Peer-reviewed article

NEIM-07 HARNESSING END-TO-END CLOUD-BASED WORKFLOWS AND MULTI-MODAL DATA ANALYTICS IN PEDIATRIC BRAIN TUMOR IMAGING AT THE CHILDREN’S BRAIN TUMOR NETWORK (CBTN)

· 1 Aug 2023

Abstract

Abstract Neuroimaging is an essential component of the standard of care in pediatric brain tumor patients. Developing efficient and agile workflows for image processing and integration of imaging with other data types to perform predictive analytics is an increasing need. At CBTN, we developed user-friendly workflows to support the entire imaging data lifecycle and to bridge access to multi-modal datasets with scalable analytics, to empower researchers to make breakthrough discoveries that will advance patient care. An automated deep learning-based brain extraction and tumor subregion segmentation model based on a multi-institutional dataset was developed that can reliably segment the treatment-naïve MRI scans of children across a variety of brain tumor histologies. This model was subsequently integrated into an end-to-end imaging pipeline for collecting, managing and analyzing clinically acquired radiology exams of the CBTN consortium with processing of 19,975 exams (1,443 subjects) to date. Critically, the constituent software tools enable the preparation of images for downstream AI analytics, from acquisition to feature extraction. A public website was also created to allow users to search and explore the dataset based on sequence labels, and clinical and imaging attributes. In addition, we established a scalable workflow and processes for de-identification, ingestion, quality control, and management of digital pathology slides for CBTN (over 8,000 slides to date). Finally, we evaluated the feasibility of interoperability between imaging (Flywheel) and molecular (CAVATICA) platforms deployed in cloud ecosystems which can allow streamlined, user-friendly workflows to ingest and harmonize files, perform cohort selection, prepare data using standard processing packages and cloud resources, and conduct analysis on extracted multi-modal feature sets. The described workflow lays the foundation for the broad use of imaging studies and access to multi-modal datasets and analytics, with the goal of empowering researchers to make breakthroughs in patient care.