AI chip illustration

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.

Charles Berul

Charles Berul, M.D., receives Meritorious Achievement Award

Charles Berul

Charles Berul, M.D., chief of Cardiology at Children’s National Hospital has earned a lifetime achievement award, the 2021 Council on Lifelong Congenital Heart Disease and Heart Health in the Young (Young Hearts) Meritorious Achievement Award.

The Meritorious Achievement Award recognizes a person whose achievements have made a significant impact in the field of congenital heart disease and heart health in the young and have helped to further the mission of the Young Hearts council. The council’s mission is to improve the health of children and adults with congenital heart disease and acquired heart disease during childhood through research, education, prevention and advocacy.

Dr. Berul received this award in recognition of his lifelong achievements in the field of pediatric electrophysiology. He is known for his development of innovative electrophysiologic studies for phenotypic evaluations of genetically manipulated pre-clinical models. Over the past two decades, his research focus and passion have been to develop novel minimally invasive approaches to the heart and improving methods for pediatric pacing and defibrillation.

He has also mentored dozens of trainees who have gone on to successful careers and particularly advocates for young investigators and clinician-scientists. He is known for his collaborative style and for supporting advancement of faculty physicians in academic medicine.

Dr. Berul has served on multiple society committees, task forces and writing groups, and is currently an associate editor for the Heart Rhythm Society’s journal. He is also actively involved in other key organizations such as Mended Little Hearts and the Pediatric and Congenital Electrophysiology Society (PACES). He has more than 300 publications and is an invited speaker nationally and internationally in the areas of pediatric cardiac electrophysiology and miniaturized device development.

Dr. Berul received the award on November 12 during a virtual presentation at the American Heart Association’s Scientific Sessions. He is the fourth Children’s National cardiologist to be recognized with this prestigious honor from the council in the last decade.

brain network illustration

Cardiopulmonary bypass may cause significant changes to developing brain and nerve cells

brain network illustration

Cardiopulmonary bypass, more commonly known as heart-and-lung bypass, has some unique impacts on the creation and growth of brain cells in the area of a child’s brain called the subventricular zone (SVZ), according to a study in the Annals of Neurology. The SVZ is a critical area for the growth and migration of neurons and nerve cells called neuroblasts, both of which ultimately contribute to the proper development of key brain structures and functions during the early years of life.

The findings, from a study conducted in the Cardiac Surgery Research Laboratory at Children’s National Hospital, provide new insight into the cellular impacts of the cardiopulmonary bypass machine on brain growth and development for newborn infants with congenital heart disease. They will have an important role in the refinement of strategies to help protect the fragile brains of children who require lifesaving cardiac surgery with cardiopulmonary bypass immediately after birth.

Specifically, the research team found that during cardiopulmonary bypass:

  • Creation of neurons (neurogenesis) in the neonatal and infant subventricular zone is altered.
  • Migration of nerve cells, called neuroblasts, to the frontal lobe is potentially disrupted.
  • Changes to the growth and movement of neurons in the SVZ are prolonged.
  • Cortical development and expansion is impaired.
  • Specific types of neurons found only in the brain and spinal cord, called interneurons, are also affected.

The study uses an innovative pre-clinical model of the developing brain that is more anatomically and physiologically similar to human neonates and infants than those used in prior studies and in most neurological laboratory-based research.

Cardiopulmonary bypass is one of several key factors thought to cause children with congenital heart disease to sometimes demonstrate delays in the development of cognitive and motor skills. These disabilities often persist into adolescence and adulthood and can ultimately represent long-term neurocognitive disabilities. It is also believed that genetic factors, abnormal blood flow to the brain while in utero or low cardiac output after surgical procedures on the heart may contribute to these challenges.

“Unraveling cellular and molecular events during surgery using this preclinical model will allow us to design therapeutic approaches that can be restorative or reparative to the neurogenic potential of the neuronal stem precursor cells found in the subventricular zone of the neonatal or infant brain,” says Nobuyuki Ishibashi. M.D., Foglia-Hills Professor of Pediatric Cardiac Research, director of the Cardiac Surgery Research Laboratory at Children’s National and senior author on the study. “In particular, previous studies in our laboratory have shown improvement in the neurogenic activities of these precursor cells when they are treated with mesenchymal stromal cells (MSCs).”

The findings from this study further support the work already underway in the NIH-funded MeDCaP clinical trial for neonates and infants undergoing cardiac surgery using the cardiopulmonary bypass machine. That trial uses the heart and lung machine itself to deliver MSCs directly into the main arteries that carry blood to the brain.

Matthew Oetgen

Matthew Oetgen, M.D., M.B.A, lauded for paper on treating Compartment Syndrome

Matthew Oetgen

For his work in advancing the care for children with complex orthopaedic needs, Matthew Oetgen, M.D., M.B.A., chief of Orthopaedics at Children’s National Hospital, recently accepted the award for Best Basic Science Paper at the 2021 Pediatric Orthopaedic Society of North America (POSNA) annual meeting. Dr. Oetgen co-authored the paper titled “Activation of A Central Immunosuppressive Cascade Prevents Ischemia Reperfusion Injury after Acute Compartment Syndrome in a Murine Model.”

Compartment Syndrome is rare and often difficult to diagnose. It occurs when interstitial pressure exceeds perfusion pressure and results in warm ischemia and cell death due to impaired aerobic metabolism. Following surgical decompression and reperfusion of the extremity, a robust innate inflammatory response results in further tissue injury due to the production of reactive oxygen species and local capillary dysfunction.

The authors described using varenicline, an FDA-approved medication for smoking cessation, to mitigate inflammation after ischemia reperfusion injury in murine models. Twenty-four hours after reperfusion, the treatment reduced acute leukocyte infiltrate, 7 days following reperfusion, the expression of pro-fibrotic genes was reduced and 14 days following treatment, histologic evidence of collagen deposition was also significantly reduced.

“The promising results of this study show that this medication may have the potential to blunt the immune response resulting in better outcomes for children with compartment syndrome,” says Dr. Oetgen.

Watch Dr. Oetgen’s presentation here.

x-ray of human skull

Researchers awarded $3.5 million to study brain and cranium development in children

x-ray of human skull

Currently, studies on typical brain and cranium development are limited. One reason for this is that imaging techniques are optimized to best visualize either bone or soft tissue, but not both.

With prevalence of developmental disorders on the rise, the need to understand brain development has never been more critical. Development of the brain is strongly influenced by the cranium, but this relationship has not been adequately studied because of limitations in imaging technology. Now, researchers from Children’s Hospital Los Angeles and Children’s National Hospital are working together to develop techniques that will provide greater insight into this relationship. Their studies will be funded by The National Institute of Dental and Craniofacial Research, which has awarded them $3.5 million.

Natasha Leporé, Ph.D., of Children’s Hospital Los Angeles, studies methods to interpret brain imaging data. “There’s a lot of interaction between the skull and the brain,” she says, “and we want to better understand how they grow together.”

Currently, studies on typical brain and cranium development are limited. One reason for this is that imaging techniques are optimized to best visualize either bone or soft tissue, but not both.

The brain — mostly composed of water, protein and fat — doesn’t show up well on computerized tomography (CT) scans, which use X-ray images. In addition, radiation exposure limits the amount of CT scan data available in children. On the other hand, magnetic resonance imaging (MRI) scans are excellent for brain images but are not optimal for surrounding bone.

This presents researchers with a dilemma if they want to see the brain and the skull together in one image. Fortunately, research barriers like these are often overcome by collaboration.

Leporé will work with Marius George Linguraru, D.Phil, M.A., MS.c., principal investigator in the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National Hospital.

Linguraru works on a set of tools for cranial phenotyping, using existing CT images from typically developing children. In their collaboration, Leporé and Linguraru will extend the tools to MRI scans, allowing the team to analyze the brain and cranium simultaneously. The pair has received a $3.5 million award over 5 years.

“The tools we develop together will help us to better understand the healthy growth of children,” says Linguraru. “We will have the ability to analyze the joint cranial and brain development from large medical image datasets of pediatric patients.”

This, the team says, will be invaluable to the medical community.

“These tools will help clinicians to better assess, diagnose and plan treatment for infants with cranial deformities,” says Linguraru.

Collaborations like this allow expertise to be shared across specialties, ultimately benefiting children in need. Exceptional pediatric care is a result of teamwork; not only doctors, nurses and clinical staff, but also biomedical research, which arms clinicians with the information they depend on.

“We need to have a clear idea of what is expected in normal development,” says Leporé. “This allows doctors to detect and better understand differences in development.”

Other members of the research team include: Vidya Rajagopalan, Ph.D.; Marvin Nelson, M.D.; Alexis Johns, Ph.D.; Niharika Gajawelli, Ph.D. (from Children’s Hospital Los Angeles and University of Southern California); Robert Keating, M.D. (Children’s National Hospital); Yalin Wang, Ph.D. (Arizona State University); Antonio Porras, Ph.D. (University of Colorado); Sean Deoni, Ph.D. (Rhode Island Hospital and Brown University).

A version of this story appeared on the Children’s Hospital Los Angeles newsroom.

x-ray of child's chest with COVID

Chest X-rays help distinguish COVID-19 from other types of viral respiratory infections

x-ray of child's chest with COVID

COVID-19 in a 9-month infant demonstrating a GGO/consolidation pattern.

Increased infections of COVID-19 and other respiratory viruses in kids are filling up children’s hospitals, pushing them to critical occupancy nationwide. As schools open, the community spread of viral infections has become more common, and the rapid differentiation of pediatric COVID-19 from other viruses is — more than ever — relevant to pediatric clinicians.

“Pediatric cases have increased exponentially and currently represent over 15% of the total cases, and about 26% of the new infections in the U.S. Chest imaging is a powerful tool for determining their status.” 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 Hospital.

In a new peer-reviewed study, researchers from Children’s National found novel and clinically relevant data regarding the specific lung imaging patterns of pediatric COVID-19 on chest radiographs (CXR), their relationship to clinical outcomes and the possible differences from infections caused by other respiratory viruses in children.

“While most studies have focused on clinical manifestations and lung imaging of COVID-19 in adults, this study is the first to define specific patterns of clinical disease and imaging signatures in CXR in different age groups of children infected with COVID-19,” said Gustavo Nino, M.D., director of sleep medicine at Children’s National.

Lung imaging has become critically important for the early identification and treatment of pediatric patients affected by COVID-19 and may play an important role in distinguishing COVID-19 infection from viral bronchiolitis.

“The old perception that COVID-19 only affects older patients is no longer true,” said Dr. Nino. “Pediatric intensive care units and emergency departments are overwhelmed with COVID-19 cases, and now hospitals are admitting more children with COVID-19 than ever.”

As next steps, Nino et al. will develop pediatric-centered technology for early identification, risk stratification, and outcome prediction of COVID-19 in children, similar to what the scientific community has done for adults.

control population and population with Williams-Beuren syndrome.

Machine learning tool detects the risk of genetic syndromes

control population and population with Williams-Beuren syndrome.

(A) Control population. (B) Population with Williams-Beuren syndrome. Average faces were generated for each demographic group after automatic face pose correction.

With an average accuracy of 88%, a deep learning technology offers rapid genetic screening that could accelerate the diagnosis of genetic syndromes, recommending further investigation or referral to a specialist in seconds, according to a study published in The Lancet Digital Health. Trained with data from 2,800 pediatric patients from 28 countries, the technology also considers the face variability related to sex, age, racial and ethnic background, according to the study led by Children’s National Hospital researchers.

“We built a software device to increase access to care and a machine learning technology to identify the disease patterns not immediately obvious to the human eye or intuition, and to help physicians non-specialized in genetics,” 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 Hospital and senior author of the study. “This technological innovation can help children without access to specialized clinics, which are unavailable in most of the world. Ultimately, it can help reduce health inequality in under-resourced societies.”

This machine learning technology indicates the presence of a genetic syndrome from a facial photograph captured at the point-of-care, such as in pediatrician offices, maternity wards and general practitioner clinics.

“Unlike other technologies, the strength of this program is distinguishing ‘normal’ from ‘not-normal,’ which makes it an effective screening tool in the hands of community caregivers,” said Marshall L. Summar, M.D., director of the Rare Disease Institute at Children’s National. “This can substantially accelerate the time to diagnosis by providing a robust indicator for patients that need further workup. This first step is often the greatest barrier to moving towards a diagnosis. Once a patient is in the workup system, then the likelihood of diagnosis (by many means) is significantly increased.”

Every year, millions of children are born with genetic disorders — including Down syndrome, a condition in which a child is born with an extra copy of their 21st chromosome causing developmental delays and disabilities, Williams-Beuren syndrome, a rare multisystem condition caused by a submicroscopic deletion from a region of chromosome 7, and Noonan syndrome, a genetic disorder caused by a faulty gene that prevents normal development in various parts of the body.

Most children with genetic syndromes live in regions with limited resources and access to genetic services. The genetic screening may come with a hefty price tag. There are also insufficient specialists to help identify genetic syndromes early in life when preventive care can save lives, especially in areas of low income, limited resources and isolated communities.

“The presented technology can assist pediatricians, neonatologists and family physicians in the routine or remote evaluation of pediatric patients, especially in areas with limited access to specialized care,” said Porras et al. “Our technology may be a step forward for the democratization of health resources for genetic screening.”

The researchers trained the technology using 2,800 retrospective facial photographs of children, with or without a genetic syndrome, from 28 countries, such as Argentina, Australia, Brazil, China, France, Morocco, Nigeria, Paraguay, Thailand and the U.S. The deep learning architecture was designed to account for the normal variations in the face appearance among populations from diverse demographic groups.

“Facial appearance is influenced by the race and ethnicity of the patients. The large variety of conditions and the diversity of populations are impacting the early identification of these conditions due to the lack of data that can serve as a point of reference,” said Linguraru. “Racial and ethnic disparities still exist in genetic syndrome survival even in some of the most common and best-studied conditions.”

Like all machine learning tools, they are trained with the available dataset. The researchers expect that as more data from underrepresented groups becomes available, they will adapt the model to localize phenotypical variations within more specific demographic groups.

In addition to being an accessible tool that could be used in telehealth services to assess genetic risk, there are other potentials for this technology.

“I am also excited about the potential of the technology in newborn screening,” said Linguraru. “There are approximately 140 million newborns every year worldwide of which eight million are born with a serious birth defect of genetic or partially genetic origin, many of which are discovered late.”

Children’s National as well recently announced that it has entered into a licensing agreement with MGeneRx Inc. for its patented pediatric medical device technology. MGeneRx is a spinoff from BreakThrough BioAssets LLC, a life sciences technology operating company focused on accelerating and commercializing new innovations, such as this technology, with an emphasis on positive social impact.

“The social impact of this technology cannot be underestimated,” said Nasser Hassan, acting chief executive officer of MGeneRx Inc. “We are excited about this licensing agreement with Children’s National Hospital and the opportunity to enhance this technology and expand its application to populations where precision medicine and the earliest possible interventions are sorely needed in order to save and improve children’s lives.”

Drs. Packer and van den Acker at the Pediatric Device Innovators Forum

Pediatric Device Innovators Forum explores state of focused ultrasound

For children living with pediatric tumors, less invasive and less painful treatment with no radiation exposure was not always possible. In recent years, the development of technologies like Magnetic resonance guided high intensity focused ultrasound (MR-HIFU) and Low intensity transcranial focused ultrasound (LIFU) is helping to reverse that trend.

This topic was the focus of the recent Pediatric Device Innovators Forum (PDIF) hosted by the National Capital Consortium for Pediatric Device Innovation (NCC-PDI) in partnership with the U.S. Food and Drug Administration’s (FDA) Pediatric Device Consortia (PDC) grant program. A collaboration between Children’s National Hospital and University of Maryland Fischell Institute for Biomedical Devices, NCC-PDI is one of five PDCs funded by the FDA to support pediatric device innovators in bringing more medical devices to market for children.

The discussion, moderated by Kolaleh Eskandanian, Ph.D., MBA, PMP, vice president and chief innovation officer at Children’s National and principal investigator of NCC-PDI, explored the use of focused ultrasound’s noninvasive therapeutic technology for two pediatric indications, Osteoid Osteoma (OO) and Diffuse Intrinsic Pontine Glioma (DIPG), and the ways it can increase the quality of life for pediatric patients while also decreasing the cost of care.

The discussion also examined the most common barriers preventing more widespread implementation of focused ultrasound technology, specifically small sample size for evidence generation, lack of funding opportunities and reimbursement issues that can make or break a technology’s chances at reaching the patients that need it.

Karun Sharma, M.D., director of Interventional Radiology at Children’s National, emphasized the potential for focused ultrasound to treat localized pain relief and treat other diseases that, like OO, do not have any other therapeutic alternative

“At Children’s National, we use MR-HIFU to focus an ultrasound beam into lesions, usually tumors of the bone and soft tissues, to heat and destroy the harmful tissue in that region, eliminating the need for incisions,” says Sharma. “In 2015, Children’s National doctors became the first in the U.S. to use MR-HIFU to treat pediatric osteoid osteoma (OO), a painful, but benign, bone tumor that commonly occurs in children and young adults. The trial demonstrated early success in establishing the safety and feasibility of noninvasive MR-HIFU in children as an alternative to current, more invasive approaches to treat these tumors.”

In November 2020, the FDA approved this MR-HIFU system to treat OO in pediatric patients.

Roger Packer, M.D., senior vice president of the Center for Neuroscience and Behavioral Medicine at Children’s National, also discussed how focused ultrasound, specifically LIFU, has also proven to be an attractive modality for its ability to non-invasively, focally and temporarily disrupt the blood brain barrier (BBB) to allow therapies to reach tumors that, until recently, would have been considered unreachable without severe intervention.

“This presents an opportunity in pediatric care to treat conditions like Diffuse Intrinsic Pontine Glioma (DIPG), a highly aggressive brain tumor that typically causes death and morbidity,” says Packer.

Packer is planning a clinical trial protocol to investigate the safety and efficacy of LIFU for this pediatric indication.

The forum also featured insight from Jessica Foley, M.D., chief scientific officer, Focused Ultrasound Foundation; Arjun Desai, M.D., chief strategic innovation officer, Insighttec; Arun Menawat, M.D., chairman and CEO, Profound Medical; Francesca Joseph, M.D., Children’s National; Johannes N. van den Anker, M.D., Ph.D., vice chair of Experimental Therapeutics, Children’s National; Gordon Schatz, president, Schatz Reimbursement Strategies; Mary Daymont, vice president of Revenue Cycle and Care Management, Children’s National; and Michael Anderson, MD, MBA, FAAP, FCCM, FAARC, senior advisor to US Department of Health and Human Services (HHS/ASPR) and Children’s National.

Anthony Sandler, M.D., senior vice president and surgeon-in-chief of the Joseph E. Robert Jr. Center for Surgical Care and director of the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National Hospital, and Sally Allain, regional head of Johnson & Johnson Innovation, JLABS @ Washington, DC, opened the forum by reinforcing both organizations’ commitment to improving pediatric health.

In September 2020, the Focused Ultrasound Foundation designated Children’s National Hospital as the first global pediatric Center of Excellence for using this technology to help patients with specific types of childhood tumors. As a designated COE, Children’s National has the necessary infrastructure to support the ongoing use of this technology, especially for carrying out future pediatric clinical trials. This infrastructure includes an ethics committee familiar with focused ultrasound, a robust clinical trials research support team, a data review committee for ongoing safety monitoring and annual safety reviews, and a scientific review committee for protocol evaluation.

The Pediatric Device Innovators Forum is a recurring collaborative educational experience designed by the FDA-supported pediatric device consortia to connect and foster synergy among innovators across the technology development ecosystem interested in pediatric medical device development. Each forum is hosted by one of the five consortia. This hybrid event took place at the new Children’s National Research and Innovation Campus, the first-of-its-kind focused on pediatric health care innovation, on the former Walter Reed Army Medical Center campus in Washington, D.C.

To view the latest edition of the forum, visit the NCC-PDI website.

Panelists at the Pediatric Device Innovators Forum

The recent Pediatric Device Innovators Forum (PDIF) exploring the state of focused ultrasound was held at the new Children’s National Research and Innovation Campus, a first-of-its-kind focused on pediatric health care innovation.