A smartphone and new software could help save infants born preterm

November 20, 2018

WASHINGTON -- Worldwide, preterm birth is a leading cause of death for children under five-years-old. A new algorithm combined with a handheld, smartphone-based device could aid health care workers in remote locations to estimate degrees of prematurity for affected infants. Such information can be critical for administering life-saving treatments.

The new method is based on previous clinical studies showing that gestational age can be calculated from the density of blood vessels in a specific region of the eye. In The Optical Society (OSA) journal Biomedical Optics Express, the researchers report that their automated method for analyzing video of the eye in most cases outperformed a manual method for determining the gestational age of 124 newborns.

"We invented a fully automatic, machine learning algorithm that uses images acquired with an inexpensive, portable smartphone-based device to classify the gestational age of a newborn," said Arjun D. Desai from Duke University, first author of the paper. "We expect the algorithm to be useful for remote and point-of-care gestational age estimation of premature newborns in low-income countries without the need for medical experts."

The researchers have made software using the new algorithm open source and freely available online. In collaboration with Jennifer B. Griffin of RTI International, the software will be further tested and fine-tuned during an upcoming large-scale clinical trial in sub-Saharan Africa and South Asia, where more than 60 percent of the world's preterm births occur. The trial is being funded by the Bill and Melinda Gates Foundation.

"Our work demonstrates that machine learning approaches combined with inexpensive, noninvasive optical imaging systems can address resource-intensive, complex global health problems," said the paper's senior author Sina Farsiu, from the Departments of Biomedical Engineering and Ophthalmology at Duke University.

No expert needed

The new approach involves using an ophthalmoscope -- a handheld instrument used to inspect the eye -- attached to the lens of a smartphone camera to acquire video of blood vessels in a part of the eye known as the anterior lens capsule. To remove the need for an expert to capture images, the researchers developed an algorithm that automatically parses through video to identify the highest quality frame and the region of interest for analysis.

Once the video is captured, the system applies computational techniques including convolutional neural networks and machine learning algorithms to assess image features in the region of interest and estimate the gestational age. These artificial intelligence approaches allow the computer system to learn from data and improve with experience.

The researchers tested their new approach on a group of 124 newborns in the U.S. They compared their automated method to the best performing manual method, which involves manually selecting the highest quality frame in the video, identifying the area showing the anterior lens capsule, and then applying a model of the relationship between the density of blood vessels and gestational age. They performed both methods on newborns that were six gestational ages: less than or equal to 33, 34, 35, 36, 37 and 38 weeks. The automatic method performed as well as or better than the manual method at all the gestational ages except for 33 weeks.

Expanding to other parts of the world

"Our work is a first step to developing a fully automatic pipeline for determining gestational age that is accurate and robust to differences across newborns," said Desai. "If needed, we will fine-tune our algorithm using data from populations with different geographical, racial and socioeconomic backgrounds."

During the upcoming clinical trial, researchers plan to collect videos from newborns in low-income countries to see how well the new method works for these children. They expect that the automated imaging analysis method combined with other noninvasive imaging biomarkers will obtain the best results.
-end-
Paper: A. D. Desai, C. Peng, L. Fang, D. Mukherjee, A. Yeung, S. J. Jaffe, J. B. Griffin, S. Farsiu, "Open-source, machine and deep learning-based automated algorithm for gestational age estimation through smartphone lens imaging," Biomed. Opt. Express, volume 9, issue 12, pp. 6038-6052 (2018).

DOI: 10.1364/BOE.9.006038

About Biomedical Optics Express

Biomedical Optics Express is OSA's principal outlet for serving the biomedical optics community with rapid, open-access, peer-reviewed papers related to optics, photonics and imaging in the life sciences. The journal scope encompasses theoretical modeling and simulations, technology development, and biomedical studies and clinical applications. It is published by The Optical Society and edited by Christoph Hitzenberger, Medical University of Vienna. Biomedical Optics Express is an open-access journal and is available at no cost to readers online at OSA Publishing.

About The Optical Society

Founded in 1916, The Optical Society (OSA) is the leading professional organization for scientists, engineers, students and business leaders who fuel discoveries, shape real-life applications and accelerate achievements in the science of light. Through world-renowned publications, meetings and membership initiatives, OSA provides quality research, inspired interactions and dedicated resources for its extensive global network of optics and photonics experts. For more information, visit osa.org.

Media Contact:

mediarelations@osa.org

The Optical Society

Related Blood Vessels Articles from Brightsurf:

Biofriendly protocells pump up blood vessels
In a new study published today in Nature Chemistry, Professor Stephen Mann and Dr Mei Li from Bristol's School of Chemistry, together with Associate Professor Jianbo Liu and colleagues at Hunan University and Central South University in China, prepared synthetic protocells coated in red blood cell fragments for use as nitric oxide generating bio-bots within blood vessels.

Specific and rapid expansion of blood vessels
Upon a heart infarct or stroke, rapid restoration of blood flow, and oxygen delivery to the hypo perfused regions is of eminent importance to prevent further damage to heart or brain.

Flexible and biodegradable electronic blood vessels
Researchers in China and Switzerland have developed electronic blood vessels that can be actively tuned to address subtle changes in the body after implantation.

Lumpy proteins stiffen blood vessels of the brain
Deposits of a protein called ''Medin'', which manifest in virtually all older adults, reduce the elasticity of blood vessels during aging and hence may be a risk factor for vascular dementia.

Cancer cells take over blood vessels to spread
In laboratory studies, Johns Hopkins Kimmel Cancer Center and Johns Hopkins University researchers observed a key step in how cancer cells may spread from a primary tumor to a distant site within the body, a process known as metastasis.

Novel function of platelets in tumor blood vessels found
Scientists at Uppsala University have discovered a hitherto unknown function of blood platelets in cancer.

Blood vessels can make you fat, and yet fit
IBS scientists have reported Angiopoietin-2 (Angpt2) as a key driver that inhibits the accumulation of potbellies by enabling the proper transport of fatty acid into general circulation in blood vessels, thus preventing insulin resistance.

Brothers in arms: The brain and its blood vessels
The brain and its surrounding blood vessels exist in a close relationship.

Feeling the pressure: How blood vessels sense their environment
Researchers from the University of Tsukuba discovered that Thbs1 is a key extracellular mediator of mechanotransduction upon mechanical stress.

Human textiles to repair blood vessels
As the leading cause of mortality worldwide, cardiovascular diseases claim over 17 million lives each year, according to World Health Organization estimates.

Read More: Blood Vessels News and Blood Vessels Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.