– Researchers at Duke University’s Pratt School of Engineering have developed a machine learning algorithm that can increase the resolution of optical coherence tomography (OCT), an imaging technology similar to ultrasound that uses light instead of soundwaves.
The new technique increased the resolution of OCT in all directions, even in a living patient, and could improve images obtained in the OCT industry for cardiology, oncology, and other medical fields.
With OCT, a probe shoots a beam of light into a tissue, and determines the boundaries of the features within based on the delays of the light waves as they bounce back. The process is repeated at many horizontal positions over the surface of the tissue to get a full picture of these structures.
OCT provides much better resolution of depth than lateral direction, so it works best when structures contain mostly flat layers. When structures within the tissue are shaped irregularly, the features become blurred, which reduces the image’s quality.
“An historic issue with OCT is that the depth resolution is typically several times better than the lateral resolution,” said Joseph Izatt, the Michael J. Fitzpatrick Professor of Engineering at Duke.
“If the layers of imaged tissues happen to be horizontal, then they’re well defined in the scan. But to extend the full power of OCT for live imaging of tissues throughout the body, a method for overcoming the tradeoff between lateral resolution and depth of imaging was needed.”
To create OCT images with high lateral resolution, researchers have previously relied on a method called holography, which involves measuring the electromagnetic field reflected back from the object. It’s a tedious approach, requiring that the sample and imaging tool stay completely still during the measurement.
“This has been achieved in a laboratory setting,” said Izatt, who also holds an appointment in ophthalmology at the Duke University School of Medicine. “But it is very difficult to achieve in living tissues because they live, breathe, flow and change.”
The team built a machine learning algorithm that creates a map of the way light bends as it passes through the model. Researchers used TensorFlow, a software created by Google, to implement the method.
“One of the many reasons why I find this work exciting is that we were able to borrow tools from the machine learning community and apply them not only to post-process OCT images, but also to combine them in a novel way and extract new information,” said Kevin Zhou, a doctoral student at the Pratt School of Engineering.
“I think there are many applications of these deep learning libraries such as TensorFlow, outside of the standard tasks such as image classification and segmentation.”
Researchers are already exploring the possibility of using the technology for other parts of the body. The team was able to take tissue samples of the bladder or trachea of a mouse and rotate the samples 360 degrees beneath an OCT scanner. The algorithm was able to successfully create a map of each sample’s refractive index.
Although the study used samples already removed from the body, the research group is confident that the tool can be adapted to use in a living person.
“Rather than rotating the tissue, a scanning probe developed for this technique could rotate the angle of the beam on the tissue surface,” said Zhou.
This technique has promising implications for the future of eye imaging, researchers noted.
“Capturing high-resolution images of the conventional outflow tissues in the eye is a long-sought-after goal in ophthalmology,” said Sina Farsiu, the Paul Ruffin Scarborough Associate Professor of Engineering at Duke. “Having an OCT scanner with this type of lateral resolution would be very important for early diagnosis and finding new therapeutic targets for glaucoma.”
Going forward, the technology could also make a positive impact on other areas of medical imaging.
“OCT has already revolutionized ophthalmic diagnostics by advancing noninvasive microscopic imaging of the living human retina,” said Izatt. “We believe that with further advances, the high impact of this technology may be extended not only to additional ophthalmic diagnostics, but to imaging of pathologies in tissues accessible by endoscopes, catheters, and bronchoscopes throughout the body.”
Credit: Google News