SBIR-STTR Award

Prematurity is the largest single cause of death in children under five in the world and lower respiratory tract infections (LRTI) are the top cause of hospitalization and mortality in premature infants. Clinical tools to predict and prevent severe LRTI in premature pediatric patients are critically needed to allow early interventions to decrease the high morbidity and mortality in this patient group. Although imaging biomarkers of lung disease from computed tomography have been successfully used in adults, they entail heightened risks for children due to cumulative radiation and the need for sedation. Our goal is to address these gaps and improve clinical practice by developing an objective imaging biomarker framework to assess the risk of severe respiratory disease in premature babies using non-invasive low-radiation X-ray imaging. Previous efforts lead by Dr. Linguraru (Principal Investigator) at Children's National Health System (CNHS) have focused on developing technical components to quantify lung structural data from chest X-ray (CXR) in children. The image processing pipeline developed at CNHS integrates three novel technical components: a) automatic lung segmentation, b) obtrusive object removal in CXR, and c) severity quantification of lung pathology. These innovations enabled the development of a quantitative imaging software technology to quantify Lung Air trapping and Irregular opacities Radiological analyzer (LungAIR). This Phase I project builds on the methodology developed in preliminary work. We will analyze a large database (n=200) of retrospective CXR images from premature infants with known clinical outcomes, and further develop and validate lung imaging biomarkers. In Specific Aim 1 we will design and implement a prototype of the software technology (LungAIR) for the localization and quantification of heterogeneous aeration patterns in each lung quadrant through quantitative imaging algorithms. A graphical user interface will also be developed for the simple clinical use of the technology. In Specific Aim 2 we will perform clinical outcome analysis to correlate these biomarkers with the severity of lung disease. We will also combine our new imaging biomarkers with clinical parameters to design and evaluate a predictive model of LRTI risk in the first year of life to optimize the clinical management and improve the outcomes for premature babies. In this project, CNHS partners with Kitware to translate our research into a clinical software application and lay the groundwork for further developments and clinical studies in Phase II. In summary, our approach will enable better clinical management of diseases of prematurity leading to novel diagnostic strategies to improve treatment and outcomes for the highly vulnerable population of premature infants.

Public Health Relevance Statement:
PROJECT NARRATIVE Prematurity is the largest single cause of death in children under five in the world and lower respiratory tract infections (LRTI) are the top cause of hospitalization and mortality in premature infants. Clinical tools to predict and prevent severe LRTI in premature pediatric patients are critically needed to allow early interventions to decrease the high morbidity and mortality in this patient group. In this project, we will develop and evaluate a quantitative imaging technology to assess the risk for severe respiratory disease in premature babies using non-invasive low-radiation X-ray imaging.

Project Terms:
Address; Adult; Air; Algorithms; base; Biological Markers; Bronchopulmonary Dysplasia; Cause of Death; Child; Chronic; Clinical; clinical application; clinical decision-making; Clinical Management; Clinical Markers; clinical practice; Clinical Research; clinical translation; Collaborations; Complement; Complication; Computer software; cost; Country; Data; Databases; deep learning; design; Development; Diagnostic radiologic examination; Disease Management; Early identification; Early Intervention; Excision; Goals; Graph; graphical user interface; Health system; Healthcare; Heterogeneity; high risk; Hospitalization; Image; image processing; imaging biomarker; Imaging Device; imaging software; Imaging technology; improved; improved outcome; infant monitoring; Infant Mortality; innovation; Lead; Learning; Life; Lower Respiratory Tract Infection; Lower respiratory tract structure; Lung; lung basal segment; Lung diseases; lung imaging; Measures; Methodology; Monitor; Morbidity - disease rate; mortality; multidisciplinary; Neonatal Intensive Care Units; Neonatology; news; novel; novel diagnostics; Outcome; Patients; Pattern; Pediatric Hospitals; pediatric patients; Phase; predictive modeling; Pregnancy; premature; Premature Infant; prevent; Principal Investigator; programs; prototype; Pulmonary Pathology; quantitative imaging; Radiation; Radiology Specialty; Reporting; Research; research clinical testing; respiratory; Respiratory Tract Infections; Risk; Risk Assessment; Risk stratification; Roentgen Rays; Sampling; Sedation procedure; Severities; Severity of illness; Shapes; Small Business Technology Transfer Research; Software Engineering; Specialist; standard of care; Technology; Therapy Clinical Trials; Thoracic Radiography; Time; tool; Translating; Treatment outcome; Validation; Vulnerable Populations; Work; X-Ray Computed Tomography

Prematurity is the largest single cause of death in children under five in the world and lower respiratory tractinfections (LRTI) are the top cause of hospitalization and mortality in premature infants. Clinical tools to predictthe risk and assess the severity of LRTI in premature babies are critically needed to allow early interventions todecrease the high morbidity and mortality in this patient group. Our goal is to improve clinical practice bydeveloping an objective framework to predict the risk and assess the severity of respiratory disease in prematurebabies using non-invasive low-radiation X-ray imaging biomarkers and clinical parameters. In the Phase I of this project, our multidisciplinary team of pulmonologists, neonatologists and imaging andmachine learning specialists developed an imaging software technology called Lung Aeration and Irregularopacities Radiological analyzer (LungAIR). Our accomplishments include: 1) establishing a curated ground truthof focal findings in chest X-Ray (CXR) of premature babies; 2) developing a machine learning algorithm toautomatically localize and quantify CXR-based prematurity lung disease signatures (fibrosis/interstitial opacities,cystic changes and hyperinflation); 3) creating a graphical user interface for clinical deployment; and 4)evaluating our imaging software technology in an independent cohort. We also demonstrated that the imagingbiomarkers obtained by LungAIR correlate strongly with the severity of bronchopulmonary dysplasia (BPD)-themost common respiratory complication of prematurity-- and the cumulative exposure to supplemental O2 andmechanical ventilation in the neonatal intensive care unit (NICU) (p<0.001). Importantly, our preliminary resultsindicated that the combination of imaging and clinical markers (BPD severity) provide an accurate predictivemodel for LRTI-related complications in the first year of life (AUC=74, p<0.01). This Phase II project builds on the findings and methodology developed in Phase I. In Specific Aim 1, we willincorporate a model of lung disease risk factors in LungAIR platform. Our software will ingest respiratory supportinformation daily during NICU hospitalization and integrate the data with CXR analysis. In Specific Aim 2, we willextend LungAIR to perform longitudinal analyses during hospitalization with the potential to accelerate theprediction of health risks. We will also integrate our results with the electronic health record of the patient forimprove the clinical workflow. In Specific Aim 3 we will conduct a clinical study to prospectively evaluate theLungAIR clinical platform functionality. The proposal includes the business model and a path to commercializingLungAIR. The early identification of premature babies at high risk for BPD and severe LRTI should improve theiroutcome, reduce hospitalization times and inherent clinical costs, and decrease infant mortality. In addition, theability to objectively quantify and track lung imaging biomarkers will also guide therapy and clinical trials, as wellas improve the longitudinal monitoring of infants.

Public Health Relevance Statement:
PROJECT NARRATIVE Prematurity is the largest single cause of death in children under five in the world and lower respiratory tract infections (LRTI) are the top cause of hospitalization and mortality in premature infants. Clinical tools to predict and prevent severe LRTI in premature pediatric patients are critically needed to allow early interventions to decrease the high morbidity and mortality in this patient group. In this project, we will develop and evaluate a quantitative imaging software technology to predict the risk and assess the severity of respiratory diseases in premature babies using non-invasive low-radiation X-ray imaging and clinical parameters.

Project Terms:
<0-11 years old>