Genomic Companies Collaborate to Develop Facial Analysis Technology Pathologists Might Eventually Use to Diagnose Rare Genetic Disorders
Phenotypic data combined with artificial intelligence provides a new biomarker for genetic laboratories to use when diagnosing disease
Researchers are demonstrating that facial analysis and facial recognition technology can play a useful role in helping pathology and medical laboratory scientists diagnose disease. This is just the latest example of how advances in different technologies can add new sources of biomarkers for clinical laboratories.
Biomarkers used by clinical laboratories and anatomic pathologists are usually biological substances or states that can be measured during testing either in vivo or in vitro. However, clinical laboratories may soon be working with biomarkers based on measurable aspects of external human anatomy. One such biomarker employs facial analysis and facial recognition technology to produced phenotypic data that could help pathologists diagnose rare genetic disorders. A human phenotype is data comprised of a person’s “observable characteristics or traits.”
Phenotypic Data from Photographs
Three genomics companies: FDNA, GeneDx, and Blueprint Genetics, are collaborating on a unique project, dubbed Face2Gene Labs. They are using a facial recognition application called Face2Gene developed by FDNA. The application uses artificial intelligence (AI) and phenotyping technology to extract data from facial photographs of patients. The data is then examined and compared to a database of hundreds of thousands of patterns that were generated from photos of patients with known rare genetic disorders. The algorithm then compiles a list of possible diagnoses. The goal is to produce phenotypic data that clinicians can transmit in real-time directly to medical laboratories for analysis.
“Trying to diagnose patients with genetic sequencing is like searching for a pin in a 22,000-needle haystack,” stated Dekel Gelbman, CEO, FDNA, in a news release. “By providing accurate phenotypic and clinical data to the lab directly at the point of genetic interpretation, we are truly realizing the promise of precision medicine. And, with the power of artificial intelligence behind it, clinicians will be pointed toward potential diagnoses that they may have never otherwise considered.”
The Face2Gene application developed by FDNA uses artificial intelligence to compare digital photographs of patients’ faces against hundreds of thousands of stored patterns to help clinicians identify genetic disorders in children. (Photo copyright: FDNA.)
Solomon goes on to praise GeneDx and Blueprint Genetics as examples of innovative and renowned labs adopting technology that will lead the way in pinpointing rare disease and promote further medical advancements.
“This is an important collaboration for several reasons,” states Ben Solomon, MD, a Clinical Geneticist and Managing Director of GeneDx, in the news release. “It’s a great way to leverage clinical and genetic information and machine learning approaches to find answers for the clinicians, patients, and families GeneDx serves. Aside from providing answers, this integration will make the diagnostic testing process easier, smoother, and more enjoyable for clinicians.”
85% Increase in Diagnostic Yield with Addition of Phenotypic Data
A recent multi-center study called PEDIA (short for Prioritization of Exome Data by Image Analysis) looked into the accuracy of genetic testing when using FDNA’s Face2Gene tool. The study, conducted by researchers at the Berlin Institute of Health and Charité University of Medicine in Berlin, showed promising results of the collaboration.
“We estimate that the addition of phenotypic features [encoded in HPO terms] increases the diagnostic yield to about 60% [from 25% without],” stated Peter Krawitz, MD, PhD, and Principal Investigator for PEDIA. “When adding facial analysis, FDNA’s technology, to that process, the diagnostic yield increases to more than 85%,” he explained in the FDNA news release.
The Rarity Paradox and Diagnosing Genetic Disorders in Children
According to Global Genes, a rare disease patient advocacy non-profit organization, one in 10 Americans (approximately 30 million people) suffer from a rare genetic disorder. These disorders also affect the same percentage of people worldwide, or about 350 million people. There are more than 7,000 distinct rare diseases known to exist and approximately 80% of those illnesses are caused by faulty genes. In addition, about half of the people affected by rare genetic illnesses are children.
“We call it the rarity paradox,” stated Gelbman in an article published in Wired. “Each rare disease in itself affects very few people, but on aggregate the effect is pretty staggering.”
The three companies hope their collaboration will help clinicians determine faster, more accurate diagnoses, while diminishing anxiety among patients and their families regarding the unknowns of rare genetic disorders.
“Since 2012, Blueprint Genetics has been developing technological innovations in sequencing and clinical interpretation to improve the quality and performance of rare disease diagnostics,” noted Tero-Pekka Alastalo, MD, PhD, President, Chief Medical Officer of Blueprint Genetics, in the FDNA news release. “It’s great to see how these innovations are now helping the genetics community and patients suffering from inherited disorders. Combining these technological innovations with our transparent approach to diagnostics and next generation phenotyping tools like Face2Gene represents the next steps forward in molecular genetic diagnostics.”
Pathology groups and clinical laboratories are advised to monitor this exciting development in genomic research. It illustrates how unrelated technologies, such as facial analysis software, could soon be used for diagnostic purposes to detect the presence of genetic disorders, and to determine the best therapies for patients. Labs will want to be prepared to engage with clinicians who adopt this technology and to answer patients’ questions about it.
—JP Schlingman
Related Information:
FDNA Announces Collaboration with GeneDx and Blueprint Genetics in the Launch of Face2Gene LABS
FDNA Expands Facial Analysis Reach to 2,000 Syndromes
Groups Explore Facial Analysis Software for Inherited Disease Diagnosis, Research
Winners of the Qualcomm Tricorder XPRIZE for Medical Laboratory Testing Were Announced in April, Five Years After the Competition Began
More than 312 teams applied for the completion and the prize-winning hand-held device uses clinical laboratory assays to diagnose up to 34 different medical conditions
Star Trek fans among clinical laboratory manager and pathologist will be excited to learn that the winners of the Qualcomm Tricorder XPRIZE were announced earlier this year, five years after the contest began. The purpose of the XPRIZE competition was to challenge teams to create a mobile integrated diagnostic device that weighed less than five pounds and had the ability to monitor health metrics and diagnose 13 specific health conditions. The premise for the contest was inspired by the Star Trek medical tricorder that was first conceptualized on the television show “Star Trek” in the 1960s.
In the popular science-fiction show, the tricorder was a multifunctional hand-held device used for sensor scanning, data analysis, and recording data. The name “tricorder” was an abbreviation for the full name of the gadget, “tri-function recorder,” which referred to the three primary functions of the device.
Based in Culver City, Calif, the XPRIZE Foundation is a non-profit organization that creates and oversees prestigious technological competitions for the purpose of prompting innovations that could benefit humanity.
Handheld Device That Can Perform Multiple Clinical Laboratory Assays
The Qualcomm Tricorder XPRIZE competition was launched in January 2012. Participants had until August 2013 to register for the contest. The qualifying round was held the following August. Three hundred and twelve teams entered the competition. Qualifiers had until March 2015 to design and build their prototypes. Consumer testing on the products began in September 2016 and the winners were announced in April 2017.
The top prize of $2.6 million was awarded to Final Frontier Medical Devices, the team led by Basil Harris, MD, an emergency room physician with a PhD in Materials Engineering led the team, along with his network engineer brother, George Harris.
Basil Leaf Technologies, founded by Basil Harris, MD, PhD, FACEP (above center); and his brother George, a Network Engineer (second from left), is a medical technology company headquartered in Paoli, Pa. Their winning entry, called DxtER (pronounced Dexter), is a small FDA-approved group of medical devices that enable consumers to diagnose illnesses at home or remotely and share that data with healthcare providers. (Photo copyright: XPRIZE Foundation.)
The collection of FDA-approved devices that make up the “tricorder” includes sensors designed to gather data about vital signs, body chemistry, and biological functions. The DxtER device walks patients through the self-diagnosis of 34 medical conditions. The instruments include:
· A compact spirometer that calculates lung strength;
· A test kit for Mononucleosis;
· A heart rate monitor;
· A respiration monitor;
· The DxtER Orb, a digital stethoscope that also serves as a thermometer; and
· An artificial intelligence (AI) “engine” that diagnoses medical conditions.
DxtER communicates with a tablet and/or smartphone-based app. Since the components are FDA-approved, diagnostic test results can be taken directly to healthcare professionals.
“You can [receive the] results and take them to the ER or to your physician or whoever’s helping you, and they can build off those results,” George Harris explained in an Engadget article. “They don’t have to start back at square one. They can jump off at that point and move on with their healthcare.”
Basil Leaf Technologies’ DxtER “tricorder” (above) enables the user to self-diagnose up to 34 medical conditions. Each individual component is FDA-approved, so hospital physicians can rely on the accuracy of the test results. (Photo copyright: XPRIZE Foundation.)
According to the contest website, “at the heart of DxtER is an artificially intelligent engine that learned to diagnose by integrating years of experience in clinical emergency medicine with data analysis from actual patients having a variety of medical conditions and outcomes.”
“It is very exciting that our vision of mobile, personalized patient-centric healthcare is getting closer to becoming a reality thanks to the great work of the Qualcomm Tricorder XPRIZE teams,” declared Paul E. Jacobs, PhD, Executive Chairman of Qualcomm Incorporated (NASDAQ:QCOM) in an XPRIZE press release. “Creating technology breakthroughs in an industry as complex as healthcare is quite a milestone, and what these teams accomplished is a great stepping stone to making mobile healthcare a viable option across the world.”
DxtER Functions Like a Mobile Medical Laboratory
In addition to the $2.6-million prize, Qualcomm Foundation is giving the Basil Leaf team $3.8 million to further develop the device. This amount includes a:
· $2.5 million proposal grant to the University of California San Diego; and a
· $1.6-million gift from the Roddenberry Foundation to adapt the tricorder for hospital use in the developing world.
The XPRIZE competition required contestants to create a tricorder device that could accurately diagnose 13 health conditions. This included 10 core conditions and a choice of three elective health conditions. The devices also needed to be able to acquire five real-time vital signs:
1. Blood pressure;
2. Heart rate;
3. Oxygen saturation;
4. Respiratory rate; and
5. Temperature.
The 10 core conditions the devices had to be able to identify were:
1. Anemia;
3. Chronic Obstructive Pulmonary Disease;
5. Leukocytosis;
6. Pneumonia;
7. Otitis;
8. Sleep Apnea;
9. Urinary Tract Infection; and
10. Absence of condition.
The contest also required participants to choose three elective conditions from the following list:
· Human Immunodeficiency Virus (HIV) screen;
· Hypertension;
· Hypothyroidism/Hyperthyroidism;
· Melanoma;
· Pertussis;
· Shingles, and
· Strep throat.
It is notable that the TriCorder XPRIZE—with its $2.6 million prize—generated entries from 312 teams. Pathologists and clinical laboratory managers can take this high number of entrants as a sign that the ongoing advances in technology are poised to support a new generation of very small medical lab testing devices. Thus, miniaturized diagnostic technologies, when combined with more sophisticated computing chips and software are making it simpler and more feasible to pack multiple diagnostic instruments into a hand-held package.
—JP Schlingman
Related Information:
Final Frontier Medical Devices
The Contest to Build the First Star Trek Tricorder Has a Winner [Infographic]
XPRIZE Winner Says its Tricorder is Better Than ‘Star Trek’
Underdog Team Wins Millions in Competition to Make Real-Life Tricorder
Star Trek’s “Tricorder” Medical Scanner Just Got Closer to Becoming a Reality
Qualcomm Tricorder XPRIZE Goes to US Team for Device Fusing AI, IoT, Health
Star Trek’s Tricorder, Realized? This Device Uses AI to Diagnose Medical Conditions
Canadian Researchers Develop Low-Cost, Lens-Free Light-Field Microscope; Could Make Anatomic Pathology Labs Portable and More Affordable
Second-generation spectral fusion microscope captures light-field images in full color using artificial intelligence and mathematical models of light to develop large-scale 3D images
Researchers in Canada have developed an inexpensive, lens-free microscope that uses artificial intelligence (AI) and mathematical models of light to develop three-dimensional (3D) images. This invention has the potential to make the clinical pathology laboratory portable and affordable. And the advancement could improve access to anatomic pathology services in remote regions and less developed countries that cannot afford conventional microscopic diagnostic equipment.
New Microscope a Boon to Pathology Laboratories Worldwide
This spectral light-fusion microscope, developed by a pair of researchers from the University of Waterloo in Ontario, uses second-generation spectral light-fusion technology for capturing light-field images in full color.
“The several-hundred-dollar microscope has no lens, and uses artificial intelligence and mathematical models of light to develop 3D images at a large scale,” states a University of Waterloo news release.
The new microscope’s low price point provides a major advantage over larger traditional microscopes that require a skilled technician to electronically “stitch” together multiple images using a machine costing several hundred thousand dollars to get the same 3D effect.
“In medicine, we know that pathology is the gold standard in helping to analyze and diagnose patients, but that standard is difficult to come by in areas that can’t afford it. This technology has the potential to make pathology labs more affordable for communities that currently don’t have access to conventional equipment,” Associate Professor of Engineering Alexander Wong, PhD, PEng, said in the University of Waterloo news release.
Wong, Associate Professor and Canada Research Chair in Medical Imaging, and Systems Design Engineer Farnoud Kazemzadeh, PhD, a Postdoctoral Fellow at Environmental Bio-Detection Products and Adjunct Professor at University of Waterloo, led the research.
“Currently the technology required to operate a pathology lab is quite expensive and is largely restricted to places such as Europe and North America, which can afford them,” Kazemzadeh noted in the news release. “It would be interesting to see what a more affordable mobile pathology lab could achieve.”
Alexander Wong, PhD, PEng (above left), and Farnoud Kazemzadeh, PhD (above right), of the University of Waterloo in Ontario, Canada, developed their new spectral light-fusion microscope to make pathology more affordable for communities that cannot access conventional equipment. They patented the first version of the microscope last year and expect their technology to be a boon to mobile anatomic pathology labs. (Photo copyright: University of Waterloo.)
Wong and Kazemzadeh described the first generation of their instrument in a research paper published in Nature Scientific Reports. In that paper, the pair demonstrated for the first time that laser light-field fusion phase contrast microscopy could detect particles at nanometer resolutions.
“We introduced a wide-field lens-free on-chip phase contrast microscopy instrument capable of detecting particles at the nanometer resolution. The instrument does not require hologram magnification, specialized sample preparation, or the use of synthetic aperture- or lateral shift-based techniques to accomplish detection of nanoparticles,” they wrote.
The researchers understand the potential of their invention to expand access to pathology. They describe the microscope as “extremely simple and economical to implement, allowing for democratization and proliferation of such systems at every level of healthcare, industry, education, or research.”
The researchers’ new second-generation device can construct nanometer-resolution images with an ultra-wide field-of-view. “The microscope captures light fields that can be analyzed using the mathematical models of light and artificial intelligence to construct 3D images that are around 100 times larger than the 2D images captured by traditional microscopes,” reported The Engineer, a United Kingdom-based publication.
Shaping the Future of Clinical Laboratories
The spectral light-fusion microscope is one example of research teams exploring how to use different technologies for the assessment of human tissue. Another example that we covered in a previous Dark Daily e-briefing involved the development of a lens-free smartphone microscope by UCLA researchers. That microscope produces holographic images of tissue samples that enable pathologists to view cancer and other abnormalities at the cellular level with the same accuracy as larger and more expensive optical microscopes.
The discipline of pathology and laboratory medicine is evolving to embrace technologies that were science fiction yesterday, but today are science fact. These technologies will continue to shape the clinical laboratory industry for years to come.
—Andrea Downing Peck
Related Information:
Lens-free Microscope Enables Full-Color Pathology at Low Cost
Artificial Intelligence-driven Imaging Research Makes Diagnosing Disease Easier
Laser Light-field Fusion for Wide-field Lens-Free On-chip Phase Contrast Microscopy of Nanoparticles
Technologies on IBM’s 5-in-5 List Could Impact Pathology and Clinical Laboratories
This year, one of IBM’s closely-watched picks of the technologies most likely to have the greatest impact on society is the medical lab-on-a-chip
Clinical laboratory testing and diagnostics are one of the five technologies included in IBM’s 2017 list of the technologies it predicts will have the greatest impact on society during the next five years. Of equal interest to medical laboratory professionals is that several of the other technologies included in IBM’s list have the potential be used in medical laboratories and anatomic pathology groups.
IBM Research, corporate research laboratory for parent company IBM (NYSE:IBM), has more than 3,000 researchers working in 12 labs on six continents. Each year the lab releases a list of five technologies it forecasts will have the greatest influence on how our bodies, minds, society, and the planet, develop over the next five years. The list is called “5-in-5” and has been released annually for the past 10 years by the tech giant. (more…)
