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

19 Feb 2020
New Artificial Intelligence Algorithm Boosts Quality of Brain Magnetic Resonance Imaging
 Researchers from the ICAI Group -Computational Intelligence and Image Analysis- of the University of Malaga {(UMA) Málaga, Spain) have designed a method that is capable of improving brain images obtained through magnetic resonance imaging using artificial intelligence (AI). The new model manages to increase image quality from low resolution to high resolution without distorting the patients' brain structures, using a deep learning artificial neural network - a model based on the functioning of the human brain - that "learns" this process.
Read More
17 Feb 2020
New System Combines Advanced Optical Imaging with AI Algorithm to Accurately Identify Brain Tumors
 Researchers from the NYU Grossman School of Medicine (New York, NY, USA) and the University of Michigan (Ann Arbor, MI, USA) have developed a novel method of combining advanced optical imaging with an artificial intelligence (AI) algorithm to produce accurate, real-time intraoperative diagnosis of brain tumors. The imaging technique, stimulated Raman histology (SRH), reveals tumor infiltration in human tissue by collecting scattered laser light, illuminating essential features not typically seen in standard histologic images. The microscopic images are then processed and analyzed with AI, allowing surgeons to see a predicted brain tumor diagnosis in less than three minutes. Using the same technology, after the resection, the surgeons can accurately detect and remove otherwise undetectable tumor.
Read More
10 Feb 2020
Global Medical Robotics Market to Reach USD 13.90 Billion by 2026
 The global medical robotics market is projected to grow at a double-digit CAGR from 2019 to 2026 to reach USD 13.90 billion by 2026, driven by the increasing demand for minimally invasive surgery, rising prevalence of gynecology, urology and orthopedic disorders, increasing aging population, technological innovations, growing adoption of medical robots among the population and increasing clinical trials.
Read More
04 Feb 2020
Patient Handling Equipment Market to Reach USD 12.6 Billion by 2024
 The global patient handling equipment market is projected to grow at a CAGR of 7.2% from USD 8.9 billion in 2019 to USD 12.6 billion by 2024, driven mainly by the rising geriatric population, high risk of injuries to caregivers during manual handling of patients, and regulations for ensuring the safety of healthcare personnel during manual lifting processes. However, continued difficulties in handling bariatric patients are expected to limit the market growth to some extent.
Read More
30 Jan 2020
Study Finds Most Healthcare Institutions Plan to Use AI and Develop Own AI Algorithm
 A new study of healthcare professionals has revealed that Artificial Intelligence (AI) is widely expected to drive important benefits across the health system, from increasing efficiency to improving patient outcomes, but may also be the key to making healthcare more human. AI’s benefits range from increasing the amount of time clinicians can spend with patients and on cross-care team collaboration to enhancing the ability to deliver preventative care.
Read More
30 Jan 2020
Quest Diagnostics Acquires Blueprint Genetics
 Quest Diagnostics (Secaucus, NJ, USA), a provider of diagnostic information services, has acquired Blueprint Genetics (Helsinki, Finland), a specialty genetic testing company with expertise in gene variant interpretation based on next generation sequencing (NGS) and proprietary bioinformatics. Together, Quest and Blueprint Genetics will broaden access to actionable insights in genetic and rare diseases, improving patient care and pharmaceutical drug research and development.
Read More
27 Jan 2020
JNJ Acquires Remaining Stake in Verb Surgical
 Johnson & Johnson (New Brunswick, N.J., USA) has acquired the remaining stake in Verb Surgical Inc. (Santa Clara, CA, USA), following a successful strategic collaboration with Verily, an Alphabet company. Verb Surgical's robotics and data science capabilities, combined with Johnson & Johnson's health care leadership and global reach, aim to make medical interventions smarter, less invasive and more personalized.
Read More
22 Jan 2020
Global Point of Care Testing (POCT) Market to Reach USD 46.7 Billion by 2024
 The global point of care testing (POCT) market is expected to surpass USD 37 billion by 2025, driven mainly by the migration of POCT from the hospital environment to a range of medical environments, including the workplace, home, disaster care and most recently, convenience clinics. POCT now appears to be headed for a bigger role in diagnosis and monitoring patient care. Additionally, growing awareness about early disease diagnosis and prevention has stimulated the demand for POCT for detecting cancer and infectious disease in the early stages. Moreover, the rising incidence of infectious diseases and chronic conditions, such as cardiovascular diseases and diabetes in the developing countries such as India and China, is stimulating the demand for POCT services.
Read More
16 Jan 2020
Radiomic Algorithm Predicts if Patient’s Cancer Can Return 10 Years After Treatment
 A new study by researchers at Penn Medicine (Philadelphia, PA, USA) has found that Magnetic Resonance Imaging (MRI) and an emerging field of medicine called radiomics — which uses algorithms to extract a large amount of features from medical images — could help to characterize the heterogeneity of cancer cells within a tumor and allow for a better understanding of the causes and progression of a person’s individual disease.
Read More
Copyright © 2000-2020 TradeMed.com. All rights reserved. | Terms And Conditions