Childhood (diffuse) interstitial lung diseases affects infants, children, and teens andmanifests as dyspnea, hypoxemia, and respiratory compromise resulting in highmorbidity and mortality or life-long sequelae for survivors. Despite improvements in theunderstanding of and interventions for pediatric diffuse lung disease in the past 15 years, the current standard-of-care for confirmation and characterization of chILD bythin-section chest computed tomography (CT) has had limited progress through visualassessments that are inherently subjective and suffer from inter-reader variability indefining the specific characteristic findings. This can limit accurate diagnosis of earlyand progressive disease and translates to a more time-consuming and burdensomeclinical evaluation. An automated and objective approach to quantify commonradiological lung CT patterns observed in ILDs specifically in pediatrics would providemore reliable information and reduce costs by standardizing and streamlining image-based assessment.In this grant proposal, Imbio Inc., an industry leader in developing, commercializing, andachieving regulatory approval of imaging biomarker software, proposes to develop afully-automated software application for quantifying lung CT textures. The collaborationleverages the clinical and research expertise at the Children's Hospital Los Angeles(CHLA) which is a large, safety-net pediatric hospital. The specific aims are 1) todevelop a data repository of chest CT scans in subjects with pediatric diffuse lungdisease and control subjects along with expert annotations of radiologic textures and 2)develop and validate an integrated pediatric/adult deep-learning-based algorithm toquantify radiological lung textures (i.e., DeepLTA). Upon completion of the aims, thefinal algorithm will have broad applicability and generalizability to detect parenchymalCT textures in both adult and pediatric ILDs. This will enable a Phase II submission andintegration of this software to enhance pediatric access to state-of-the-art quantitativemedical imaging analysis for improved prognosis, diagnosis, and therapy responseassessment in pediatric interstitial lung disease.
Public Health Relevance Statement: PROJECT NARRATIVE
Childhood (diffuse) interstitial lung disease comprises a group of parenchymal lung
disorders associated with high morbidity and mortality and life-long sequelae for
survivors. Development of imaging technology targeted towards automating
identification of common radiological lung CT patterns in pediatric populations with
interstitial lung disease is critical to improve early detection, accurately assess disease
severity, and stratify patients based on therapeutic response thereby improving clinical
outcomes in these patients. This project coalesces a unique pediatric diffuse lung
disease chest CT imaging data repository and validates a deep-learning-based Lung
Texture Analysis (DeepLTA) software to automate quantitative analysis for improved
prognosis and diagnosis in childhood diffuse lung disease.
Project Terms: <21+ years old><0-11 years old>
