Department: Radiology and Imaging Sciences
Project:
In partnership with researchers from the Radiology Department, the Enterprise Data Warehouse (EDW) and the Center for High Performance Computing (CHPC), we have developed software and hardware infrastructure to support secured data transfer (from the hospital PACS), HIPAA-compliant data storage (via databases) and data management of large radiological datasets, to enable deep learning and natural language processing analyses.
Progress:
We have been querying, retrieving and managing 2D chest X-ray imaging data from 59,000+ patients (140,000 studies) to study retrospective thoracic imaging studies. Driving clinical applications include chronic obstructive pulmonary disease (COPD), COVID-19 and acute respiratory infections. Data management entails both radiological images and clinical text reports in a HIPAA-compliant environment at CHPC.
1. J.D. Schroeder et al., Prediction of obstructive lung disease from chest radiographs via deep learning trained on pulmonary function data, International Journal of Chronic Obstructive Pulmonary Disease, 2020
2. R. Lanfredi et al., Interpretation of disease evidence from medical images using adversarial deformation fields, MICCAI 2020
3. R. Lanfredi et al., Adversarial regression training for visualizing the progression of chronic obstructive pulmonary disease with chest x-rays, MICCAI 2019