grows larger. This affects features such as cell volume, perimeter, shape, and center of mass.
“However, none of the parameters were reliable more than 90% of the time on their own,” Park said. “So we decided to use them all.”
“To be adopted, any new diagnostic device has to be just as reliable as a trained field worker with a microscope,” Dr Wax said. “Otherwise, even with a 90% success rate, you’d still miss more than 20 million [malaria] cases a year.”
To get a more accurate reading, Dr Wax and his colleagues turned to deep learning—a method by which computers teach themselves how to distinguish between different objects.
Feeding data on healthy and diseased cells into a computer enabled the deep learning program to determine which sets of measurements at which thresholds most clearly distinguished healthy cells from diseased cells.
When the scientists put the resulting algorithm to the test with hundreds of cells, the algorithm was able to correctly spot malaria more than 95% of the time—a number the team believes will increase as more cells are used to train the program.
The team noted that, because the technique breaks data-rich holograms down to just 23 numbers, tests can be easily transmitted in bulk. They said this is important for locations that often do not have reliable, fast internet connections.
Dr Wax and his colleagues are now 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.
Dr Wax has also received funding to begin exploring the use of the technique for spotting cancerous cells in blood samples.