En Es
Categories

Industry News

Researchers Use Machine Learning to Increase Resolution of OCT Imaging

By Medimaging International staff writers
03 Oct 2019

Image: A new technique, called optical coherence refraction tomography (OCRT), could improve medical images obtained in the multibillion-dollar OCT industry for medical fields ranging from cardiology to oncology (Photo courtesy of Pixabay).Biomedical engineers at Duke University (Durham, NC, USA) have devised a method for increasing the resolution of optical coherence tomography (OCT) down to a single micrometer scale in all directions. The new technique, called optical coherence refraction tomography (OCRT), could improve medical images obtained in the multibillion-dollar OCT industry for medical fields ranging from cardiology to oncology.

OCT is an imaging technology analogous to ultrasound that uses light rather than sound waves. A probe shoots a beam of light into a tissue and, based on the delays of the light waves as they bounce back, determines the boundaries of the features within. To get a full picture of these structures, the process is repeated at many horizontal positions over the surface of the tissue being scanned.

Since OCT provides much better resolution of depth than lateral direction, it works best when these features contain mostly flat layers. When objects within the tissue have irregular shapes, the features become blurred and the light refracts in different directions, reducing the image quality. Previous attempts at creating OCT images with high lateral resolution have relied on holography—painstakingly measuring the complex electromagnetic field reflected back from the object. While this has been demonstrated, the approach requires the sample and imaging apparatus to remain perfectly still down to the nanometer scale during the entire measurement.

However, the biomedical engineers at Duke University have taken a different approach. Instead of relying on holography, the researchers combined OCT images acquired from multiple angles to extend the depth resolution to the lateral dimension. Each individual OCT image, however, becomes distorted by the light’s refraction through irregularities in the cells and other tissue components. To compensate for these altered paths when compiling the final images, the researchers needed to accurately model how the light is bent as it passes through the sample.

To accomplish this computational feat, the biomedical engineers developed a method using “gradient-based optimization” to infer the refractive index within the different areas of tissue based on the multi-angle images. This approach determines the direction in which the given property—in this case, the refractive index—needs to be adjusted to create a better image. After several iterations, the algorithm creates a map of the tissue’s refractive index that best compensates for the light’s distortions. The method was implemented using TensorFlow, a popular software library created by Google for deep learning applications.

For proof-of-concept experiments, the researchers took tissue samples such as the bladder or trachea of a mouse, placed them in a tube, and rotated the samples 360 degrees beneath an OCT scanner. The algorithm successfully created a map of each sample’s refractive index, increasing the lateral resolution of the scan by more than 300% while reducing the background noise in the final image. While the study used samples already removed from the body, the researchers believe OCRT can be adapted to work in a living organism.

“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 researcher Kevin Zhou. “I think there are many applications of these deep learning libraries such as TensorFlow and PyTorch, outside of the standard tasks such as image classification and segmentation.”

Related Links:
Duke University



E-mail Print
FaceBook Twitter Google+ Linked in

Additional news

03 Oct 2019
New Mount Sinai BMEII Center to Focus on AI in Advanced Imaging
The Mount Sinai Health System has announced the creation of the Biomedical Engineering and Imaging Institute (BMEII), the first of its kind in New York City, and one of the few in the world.
Read More
03 Oct 2019
NIH Awards USD 1.6 Million Grant to Subtle Medical
The National Institutes of Health has awarded healthcare technology company Subtle Medical a Fast-Track Small Business Innovation Research (SBIR) grant of USD 1.6 million.
Read More
01 Oct 2019
RSNA Announces Intracranial Hemorrhage AI Challenge
The Radiological Society of North America has launched its third annual artificial intelligence (AI) challenge: the RSNA Intracranial Hemorrhage Detection and Classification Challenge.
Read More
01 Oct 2019
Artificial Intelligence Accurately Predicts Radiation Treatment Side Effects
Researchers from the University of Texas MD Anderson Cancer Center have demonstrated that a sophisticated computer model can accurately predict two of the most challenging side effects associated with radiation therapy for head and neck cancer.
Read More
01 Oct 2019
Global Microfluidic Immunoassay Market to Reach USD 2 Billion by 2025
The global microfluidic immunoassay market is expected to grow at a CAGR of 12.7% from 2019 to USD 2.0 billion by 2025, driven by greater benefits offered by Lab-on-chip (LOC) over conventional quantifiable technologies, the growing need for point-of-care (POC) in low-resource settings, and increasing research activities in the field of microfluidic technology.
Read More
27 Sep 2019
Agfa Demonstrates AI-Powered Intelligent DR Solutions at RSNA 2019
Agfa NV will present its intelligent radiography powered by the MUSICA Acquisition Workstation, the digital Nerve Center of every Agfa DR system, including the launch of a new, groundbreaking direct radiography (DR) unit at RSNA 2019, to be held December 1-6, in Chicago, IL, USA.
Read More
26 Sep 2019
FUJIFILM SonoSite Collaborates with AI2 Incubator to Improve Image Analysis
FUJIFILM SonoSite has entered into a collaboration with the Allen Institute for Artificial Intelligence for interpreting ultrasound images with artificial intelligence (AI), enabling new ultrasound applications and enhanced accuracy.
Read More
26 Sep 2019
GE Healthcare and Affibody Collaborate to Develop PET Imaging Tracers
GE Healthcare and Affibody AB have entered into a strategic collaboration to develop and commercialize Affibody-based PET imaging tracers, with initial focus on HER2 and PD-L1.
Read More
18 Sep 2019
AI Solution Supporting Wins Best New Radiology Solution Award
An FDA-cleared artificial intelligence (AI) solution that supports breast cancer detection in 3D tomosynthesis has been selected as the winner of “Best New Radiology Solution” Award in the 2019 MedTech Breakthrough Awards program.
Read More
Copyright © 2000-2019 TradeMed.com. All rights reserved. | Terms And Conditions