Tag Archive for: Linguraru

Children’s National brings AI into the RHD early diagnosis equation

In December of 2024, a team that included experts from Children’s National Hospital traveled to Uganda to continue work on a pilot program applying artificial intelligence (AI) to the diagnosis of rheumatic heart disease (RHD). Ugandan health care providers have been trained and equipped to acquire echocardiograms for their patients but lack expertise in consistently being able to diagnose RHD by detecting leaky heart valves. The team created a tool that uses AI to predict RHD by identifying leaky heart valves on handheld ultrasound devices, then prompts a referral for a full echocardiogram.

The goal is to find ways to help people in Uganda diagnose RHD early, before a patient is in need of surgery, and initiate antibiotics so their heart can return to normal. The team of researchers, including fellow Kelsey Brown, MD, helped to implement additional steps toward this goal in December. According to Dr. Brown, the results were excellent. After four days of seeing patients, over 450 people were screened. The AI tool has an 86% accuracy rating. After returning from Uganda, the research team plans to work on the AI tool and further improve its accuracy rating. Eventually, the vision is that this tool can roll out on a larger scale for more places around the world to access it.

Craig Sable, MD, Marius Linguraru, DPhil, MA, MSc, and Pooneh Roshanitabrizi, PhD, from our Sheikh Zayed Institute, who developed the AI algorithms, worked in partnership with the Rheumatic Heart Disease Research Collaborative (RRCU) in Uganda. This trip was also made possible thanks to a grant funded through the Children’s National Global Health Initiative. Special thank you to our AI partner, US2.AI, who made the deployment of the AI models onto a tablet that provided real-time results, possible.

Global expert consensus defines first framework for building trustworthy AI in health care

Illustration of a brain, stethoscope and computer chip

The guidelines are the first globally acknowledged framework for developing and deploying health care AI applications and gauging whether the information they generate can be trusted or not.

More than 100 international experts in the application of artificial intelligence (AI) in health care published the first set of consensus guidelines that outline criteria for what it means for an AI tool to be considered trustworthy when implemented in health care settings.

The guidelines, published in the journal the BMJ, are the first globally acknowledged framework for developing and deploying health care AI applications and gauging whether the information they generate can be trusted or not.

What this means

Called the FUTURE-AI framework, the consensus guidelines are organized based on six guiding principles:

  • Fairness
  • Universality
  • Traceability
  • Usability
  • Robustness
  • Explainability

The cadre of experts reviewed and agreed upon a set of 30 best practices that fall within the six larger categories. These practices address technical, clinical, socio-ethical and legal aspects of trustworthy AI. The recommendations cover the entire lifecycle of health care AI: design, development and validation, regulation, deployment and monitoring.

The authors encourage researchers and developers to take these recommendations into account in the proof-of-concept phase for AI-driven applications to facilitate future translation to clinical practice.

Why it matters

“Patients, clinicians, health organizations and authorities need to know that information and analysis generated by AI can be trusted, or these tools will never make the leap from theoretical to real world application in a clinical setting,” says Marius George Linguraru, DPhil, MA, MSc, Connor Family Professor for Research and Innovation in the Sheikh Zayed Institute for Surgical Innovation at Children’s National Hospital and co-author of the guidelines. “Bringing so many international and multi-disciplinary perspectives together to outline the characteristics of a trustworthy medical AI application is part of what makes this work unique. It is my hope that finding such broad consensus will shed light on the greater good  AI can bring to clinics and help us avoid problems before they ever impact patients.”

The FUTURE-AI consortium was founded by Karim Lekadir, PhD, ICREA Research Professor at the University of Barcelona in 2021 and now comprises 117 interdisciplinary experts from 50 countries representing all continents, including AI scientists, clinical researchers, biomedical ethicists and social scientists. Over a 2-year period, the consortium established these guiding principles and best practices for trustworthy and deployable AI through an iterative process comprising an in-depth literature review, a modified Delphi survey and online consensus meetings. Dr. Linguraru contributed with a unique perspective on AI for pediatric care and rare diseases.

What’s next

The authors note that, “progressive development and adoption of medical AI tools will lead to new requirements, challenges and opportunities. For some of the recommendations, no clear standard on how these should be addressed yet exists.”

To tackle this uncertainty, they propose FUTURE-AI as a dynamic, living framework. This includes a dedicated website to allow the global community to participate in the FUTURE-AI network. Visitors can provide feedback based on their own experiences and perspectives. The input gathered will allow the consortium to refine the FUTURE-AI guidelines and learn from other voices.

Read the full manuscript outlining all 30 best practices: FUTURE-AI: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Marius George Linguraru appointed as president of the MICCAI Society

Marius George Linguraru

“MICCAI has been a professional home for me throughout my career and I am deeply honored to have a chance to give back to the organization,” said Dr. Linguraru.

We’re pleased to announce that Marius George Linguraru, DPhil, MA, MSc, Connor Family professor and endowed chair in Research and Innovation at Children’s National, has been elected as president of the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society board of directors. Dr. Linguraru has been involved in the society since he attended his first MICCAI conference in 2001. He was elected to the board of directors in 2021 and chairs the Career Development Working Group. Dr. Linguraru was instrumental in establishing the MICCAI Mentorship Program, the MICCAI Start-up Village and the AFRICAI Special Interest Group. He also served as the program chair of MICCAI 2024, which received and reviewed a record number of paper submissions. He will begin his three-year term as president on February 1, 2025. Watch Dr. Linguraru’s brief inaugural message to members here.

“MICCAI has been a professional home for me throughout my career and I am deeply honored to have a chance to give back to the organization,” said Dr. Linguraru. “I believe the society is poised not just to meet the challenges of the next few years, but to thrive as an essential leadership forum for the growth of medical image computing, computer assisted intervention and artificial intelligence in healthcare.”

Dr. Linguraru leads the AI research initiatives at Children’s National and serves as principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation. His award-winning team builds artificial intelligence applications to expand health equity and access to pediatric healthcare when diseases are rare and resources are limited. Through partnerships between Children’s National and Virginia Tech and Microsoft, Dr. Linguraru also plays an integral role in exploring how generative AI can improve pediatric care.

Meanwhile, Caroline Essert, PhD, MSc, completes her term as president of the MICCAI Society on January 31, 2025.

“It has been an honor to contribute to the growth and vibrancy of this incredible community,” said Dr. Essert. “I extend my warmest welcome to Dr. Linguraru as the incoming president of the MICCAI Board. I am confident that under his leadership, the MICCAI Society will reach new heights and continue to serve as a beacon of excellence in our field.” Read her full farewell message here.

To learn more about the MICCAI Society, click here.

AI for good: Children’s National wins global competitions for measuring brain tumors

Children's National Hospital's winning team for the Brain Tumor Segmentation-Africa (BraTS-Africa) challenge

Meet the winners (left to right): Syed M. Anwar, Ph.D., M.S., principal investigator at Children’s National; Daniel Capellan Martin, M.Sc., Polytechnic University of Madrid; Abhijeet Parida, data scientist at Children’s National; and Austin Tapp, Ph.D., postdoctoral research fellow at Children’s National.

Using an award-winning artificial intelligence (AI) algorithm developed at Children’s National Hospital, researchers ranked first in the world in the Brain Tumor Segmentation-Africa (BraTS-Africa) challenge for their approach to identifying different parts of deadly gliomas. The details of their innovative method were recently published on arXiv, a curated research-sharing platform.

“Technology can bridge the gap in healthcare between high- and low-resource countries,” said Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor in Research and Innovation and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation (SZI). “By tailoring methods we created at our hospital to fit the needs of specific regions, such as sub-Saharan Africa, our research helps improve medical imaging and diagnosis in challenging environments.”

Dr. Linguraru was the program chair of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2024 in Marrakesh, Morocco, the leading global meeting on AI in medical imaging.

Children’s National leads the way

Gliomas are a type of brain tumor with a high death rate and are especially difficult to diagnose in low- and middle-income countries. Given the increased need in Africa, researchers worldwide came together in Morocco to compete over the best way to accurately detect and measure tumors using MRI data and AI.

By applying advanced machine-learning techniques, the researchers adapted tools initially designed for well-resourced settings to work in countries with far fewer.

The study focused on transfer learning, a process in which an AI model is trained in advance on a large number of brain tumor images and then adjusted to work with smaller sets of new data. In this case, the models were adapted to work with local sub-Saharan African data using a strategy to combine different models’ strengths.

When tested, the approach achieved impressive accuracy scores. The Children’s National team, which included a colleague from the Polytechnic University of Madrid, ranked first in the BraTS-Africa 2024 challenge for identifying different parts of gliomas.

“To make the method widely available, the winning algorithm is shared online for others to use and improve upon,” Dr. Linguraru said. “My favorite part of these competitions is how they highlight the way innovation and collaboration can reduce global healthcare inequalities.”

The big picture

Children’s National researchers consistently lead global events using AI and advanced imaging to tackle complex healthcare challenges. In 2023, the team won a global contest to measure pediatric brain tumors at the MICCAI 2023 Conference. This year’s success in the BraTS-Africa challenge builds on this knowledge base and expands its use to adult gliomas.

At the Radiological Society of North America 2024 annual meeting, which drew 50,000 attendees, Zhifan Jiang, Ph.D., a staff scientist in the Precision Medical Imaging Lab at SZI, also won the Cum Laude Award for his scientific poster on applying AI to radiological images to predict severe outcomes for children with brain tumors caused by neurofibromatosis type 1.

“These achievements show how our science is leading the world in using AI for good,” Dr. Linguraru said. “Every day, we’re building on our knowledge of advanced imaging, brain tumors and AI to improve the diagnosis, measurement and treatment of deadly tumors — on a global scale.”

Attendees of the Brain Tumor Segmentation-Africa (BraTS-Africa) challenge

Transforming pediatric care: How AI is driving the next medical revolution

The future of healthcare is unfolding before scientists and clinicians: Doctors are assisted by virtual scribes trained by artificial intelligence. Algorithms are reading MRIs. Smartphones are helping to detect strep throat. Machines diagnose children without access to care.

These and dozens of other artificial intelligence (AI) applications are being tested to enhance pediatric healthcare, and many were on display at the 2nd annual Children’s National Hospital-Virginia Tech Symposium on AI for Pediatric Health at the Children’s National Research & Innovation Campus.

Some highlights from the daylong conversation about the future of pediatric medicine, augmented by AI and generative AI models capable of producing new and critical content:

  • Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor in Research and Innovation and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation: “Children are just not mini-adults. In pediatric care, we train pediatric specialists because kids die from different diseases than those that kill adults. Children also suffer from very impactful and rare conditions. If we train pediatric specialists well, we have to train AI algorithms in the same fashion.”
  • Rowland Illing, M.D., Ph.D., chief medical officer and director of global healthcare and nonprofits at Amazon Web Services: “In a short period of time, the complexity of the models available is astounding. Generative AI, just like AI, can impact outcomes at every step of the patient pathway, including the clinical workflow, care management and patient engagement. By creating a specific use case with generative AI, every step can be optimized to be smarter, which ultimately leads to improved patient care and outcomes.”
  • Children’s National Chief Academic Officer Nathan Kuppermann, M.D., M.P.H.: “AI in pediatric health is not just about identifying rare diseases. Its potential includes all aspects of clinical care, clinical operations, education and research. It has the potential to help educators enhance the novelty and impact of their methods and advance research with powerful tools to gather and analyze data.”
  • Alda Mizaku, vice president and chief data and artificial intelligence officer at Children’s National: “What excites me most about our future is the endless possibilities. We can use AI and data to uncover many things: rare diseases, operational efficiencies, time-saving and cost-saving solutions. This has to be done in a responsible way, and we must look at what some of the guardrails need to be.”

Throughout the day, expert panels offered insights into regulatory pathways to deploy AI in pediatric drugs and devices. The Food and Drug Administration’s Office of Science and Engineering Laboratories also provided guidance on collaborative tools for improving the representation of children and perinatal patients in AI-powered medical devices.

Moving the field forward

Early adopters of AI at Children’s National shared applications already under investigation, including efforts to segment and measure brain tumors on imaging, weigh the risk of strep throat with a smartphone camera and detect rheumatic heart disease with portable technology and an algorithm.

Dr. Linguraru, an expert in healthcare AI, said that artificial intelligence is no longer a hypothetical technology but is already remaking the healthcare system. “AI is here. What matters now is how we use it and how we train doctors to use it well,” he said.

The big picture

Through growing partnerships, Children’s National experts are teaming up with researchers at Virginia Tech on a series of AI-driven projects aimed at advancing pediatric health, including programs to rethink privacy in federated learning, forecast emergency department surges, extract clinical variables from documents to predict sepsis risks, identify rare genetic syndromes in children, and predict single-cell responses to genetic perturbations in pediatric developmental disorders.

Naren Ramakrishnan, Ph.D., director of the Sanghani Center at Virginia Tech and the Thomas L. Phillips Professor in the College of Engineering, said the partnership between the two academic centers is changing healthcare already and will continue to as the organizations offer future seed grants to support innovation in cardiology, neuroscience and oncology. “The roots have borne fruit,” he said.

AI’s transformative potential in radiology

Doctor using digital tablet for advanced Mri x-ray scan

The adoption of artificial intelligence (AI) has the potential to enhance radiological imaging, improve diagnostic capabilities and reduce burnout in the field.

The adoption of artificial intelligence (AI) has the potential to enhance radiological imaging, improve diagnostic capabilities and reduce burnout in the field, provided that physicians and scientists work together to ensure its careful integration into the practice of medicine, according to a special report in Radiology: Artificial Intelligence, a journal of the Radiological Society of North America (RSNA).

Assembled by experts in radiology, medical imaging and machine learning, the special report lays out the clinical, cultural, computation and regulatory considerations that are being introduced, particularly as generative AI models become part of the field.

“AI tools can play a key role in radiology, but radiologists must be able to trust in the systems’ design and receive adequate training. As the physicians most familiar with these tools, radiologists should establish clear guidelines regarding clinical accountability,” said Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor in Research and Innovation and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation.

Moving the field forward

Dr. Linguraru and his peers assembled the report based on a series of seminars hosted by RSNA and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society. They collected input from multidisciplinary experts to outline the current clinical uses of AI and its future potential.

The experts agreed that collaboration between radiologists and AI scientists will be essential to successfully integrate AI into the discipline of radiology. This partnership should focus on establishing a unified agenda, shared language and clear expectations of the tools developed. By working together, they can ensure that AI tools are designed and implemented to meet the practical needs of radiology, particularly with the incorporation of language and vision models.

What’s next

Among the challenges ahead, clinical institutions must align their staffing, data management and computational resources to deploy and monitor AI systems effectively. This alignment includes ensuring that personnel are adequately trained to use AI tools, that data is managed and processed efficiently and that sufficient computational power is available to support AI operations. Cloud computing may be vital to hospitals that don’t have hardware and technical maintenance resources.

“The successful integration of AI in radiology depends on trust in AI design, collaborative efforts between radiologists and AI scientists, and the alignment of clinical resources to support AI deployment,” Dr. Linguraru said. “With these factors in place, AI can play a transformative role in improving radiological practices and outcomes.”

Read the special report “Clinical, Cultural, Computational, and Regulatory Considerations to Deploy AI in Radiology: Perspectives of RSNA and MICCAI Experts” in Radiology: Artificial Intelligence.

Around the world

Our Global Health Initiative launched in 2016 with the goal of eliminating pediatric health disparities around the world. We aim to address the most pressing pediatric health issues through better care for medically underserved populations. This leadership helps us achieve our mission of caring for all children. A broad range of education and research projects improves health outcomes. They also offer enriching opportunities for experienced faculty and emerging leaders to advance clinical excellence.

Healing hearts in Uganda

Dr. Craig Sable in Uganda

Dr. Craig Sable and team train partners in Uganda.

Craig Sable, M.D., interim chief of Cardiology, improves care for young people with rheumatic heart disease (RHD) in Uganda. Donors, including the Karp Family Foundation, Huron Philanthropies, Zachary Blumenfeld Fund and the Wood family, make this possible. RHD affects 50 million people, mostly children, worldwide. It claims 400,000 lives each year.

Dr. Sable and Ugandan partners completed important research showing that early RHD detection, coupled with monthly penicillin treatment, can protect the heart. They are working on practical solutions, such as a new portable device with artificial intelligence (AI) that can easily screen for RHD.

In 2023, Dr. Sable led two missions in Uganda where he and his team did surgeries and special tests for 18 children with RHD. They also taught local doctors new skills to help more kids on their own.

Plastic surgery and reconstructive care in Kenya and Nepal

Each year our Craniofacial & Pediatric Plastic Surgery team, under the leadership of Johnston Family Professor of Pediatric Plastic Surgery and Chief of Pediatric Plastic Surgery Gary Rogers, M.D., J.D., LL.M., M.B.A., M.P.H., provides opportunities for fellows to participate in surgical missions.

In 2024, Perry Bradford, M.D., traveled to the Moi Teaching Hospital in Eldoret, Kenya where she provided patients with burn, pressure wound and cleft reconstruction. She built community connections with the local plastic surgeons and educated registrars and medical students. “This gave me firsthand experience working in a community with limited resources and forced me to be more creative,” Dr. Bradford says. “The experience inspired me to examine what it means to have consistent access to advanced tools and equipment.”

In 2022, a group traveled to Nepal to provide care. Some patients arrived after days of travel by yak or buffalo. One child with a burn injury recovered use of her hand. The team educated local providers to deliver life-changing treatments unavailable in Nepal.

Dr. Tesfaye Zelleke in Ethiopia

Dr. Tesfaye Zelleke, left, and team in Ethopia.

Elevating epilepsy care in Ethiopia

Neurologist Tesfaye Zelleke, M.D., and partners in Ethiopia are seeking to improve the lives of children with epilepsy. The BAND Foundation provides support. Ethiopia has a population of about 120 million yet only a handful of pediatric neurologists.

Dr. Zelleke’s team trained nonspecialist providers to diagnose and treat children in the primary care setting. They also launched a mobile epilepsy clinic to provide community care and build the capacity of local clinicians. In collaboration with advocacy groups, the team educates the public about epilepsy with a goal of reducing stigma.

New hope in Norway

In 2023, our Division of Colorectal & Pelvic Reconstruction shared its expertise with clinicians at Oslo University Hospital, Rikshospitalet, in Norway. This effort was a key first step in Oslo becoming the first dedicated colorectal center in Scandinavia.

Marc Levitt, M.D., and team members performed complex surgeries otherwise unavailable for waiting patients. They led an academic conference. They held clinics to educate nurses, reviewed patient records and made care recommendations. Specialized care enabled a young patient with significant bowel difficulties to recover function and lead a normal life.

The team will travel to South Africa, the Czech Republic and Spain in 2024. Donors, including The Dune Road Foundation and Deanna and Howard Bayless, make this work possible.

Improving outcomes for babies in the Congo

AI can be a valuable tool for diagnosing genetic conditions. It detects unique facial patterns that clinicians without genetics training can miss. However, existing facial analysis software struggles in nonwhite populations.

A team led by Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor of Research and Innovation and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation, is working to improve the newborn diagnosis rate worldwide. They are testing smartphone software in the Democratic Republic of Congo. Diverse newborn data improves AI’s ability to detect a variety of genetic conditions in more children. Early detection, diagnosis and informed care lead to better health outcomes.

Nephrology care for kids in Jamaica

Dr. Moxey-Mims and team in Jamaica

Jennifer Carver and Dr. Marva Moxey-Mims, center, with staff at Bustamante Children’s Hospital.

Marva Moxey-Mims, M.D., chief of Nephrology, is bringing care to children with kidney disease in Jamaica, with a goal of improving health equity. An International Pediatric Nephrology Association grant helped make it possible.

On a recent trip, Dr. Moxey-Mims and a small team — including Jennifer Carver, RN, CNN, lead peritoneal dialysis nurse at Children’s National, and three pediatric nephrologists from Jamaica — trained nearly 30 nurses from Jamaican hospitals. Nurses received hands-on dialysis education to improve their clinical skills. The team also worked to educate the community in disease awareness and prevention.

Read more stories like this one in the latest issue of Believe magazine.

Artificial – and accelerated – intelligence: endless applications to expand health equity

In the complex world of pediatric diseases, researchers need access to data to develop clinical trials and the participation of vulnerable patients to develop new devices and therapies. Both are in short supply, given that most children are born healthy, and most severe pediatric diseases are rare.

That creates a dilemma: how do researchers build a foundation to advance new treatments? Enter artificial intelligence (AI).

“AI is the equalizer: accelerated intelligence for sick kids. No other advance on the horizon holds more promise for improving equity and access to pediatric healthcare when diseases are rare and resources are limited,” says Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor in Research and Innovation and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation (SZI). “AI will shrink the distance between patient and provider, allowing our physicians and scientists to provide targeted healthcare for children more efficiently. The possibilities are endless.”

Why we’re excited

By pioneering AI innovation programs at Children’s National Hospital, Dr. Linguraru and the AI experts he leads are ensuring patients and families benefit from a coming wave of technological advances. The team is teaching AI to interpret complex data that could otherwise overwhelm clinicians. Their work will create systems to identify at-risk patients, forecast disease and treatment patterns, and support complex clinical decisions to optimize patient care and hospital resources. Already, the AI team at SZI has developed data-driven tools touching nearly every corner of the hospital:

  • AI for rheumatic heart disease (RHD): In partnership with Children’s National cardiology leaders, including Craig Sable, M.D., the Uganda Heart Institute and Cincinnati Children’s Hospital, the AI team has developed an algorithm that can use low-cost, portable ultrasound imaging to detect RHD in children and young adults, a disease that takes nearly 400,000 lives annually in limited-resource countries. Early testing shows the AI platform has the same accuracy as a cardiologist in detecting RHD, paving the way for earlier treatment with life-saving antibiotics. This year, Children’s National physicians will be in Uganda, screening 200,000 children with local cardiology experts and AI technology.
  • Newborn screening for genetic conditions with mGene: Working with Rare Disease Institute clinicians and Chief of Genetics and Metabolism Debra Regier, M.D., the AI team has built technology to detect rare genetic disorders, using an algorithm and a smartphone camera to identify subtle changes in facial features. Tested on patients from over 30 countries and published in The Lancet Digital Health, the application helps screen children for advanced care when a geneticist may not be within reach. With funding from the National Institutes of Health, Children’s National and its research partners are piloting a newborn screening program in the Democratic Republic of the Congo.
  • Pediatric brain tumors: To improve and personalize the treatment decisions for children with brain tumors, Dr. Linguraru’s team is working with Brain Tumor Institute Director Roger Packer, M.D., the Gilbert Family Distinguished Professor of Neurofibromatosis, on algorithms that can characterize and measure brain tumors with unprecedented precision. The team recently won the International Pediatric Brain Tumor Segmentation Challenge, distinguishing the Children’s National algorithm as among the best in the world.
  • Ultra-low field magnetic resonance imaging (MRI): With a grant from the Bill & Melinda Gates Foundation, the AI team is working alongside Children’s Hospital Los Angeles, King’s College London and the UNITY Consortium to expand global brain imaging capacity. The consortium is helping clinicians in limited-resource countries improve the treatment of neonatal neurological conditions, using AI to boost the quality of ultra-low field MRI and expand access to this portable and more affordable imaging option.
  • Federated learning: Children’s National has collaborated with NVIDIA and other industry leaders to accelerate AI advances through federated learning. Under this approach, institutions share AI models rather than data, allowing them to collaborate without exposing patient information or being constrained by essential data-sharing restrictions. The SZI team was the only pediatric partner invited to join the largest federated learning project of its kind, studying the lungs of COVID-19 patients. Details were published in Nature Medicine.

Children’s National leads the way

Looking ahead, the Children’s National AI team is pursuing a wide range of advances in clinical care. To support patients treated at multiple clinics, they are developing systems to harmonize images from different scanners and protocols, such as MRI machines made by different manufacturers. Similar work is underway to analyze pathology samples from different institutions consistently.

Automation is also making care more efficient. For example, using data from 1 million chest X-rays, the team is collaborating with NVIDIA to develop a conversational digital assistant that will allow physicians to think through 14 possible diagnoses.

Dr. Linguraru says he and his colleagues are galvanized by the jarring statistic that one in three children with a rare disease dies before age 5. While well-implemented AI initiatives can change outcomes, he says the work must be done thoughtfully.

“In the future, patients will be evaluated by human clinicians and machines with extraordinary powers to diagnose illness and determine treatments,” Dr. Linguraru said. “Our team at Children’s National is leading conversations about the future of pediatric healthcare with a focus on safety, resource allocation and basic equity.”

Learn more about our AI initiatives

Innovation leaders at Children’s National Hospital are building a community of AI caregivers through educational and community-building events. At the inaugural Symposium on Artificial Intelligence in 2023 at the Children’s National Research & Innovation Campus, experts from Virginia Tech, JLABS, Food and Drug Administration, Pfizer, Oracle Health, NVIDIA, AWS Health and elsewhere laid out a vision for using data to advance pediatric medicine. The symposium will return on Sept. 6.

Dr. Linguraru is the program chair of MICCAI 2024, the top international meeting on medical image computing and computer-assisted intervention and the preeminent forum for disseminating AI developments in healthcare. The conference is an educational platform for scientists and clinicians dedicated to AI in medical imaging, with a focus on global health equity. It will take place for the first time in Africa on Oct. 6-10.

 

 

Novel AI platform matches cardiologists in detecting rheumatic heart disease

Artificial intelligence (AI) has the potential to detect rheumatic heart disease (RHD) with the same accuracy as a cardiologist, according to new research demonstrating how sophisticated deep learning technology can be applied to this disease of inequity. The work could prevent hundreds of thousands of unnecessary deaths around the world annually.

Developed at Children’s National Hospital and detailed in the latest edition of the Journal of the American Heart Association, the new AI system combines the power of novel ultrasound probes with portable electronic devices installed with algorithms capable of diagnosing RHD on echocardiogram. Distributing these devices could allow healthcare workers, without specialized medical degrees, to carry technology that could detect RHD in regions where it remains endemic.

RHD is caused by the body’s reaction to repeated Strep A bacterial infections and can cause permanent heart damage. If detected early, the condition is treatable with penicillin, a widely available antibiotic. In the United States and other high-income nations, RHD has been almost entirely eradicated. However, in low- and middle-income countries, it impacts the lives of 40 million people, causing nearly 400,000 deaths a year.

“This technology has the potential to extend the reach of a cardiologist to anywhere in the world,” said Kelsey Brown, M.D., a cardiology fellow at Children’s National and co-lead author on the manuscript with Staff Scientist Pooneh Roshanitabrizi, Ph.D. “In one minute, anyone trained to use our system can screen a child to find out if their heart is demonstrating signs of RHD. This will lead them to more specialized care and a simple antibiotic to prevent this degenerative disease from critically damaging their hearts.”

The big picture

AI system that can detect RHD

The new AI system combines the power of novel ultrasound probes with portable electronic devices installed with algorithms capable of diagnosing RHD on echocardiogram.

Millions of citizens in impoverished countries have limited access to specialized care. Yet the gold standard for diagnosing RHD requires a highly trained cardiologist to read an echocardiogram — a non-invasive and widely distributed ultrasound imaging technology. Without access to a cardiologist, the condition may remain undetected and lead to complications, including advanced cardiac disease and even death.

According to the new research, the AI algorithm developed at Children’s National identified mitral regurgitation in up to 90% of children with RHD. This tell-tale sign of the disease causes the mitral valve flaps to close improperly, leading to backward blood flow in the heart.

Beginning in March, Craig Sable, M.D., interim division chief of Cardiology, and his partners on the project will implement a pilot program in Uganda incorporating AI into the echo screening process of children being checked for RHD. The team believes that a handheld ultrasound probe, a tablet and a laptop — installed with the sophisticated, new algorithm — could make all the difference in diagnosing these children early enough to change outcomes.

“One of the most effective ways to prevent rheumatic heart disease is to find the patients that are affected in the very early stages, give them monthly penicillin for pennies a day and prevent them from becoming one of the 400,000 people a year who die from this disease,” Dr. Sable said. “Once this technology is built and distributed at a scale to address the need, we are optimistic that it holds great promise to bring highly accurate care to economically disadvantaged countries and help eradicate RHD around the world.”

Children’s National Hospital leads the way

To devise the best approach, two Children’s National experts in AI — Dr. Roshanitabrizi and Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor in Research and Innovation and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation — tested a variety of modalities in machine learning, which mimics human intelligence, and deep learning, which goes beyond the human capacity to learn. They combined the power of both approaches to optimize the novel algorithm, which is trained to interpret ultrasound images of the heart to detect RHD.

Already, the AI algorithm has analyzed 39 features of hearts with RHD that cardiologists cannot detect or measure with the naked eye. For example, cardiologists know that the heart’s size matters when diagnosing RHD. Current guidelines lay out diagnostic criteria using two weight categories — above or below 66 pounds — as a surrogate measure for the heart’s size. Yet the size of a child’s heart can vary widely in those two groupings.

“Our algorithm can see and make adjustments for the heart’s size as a continuously fluid variable,” Dr. Roshanitabrizi said. “In the hands of healthcare workers, we expect the technology to amplify human capabilities to make calculations far more quickly and precisely than the human eye and brain, saving countless lives.”

Among other challenges, the team had to design new ways to teach the AI to handle the inherent clinical differences found in ultrasound images, along with the complexities of evaluating color Doppler echocardiograms, which historically have required specialized human skill to evaluate.

“There is a true art to interpreting this kind of information, but we now know how to teach a machine to learn faster and possibly better than the human eye and brain,” Dr. Linguraru said. “Although we have been using this diagnostic and treatment approach since World War II, we haven’t been able to share this competency globally with low- and middle-income countries, where there are far fewer cardiologists. With the power of AI, we expect that we can, which will improve equity in medicine around the world.”

Federated learning: A solution to AI’s data-sharing challenges

data science illustration

Federated learning can solve data-sharing challenges, allowing nimble collaboration across institutions to drive medical advances using artificial intelligence (AI).

Federated learning can solve data-sharing challenges, allowing nimble collaboration across institutions to drive medical advances using artificial intelligence (AI), according to a new manuscript from 10 thought leaders in AI and machine learning in medicine.

In Health Informatics Journal, these leading experts on how technology is shaping medicine shared a conversation that they had at the Radiology Society of North America’s conference. They weighed challenges facing AI, including barriers to data sharing because of privacy rules that prevent the distribution of information to different institutions. With federated learning, models are shared – rather than data – allowing institutions to aggregate information and collaborate with a master model.

“Federated learning offers tremendous promise,” said Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor of Research and Innovation, principal investigator at the Sheikh Zayed Institute of Pediatric Surgical Innovation and senior author on the manuscript. “As a community of experts, we have found that federated learning allows us to move away from the challenges of sharing data in central repositories. Instead, we share the models, which can be designed to protect privacy by limiting what’s shared outside of any given institution.”

A champion of pediatric health, Linguraru wants to ensure that children are represented in the development of models that advance science and medicine. “Sharing data is even more crucial when there are few patients, such as in rare diseases or pediatric populations,” he said. “In general, healthcare data suffers from inequitable representation in our public health systems and services.”

Learn more here about the challenges and potential solutions from experts at Rhino Health, Johns Hopkins University School of Medicine, NVIDIA, University of Cambridge, Ben-Gurion University Israel, MD Anderson Cancer Center, Dana-Farber Cancer Institute and Children’s National Hospital.

AI team wins international competition to measure pediatric brain tumors

Winners of the International Conference on Medical Image Computing and Computer Assisted Intervention
Children’s National Hospital scientists won first place in a global competition to use artificial intelligence (AI) to analyze pediatric brain tumor volumes, demonstrating the team’s ground-breaking advances in imaging and machine learning.

During the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), the Children’s National team demonstrated the most accurate algorithm to study the volume of brain tumors – the most common solid tumors affecting children and adolescents and a leading cause of disease-related death at this young age. The technology could someday help oncologists understand the extent of a patient’s disease, quantify the efficacy of treatments and predict patient outcomes.

“The Brain Tumor Segmentation Challenge inspires leaders in medical imaging and deep learning to try to solve some of the most vexing problems facing radiologists, oncologists, computer engineers and data scientists,” said Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor in Research and Innovation and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation. “I am honored that our team won, and I’m even more thrilled for our clinicians and their patients, who need us to keep moving forward to find new ways to treat pediatric brain tumors.”

Why we’re excited

With roughly 4,000 children diagnosed yearly, pediatric brain tumors are consistently the most common type of pediatric solid tumor, second only to leukemia in pediatric malignancies. At the urging of Linguraru and one of his peers at the Children’s Hospital of Philadelphia, pediatric data was included in the international competition for the first time, helping to ensure that children are represented in medical and technological advances.

The contest required participants to use data from multiple institutions and consortia to test competing methods fairly. The Children’s National team created a method to tap into the power of two types of imaging and machine learning: 3D convolutional neural network and 3D Vision Transformer-based deep learning models. They identified regions of the brain affected by tumors, made shrewd data-processing decisions driven by the team’s experience in AI for pediatric healthcare and achieved state-of-the-art results.

The competition drew 18 teams who are leaders from across the AI and machine learning community. The runner-up teams were from NVIDIA and the University of Electronic Science and Technology of China.

The big picture

“Children’s National has an all-star lineup, and I am thrilled to see our scientists recognized on an international stage,” said interim Executive Vice President and Chief Academic Officer Catherine Bollard, M.D., M.B.Ch.B., director of the Center for Cancer for Immunology Research. “As we work to attack brain tumors from multiple angles, we continue to show our exceptional ability to create new and better tools for diagnosing, imaging and treating these devastating tumors.”

“Mask up!” Soon, AI may be prompting healthcare workers

Researchers at Children’s National Hospital are embarking on an effort to deploy computer vision and artificial intelligence (AI) to ensure medical professionals appropriately use personal protective equipment (PPE). This strikingly common problem touches almost every medical specialty and setting.

With nearly $2.2 million in grants from the National Institutes of Health, the team is combining their expertise with information scientists at Drexel University and engineers at Rutgers University to build a system that will alert doctors, nurses and other medical professionals of mistakes in how they are wearing their PPE. The goal is to better protect healthcare workers (HCWs) from dangerous viruses and bacteria that they may encounter — an issue laid bare with the COVID-19 pandemic and PPE shortages.

“If any kind of healthcare setting says they don’t have a problem with PPE non-adherence, it’s because they’re not monitoring it,” said Randall Burd, M.D., Ph.D., division chief of Trauma and Burn Surgery at Children’s National and the principal investigator on the project. “We need to solve this problem, so the medical community will be prepared for the next potential disaster that we might face.”

The big picture

The World Health Organization has estimated that between 80,000 and 180,000 HCWs died globally from COVID-19 between January 2020 and May 2021 — an irreplaceable loss of life that created significant gaps in the pandemic response. Research has shown that HCWs had an 11-fold greater infection risk than the workers in other professions, and those who were not wearing appropriate PPE had a 1/3 higher infection risk, compared to peers who followed best practices.

Burd said the Centers for Disease Control and Prevention has recommended that hospitals task observers to stand in the corner with a clipboard to watch clinicians work and confirm that they are being mindful of their PPE. However, “that’s just not scalable,” he said. “You can’t always have someone watching, especially when you may have 50 people in and out of an operating room on a challenging case. On top of that, the observers are generally trained clinicians who could be filling other roles.”

What’s ahead

Bringing together the engineering talents at Drexel and Rutgers with the clinical and machine-learning expertise at Children’s National, the researchers plan to build a computer-vision system that will watch whether HCWs are properly wearing PPE such as gloves, masks, eyewear, gowns and shoe covers.

The team is contemplating how the system will alert HCWs to any errors and is considering haptic watch alerts and other types of immediate feedback. The emerging power of AI brings tremendous advantages over the current, human-driven systems, said Marius George Linguraru, D.Phil., M.A., M.Sc., the Connor Family Professor in Research and Innovation at Children’s National and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation.

“Human observers only have one pair of eyes and may fatigue or get distracted,” Linguraru said. “Yet artificial intelligence, and computers in general, work without getting tired. We are excited to figure out how a computer can do this work – without ever blinking.”

Children’s National Hospital leads the way

Linguraru says that Children’s National and its partners make up the ideal team to tackle this vexing challenge because of their ability to assemble a multidisciplinary team of scientists and engineers who can work together with clinicians. “This is a dialogue,” he said. “A computer scientist, like myself, needs to understand the intricacies of complicated clinical realities, while a clinician needs to understand how AI can impact the practice of medicine. The team we are bringing together is intentional and poised to fix this problem.”

Children’s National joins team to use AI to expand health knowledge in Kenya

Marius Linguraru, D.Phil., M.A., M.Sc., a co-principal investigator for the project, presentsChildren’s National Hospital is joining a team of global health researchers to use large language models (LLMs) like ChatGPT to help Kenyan youth learn about their health and adopt lifestyles that may prevent cancer, diabetes and other non-communicable diseases.

The work, which is one of nearly 50 Grand Challenges Catalyzing Equitable Artificial Intelligence (AI) Use grants announced by the Bill & Melinda Gates Foundation, will harness the emerging power of AI to empower young people with information that they can carry through adulthood to reduce rates of unhealthy behaviors including physical inactivity, unhealthy diet and use of tobacco and alcohol.

“We are thrilled to be part of this effort to bring our AI expertise closer to young patients who would benefit dramatically from technology and health information,” said Marius George Linguraru, D.Phil., M.A., M.Sc., a co-principal investigator for the project, the Connor Family Professor in Research and Innovation at Children’s National and principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation. “Using generative AI, we will build an application to enhance the knowledge, attitudes and healthy habits of Kenyan youth and use this as a foundation to improve health inequities around the globe.”

Why it matters

A lower middle-income country located on the east coast of Sub-Saharan Africa, Kenya is home to 50 million people and one of the continent’s fastest-growing economies. English is one of Kenya’s official languages, and the country has been recognized as a technology leader in Africa, with 82% of Kenyans having phone connectivity. Taken together, these factors make the country an ideal location to deploy an LLM-based platform designed to improve health information and attitudes.

The Gates Foundation selected this project from more than 1,300 grant applications. The nearly 50 funded projects are aimed at supporting low- and middle-income countries to harness the power of AI for good and help countries participate in the AI development process. The project’s findings will contribute to building an evidence base for testing LLMs that can fill wide gaps in access and equitable use of these tools. Each of the grants provides an opportunity to mitigate challenges experienced by communities, researchers and governments.

What’s next

The project development will be led by the National Cancer Institute of Kenya, with Linguraru and other global experts advising the effort from Kenyan institutions and Stanford University. Researchers plan to enroll youth from universities, shopping malls, markets, sporting events and other high-traffic locations. The study will look at participants’ risk factors and how their attitudes toward healthier lifestyles changed after engaging with the new LLM platform.

“The team is thrilled to be selected as one of the nearly 50 most promising AI proposals in the Gates Foundation Grand Challenge competition, and we look forward to seeing how our work can benefit the health of Kenyan youth,” said Dr. Martin Mwangi, principal investigator for the project and head of the Cancer Prevention and Control Directorate at the National Cancer Institute of Kenya. “If successful, we hope to share this model and the expertise we gain to expand health equity and knowledge to other regions.”

Marius George Linguraru, D.Phil., M.A., M.Sc., named as Connor Family Professor of Research and Innovation

Marius George Linguraru

“Artificial Intelligence may be the greatest tool we have for improving the quality of and access to medical care for children, especially those most vulnerable to health system inequities,” said Dr. Linguraru. “This professorship will help me extend our leadership in this vital field. The tools and care strategies we develop will benefit children worldwide.”

Children’s National Hospital named Marius George Linguraru, D.Phil., M.A., M.Sc., as the Connor Family Professor of Research and Innovation at Children’s National Hospital.

Dr. Linguraru is a principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National. He directs the award-winning Precision Medicine Imaging Group. He is also a professor of Radiology and Pediatrics and secondary professor of Biomedical Engineering at George Washington University.

About the award

Dr. Linguraru joins a distinguished group of 42 Children’s National physicians and scientists who hold an endowed chair. Professorships at Children’s National support groundbreaking work on behalf of children and their families and foster new discoveries and innovations in pediatric medicine. These appointments carry prestige and honor that reflect the recipient’s achievements and donor’s forethought to advance and sustain knowledge.

Dr. Linguraru is a global leader in harnessing the power of quantitative imaging and machine learning to rapidly and positively impact children’s health. Dr. Linguraru and his team use artificial intelligence (AI) and digital technology innovations to improve access to healthcare and the understanding of rare and newborn diseases. Their work enables clinicians to deliver care faster, evaluate responses to treatments and prevent health complications. They have positioned Children’s National as an international leader in the development of pediatric AI to ensure equitable care for all children.

“Artificial Intelligence may be the greatest tool we have for improving the quality of and access to medical care for children, especially those most vulnerable to health system inequities,” said Dr. Linguraru. “This professorship will help me extend our leadership in this vital field. The tools and care strategies we develop will benefit children worldwide.”

About the donors

The Connor family, through their vision and generosity, are ensuring that Dr. Linguraru and future holders of this professorship will launch bold, new initiatives to rapidly advance the field of pediatric research and innovation, elevate our leadership and improve the lifetimes of children.

“We strongly believe in the power of academic entrepreneurship to improve the health and wellbeing of children,” said Ed and Chris Connor, who are longtime donors and members of the Children’s National community. “This endowment is our way of supporting Children’s National’s work in research and innovation and recognizing Dr. Linguraru’s international leadership in using AI to benefit child health.”

AI: The “single greatest tool” for improving access to pediatric healthcare

Attendees at the inaugural symposium on AI in Pediatric Health and Rare Diseases

The daylong event drew experts from the Food and Drug Administration, Pfizer, Oracle Health, NVIDIA, AWS Health and elsewhere to start building a community aimed at using data for the advancement of pediatric medicine.

The future of pediatric medicine holds the promise of artificial intelligence (AI) that can help diagnose rare diseases, provide roadmaps for safer surgeries, tap into predictive technologies to guide individual treatment plans and shrink the distance between patients in rural areas and specialty care providers.

These and dozens of other innovations were contemplated as scientists came together at the inaugural symposium on AI in Pediatric Health and Rare Diseases, hosted by Children’s National Hospital and the Fralin Biomedical Research Institute at Virginia Tech. The daylong event drew experts from the Food and Drug Administration, Pfizer, Oracle Health, NVIDIA, AWS Health and elsewhere to start building a community aimed at using data for the advancement of pediatric medicine.

“AI is the single greatest tool for improving equity and access to health care,” said symposium host Marius George Linguraru, D.Phil., M.A., M.Sc., principal investigator at the Sheikh Zayed Institute for Pediatric Surgical Innovation. “As a population, kids are vastly underrepresented in scientific research and resulting treatments, but pediatric specialties can use AI to provide medical care to kids more efficiently, more quickly and more effectively.”

What they’re saying

Scientists shared their progress in building digital twins to predict surgical outcomes, enhancing visualization to increase the precision of delicate interventions, establishing data command centers to anticipate risks for fragile patients and more. Over two dozen speakers shared their vision for the future of medicine, augmented by the power of AI:

  • Keynote speaker Subha Madhavan, Ph.D., vice president and head of AI and machine learning at Pfizer, discussed various use cases and the potential to bring drugs to market faster using real-world evidence and AI. She saw promise for pediatrics. “This is probably the most engaging mission: children’s health and rare diseases,” she said. “It’s hard to find another mission that’s as compelling.”
  • Brandon J. Nelson, Ph.D., staff fellow in the Division of Imaging, Diagnostics and Software Reliability at the Food and Drug Administration, shared ways AI will improve diagnostic imaging and reduce radiation exposure to patients, using more advanced image reconstruction and denoising techniques. “That is really our key take-home message,” he said. “We can get what … appear as higher dose images, but with less dose.”
  • Daniel Donoho, M.D., a neurosurgeon at Children’s National, introduced the audience to the potential of “Smart ORs”: operating rooms where systems can ingest surgery video and provide feedback and skill assessments. “We have to transform the art of surgery into a measurable and improvable scientific practice,” he said.
  • Debra Regier, M.D., chief of Genetics and Metabolism at Children’s National, discussed how AI could be used to diagnose and treat rare diseases by conducting deep dives into genetics and studying dysmorphisms in patients’ faces. Already, Children’s National has designed an app – mGene – that measures facial features and provides a risk score to help anyone in general practice determine if a child has a genetic condition. “The untrained eye can stay the untrained eye, and the family can continue to have faith in their provider,” she said.

What’s next

Linguraru and others stressed the need to design AI for kids, rather than borrow it from adults, to ensure medicine meets their unique needs. He noted that scientists will need to solve challenges, such as the lack of data inherent in rare pediatric disorders and the simple fact that children grow. “Children are not mini-adults,” Linguraru said. “There are big changes in a child’s life.”

The landscape will require thoughtfulness. Naren Ramakrishnan, Ph.D., director of the Sanghani Center for Artificial Intelligence & Analytics at Virginia Tech and symposium co-host, said that scientists are heading into an era with a new incarnation of public-private partnerships, but many questions remain about how data will be shared and organizations will connect. “It is not going to be business as usual, but what is this new business?” he asked.

$1.6m grant to boost MRI access globally for maternal, child health

Researchers at Children’s National Hospital are investigating ways to bring more portable and accessible low-field magnetic resonance imaging (MRI) to parts of the world that lack access to this critical diagnostic tool, thanks to a grant from the Bill & Melinda Gates Foundation.

The nearly $1.6 million in funding will enable clinicians to better treat pediatric neurological conditions including ischemic brain injury, hydrocephalus, micro- and macrocephaly and more, using analysis tools that are designed to handle the loss in image quality and related challenges inherent to low-field MRI. The research brings together teams at Children’s National and Children’s Hospital Los Angeles — two organizations with extensive experience in designing processing software tools for pediatric brain MRI analysis and data enhancement.

The patient benefit

“For 30 years, MRI has primarily helped patients in high-income countries. Our team is thrilled by the prospect of expanding this powerful tool to patients coming from a wide range of nations, geographies and socioeconomic backgrounds,” said Marius George Linguraru, D.Phil., M.A., M.Sc., principal investigator at the Sheikh Zayed Institute for Pediatric Surgical Innovation (SZI). “Low-field MRI comes with great advantages including portability at the point of care of patients, lower clinical costs and the elimination of sedation for young children.”

Linguraru and his long-time collaborator, Natasha Lepore, Ph.D., principal investigator at The Saban Research Institute at Children’s Hospital Los Angeles, will analyze data from the brains of children from birth for the maternal and child health studies. The MRI data analyzed will form the basis for future studies of children’s brain anatomy in health and disease.

The big picture

Through the new grant, researchers will develop a suite of tools to help clinicians better analyze data and images from low-field MRI systems. These systems already have been integrated into interventional and observational studies to help characterize early neurodevelopmental patterns and identify drivers of abnormal development. They are also evaluating the efficacy of maternal and infant-focused interventions aimed at improving neurodevelopmental outcomes.

Why we’re excited

At Children’s National, SZI has installed a Hyperfine Swoop system, and Linguraru’s team is creating image enhancement tools tailored to the unique challenges of low-field MRI. Chief among them, conventional processing tools developed over the past several decades remain incompatible with the low-field data and require new software to take full advantage of the diagnostic power of imaging.

The work brings together a prestigious international consortium of scientists and clinicians from around the world to harness the power of computing and expand the reach of diagnostic imaging. Lepore said the team is eager to bring modern medical imaging to parts of the world that have missed its many benefits.

“Children’s brain development in underserved areas can be affected by so many factors, like malnutrition or anemia,” Lepore said. “The software we will design for the Hyperfine scanners will improve research into these factors, so the optimal interventions can be designed. We are excited to bring our expertise to this important and timely project.”

With COVID-19, artificial intelligence performs well to study diseased lungs

lung ct scan

New research shows that artificial intelligence can be rapidly designed to study the lung images of COVID-19 patients.

Artificial intelligence can be rapidly designed to study the lung images of COVID-19 patients, opening the door to the development of platforms that can provide more timely and patient-specific medical interventions during outbreaks, according to research published this month in Medical Image Analysis.

The findings come as part of a global test of AI’s power, called the COVID-19 Lung CT Lesion Segmentation Challenge 2020. More than 2,000 international teams came together to train the power of machine learning and imaging on COVID-19, led by researchers at Children’s National Hospital, AI tech giant NVIDIA and the National Institutes of Health (NIH).

The bottom line

Many of the competing AI platforms were successfully trained to analyze lung lesions in COVID-19 patients and measure acute issues including lung thickening, effusions and other clinical findings. Ten leaders were named in the competition, which ran between November and December 2020. The datasets included patients with a range of ages and disease severity.

Yet work remains before AI could be implemented in a clinical setting. The AI models performed comparably to radiologists when analyzing data similar to what the algorithms had already encountered. However, the AI was less valuable when trained on fresh data from other sources during the testing phase, indicating that systems may need to study larger and more diverse data sets to meet their full potential. This is a challenge with AI that has been noted by others too.

What they’re saying

“These are the first steps in learning how we can quickly and accurately train AI for clinical use,” said Marius George Linguraru, D.Phil., M.A., M.Sc., principal investigator at the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National, who led the Grand Challenge Initiative. “The global interest in COVID-19 gave us a groundbreaking opportunity to address a health crisis, and multidisciplinary teams can now focus that interest and energy on developing better tools and methods.”

Holger Roth, senior applied research scientist at NVIDIA, said the challenge gave researchers around the world a shared platform for developing and evaluating AI algorithms to quickly detect and quantify COVID lesions from lung CT images. “These models help researchers visualize and measure COVID-specific lesions of infected patients and can facilitate timelier and patient-specific medical interventions to better treat COVID,” he said.

Moving the field forward

The organizers see great potential for clinical use. In areas with limited resources, AI could help triage patients, guide the use of therapeutics or provide diagnoses when expensive testing is unavailable. AI-defined standardization in clinical trials could also uniformly measure the effects of the countermeasures used against the disease.

Linguraru and his colleagues recommend more challenges, like the lung segmentation challenge, to develop AI applications in biomedical spaces that can test the functionality of these platforms and harness their potential. Open-source AI algorithms and public curated data, such as those offered through the COVID-19 Lung CT Lesion Segmentation Challenge 2020, are valuable resources for the scientific and clinical communities to work together on advancing healthcare.

“The optimal treatment of COVID-19 and other diseases hinges on the ability of clinicians to understand disease throughout populations – in both adults and children,” Linguraru said. “We are making significant progress with AI, but we must walk before we can run.”

AI may revolutionize rheumatic heart disease early diagnosis

echocardiogram

Researchers at Children’s National Hospital have created a new artificial intelligence (AI) algorithm that promises to be as successful at detecting early signs of rheumatic heart disease (RHD) in color Doppler echocardiography clips as expert clinicians.

Researchers at Children’s National Hospital have created a new artificial intelligence (AI) algorithm that promises to be as successful at detecting early signs of rheumatic heart disease (RHD) in color Doppler echocardiography clips as expert clinicians. Even better, this novel model diagnoses this deadly heart condition from echocardiography images of varying quality — including from low-resource settings — a huge challenge that has delayed efforts to automate RHD diagnosis for children in these areas.

Why it matters

Current estimates are that 40.5 million people worldwide live with rheumatic heart disease, and that it kills 306,000 people every year. Most of those affected are children, adolescents and young adults under age 25.

Though widely eradicated in nations such as the United States, rheumatic fever remains prevalent in developing countries, including those in sub-Saharan Africa. Recent studies have shown that, if detected soon enough, a regular dose of penicillin may slow the development and damage caused by RHD. But it has to be detected.

The hold-up in the field

Diagnosing RHD requires an ultrasound image of the heart, known as an echocardiogram. However, ultrasound in general is very variable as an imaging modality. It is full of texture and noise, making it one of the most challenging to interpret visually. Specialists undergo significant training to read them correctly. However, in areas where RHD is rampant, people who can successfully read these images are few and far between. Making matters worse, the devices used in these low resource settings have their own levels of varying quality, especially when compared to what is available in a well-resourced hospital elsewhere.

The research team hypothesized that a novel, automated deep learning-based method might detect successfully diagnose RHD, which would allow for more diagnoses in areas where specialists are limited. However, to date, machine learning has struggled the same way the human eye does with noisy ultrasound images.

Children’s National leads the way

Using approaches that led to successful objective digital biometric analysis software for non-invasive screening of genetic disease, researchers at the Sheikh Zayed Institute for Pediatric Surgical Innovation, including medical imaging scientist Pooneh Roshanitabrizi, Ph.D., and Marius Linguraru, D.Phil., M.A., M.Sc., principal investigator, partnered with clinicians from Children’s National Hospital, including Craig Sable, M.D., associate chief of Cardiology and director of Echocardiography, and cardiology fellow Kelsey Brown, M.D., who are heavily involved in efforts to research, improve treatments and ultimately eliminate the deadly impacts of RHD in children. The collaborators also included cardiac surgeons from the Uganda Heart Institute and cardiologists from Cincinnati Children’s Hospital Medical Center.

Dr. Linguraru’s team of AI and imaging scientists spent hours working with cardiologists, including Dr. Sable, to truly understand how they approach and assess RHD from echocardiograms. Building the tool based on that knowledge is why this tool stands apart from other efforts to use machine-learning for this purpose. Orienting the approach to the clinical steps of diagnosis is what led to the very first deep learning algorithm that diagnoses mild RHD with similar success to the specialists themselves. After the platform was built, 2,136 echocardiograms from 591 children treated at the Uganda Heart Institute fed the learning algorithm.

What’s next

The team will continue to collect data points based on clinical imaging data to refine and validate the tool. Ultimately, researchers will look for a way that the algorithm can work directly with ultrasound/echocardiogram machines. For example, the program might be run through an app that sits on top of an ultrasound device and works on the same platform to communicate directly with it, right in the clinic. By putting the two technologies together, care providers on the ground will be able to diagnose mild cases and prescribe prophylactic treatments like penicillin in one visit.

The first outcomes from the program were showcased in a presentation by Dr. Roshanitabrizi at one of the biggest and most prestigious medical imaging and AI computing meetings — the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI).

Integrating clinical parameters with lung imaging to predict respiratory outcomes in premature babies

computer circuit board

The team will develop an objective framework to predict the risk and assess the severity of respiratory disease in premature babies using non-invasive low-radiation X-ray imaging biomarkers and clinical parameters from the patient bedside.

Children’s National Hospital received a $1.7M award from the National Institutes of Health (NIH) National Heart, Lung, and Blood Institute (NHLBI) to develop computational tools that integrate continuous clinical parameters with lung imaging to predict respiratory outcomes for babies born severely premature in newborn intensive care unit (NICU) settings.

The multi-disciplinary team of internationally recognized experts in quantitative imaging, machine learning and neonatal respiratory research believes they can improve clinical practice. To get there, they will develop an objective framework to predict the risk and assess the severity of respiratory disease in premature babies using non-invasive low-radiation X-ray imaging biomarkers and clinical parameters from the patient bedside.

“This computational tool will assist clinicians in making critical decisions about the course of therapy and other necessary follow-ups,” said Gustavo Nino, M.D., M.S.H.S., D’A.B.S.M., principal investigator in the Center for Genetic Medicine at Children’s National. “An objective informed decision about the severity of lung disease in prematurity will result in fewer rehospitalizations, better long-term outcomes and life-saving benefits.”

Prematurity is the largest single cause of death in children under five in the world. Lower respiratory tract infections (LRTI) are the top cause of hospitalization and mortality in premature infants. Clinical tools to predict the risk and assess the severity of LRTI in premature babies are needed to allow early interventions that can decrease the high morbidity and mortality in this patient group.

“Our new technology will provide clinicians an accurate, fast and comprehensive summary of the respiratory status of premature babies,” said Dr. Nino. “The data analysis along with the software technology will help determine if a premature baby seen in the NICU can be safely discharged or will require further monitoring and treatment.”

Predictive analytics could help in many ways. For example, there are instances where newborns in the NICU are on the right path with no risks in the future, but there are babies who will come back with severe infections.

“In the first scenario, if we can predict earlier that they’re fine, this could reduce the number of chest X-rays and extra tests, so we assess that this child can be safely sent home,” said Marius George Linguraru, D.Phil., M.A., M.Sc., principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National. “On the other hand, for kids that may come back to the hospital in the near future, we could predict earlier that they are not that well by looking at images and other continuous measurements such as supplemental oxygen.”

This approach, in essence, is a collection of continuous data from the NICU, which is very complex itself because it needs to be collected every day and fed into a machine learning model that digests the data to identify risk patterns for the health of the lung.

“If we find that there is still a risk, it does not necessarily mean that the child has to stay in the NICU any longer, but they might continue treatment, and we will have to define how this integrates into the clinical management of these patients,” said Linguraru. “If there is something in the data that we can put our finger on, we will know which kids require timely attention, hopefully reducing future adverse situations with potential comorbidities and financial burdens.”

How radiologists and data scientists can collaborate to advance AI in clinical practice

AI chip illustration

The scientific community continues to debate AI’s possibility of outperforming humans in specific tasks. In the context of the machine’s performance versus the clinician, Linguraru et al. argue that the community must consider social, psychological and economic contexts in addition to the medical implications to answer this puzzling question.

In a special report published in Radiology: Artificial Intelligence, a Children’s National Hospital expert and other institutions discussed a shared multidisciplinary vision to develop radiologic and medical imaging techniques through advanced quantitative imaging biomarkers and artificial intelligence (AI).

“AI algorithms can construct, reconstruct and interpret radiologic images, but they also have the potential to guide the scanner and optimize its parameters,” said Marius George Linguraru, D.Phil., M.A., M.Sc., principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National. “The acquisition and analysis of radiologic images is personalized, and radiologists and technologists adapt their approach to every patient based on their experience. AI can simplify this process and make it faster.”

The scientific community continues to debate AI’s possibility of outperforming humans in specific tasks. In the context of the machine’s performance versus the clinician, Linguraru et al. argue that the community must consider social, psychological and economic contexts in addition to the medical implications to answer this puzzling question.

Still, they believe that developing a useful radiologic AI system designed with the participation of radiologists could complement and possibly surpass human’s interpretation of the visuals.

Given AI’s potential applications, the authors encouraged radiologists to access many freely available resources to learn about machine learning, and radiomics to familiarize with basic concepts. Coursera, for example, can teach radiologists about convolutional neural networks and other techniques used by AI researchers.

Conversely, AI experts must reach out to radiologists and participate in public speaking events about their work. According to the researchers, during those engagement opportunities, clinicians understood the labor-saving benefits of automatic complex measurements on millions of images—something that they have been doing manually for years.

There are also hurdles around this quest of automation, which Linguraru et al. hope both fields can sort out by working together. A critical challenge that the experts mentioned was earning the trust of clinicians that are skeptical about the “black box” functionality of AI models, which makes it hard to understand and explain the behavior of a model.

Some questions, too, need answers on how to best leverage both human intelligence and AI by using human-in-the-loop where people train, tune, and test a particular algorithm, or AI in-the-loop where this different framing generates AI input and reflection in human systems.

“The key is to have a good scientific premise to adequately train and validate the algorithms and make them clinically useful. At that point, we can trust the box,” said Linguraru. “In radiology, we should focus on AI systems with radiologists in-the-loop, but also on training radiologists with AI in-the-loop, particularly as AI systems are getting smarter and learning to work better with radiologists.”

The experts also provided possible solutions to sharing large datasets, how to build datasets that allows robust investigations and how to improve the quality of a model that might be compared against human’s gold standard.

This special report is the second in a series of panel discussions hosted by the Radiological Society of North America and the Medical Image Computing and Computer Assisted Intervention Society. The discussion builds upon the first in the series “Machine Learning for Radiology from Challenges to Clinical Applications” that touched on how to incentivize annotators to participate in projects, the promotion of “team science” to address research questions and challenges, among other topics.