Translational Imaging Research Unit

The Translational Imaging Research Unit (TIRU) hosts and manages large-scale, multi-site repositories of biomedical imaging data for researchers at CHOP and around the world as a core center for the Children’s Brain Tumor Network. The goal of this work is to provide researchers access to rich, complex datasets to ultimately accelerate discoveries in pediatric brain cancer and translate results back to patient care in the clinic.


Focus Area 1: Data processing & Analytics

To support reproducible research, we develop scalable pipelines and standardized workflows for data processing and deploy them in a cloud-based ecosystem. Additionally, we leverage state of the art techniques in artificial intelligence and machine learning to extract complex imaging features and diagnostic biomarkers to perform predictive analytics of clinical measures. Our team involves both researchers and clinicians, creating a collaborative and impactful environment that unites ideas, methods, and data.


Focus Area 2: Cancer Imaging Research

Our ongoing research projects include: (1) Relating imaging measurements to genetic and molecular characteristics of disease; (2) Utilizing molecular imaging to monitor treatment response in clinical trials; (3) Identifying and testing promising molecular imaging targets using in-vitro and small animal imaging (4) Applying deep learning to develop advanced methods for image analysis.



November 2023 – Adding Value to Liquid Biopsy for Brain Tumors: The Role of Imaging (Cancers)

September 2023 – Radio-pathomic Approaches in Pediatric Neuro-Oncology; Opportunities and Challenges (Neuro-Oncology Advances)

August 2023 – Statistical Plots in Oncologic Imaging, A Primer for Neuroradiologists (The Neuroradiology Journal)

June 2023 – Radiomics for Characterization of the Glioma Immune Microenvironment (Nature Precision Genomics)

March 2023 – Automated Tumor Segmentation and Brain Tissue Extraction from Multiparametric MRI of Pediatric Brain Tumors: A Multi-institutional Study (Neuro-Oncology Advances)

March 2023 – Current State of Pediatric Neuro-oncology Imaging, Challenges and Future Directions (Elsevier)

February 2023 – Unsupervised Machine Learning Using K-means Identifies Radiomic Subgroups of Pediatric Low-grade Gliomas that Correlate with Key Molecular Markers (Neoplasia)

May 2022 – Radiomics and Radiogenomics in Pediatric Neuro-oncology: A Review (Neuro-Oncology Advances)