Department: Radiology and Imaging Sciences
Project:
We aim to predict the severity of restrictive pulmonary function in patients with interstitial lung disease (ILD) from chest radiographs using deep convolutional neural networks. For this clinical project, we executed various stages entailing HIPAA-compliant data transfer and management, data preparation and data cleaning, as well as data analytics. This multi-modal dataset includes unstructured chest x-ray acquisitions, metrics from pulmonary function tests, along with demographic and clinical information. These initial stages in the data science workflow provide a clean dataset of 1500+ cases available for deep learning.
Publications:
1. J. Chan et al., Using deep learning to predict severity of restrictive pulmonary function from chest radiographs of patients with interstitial lung disease, abstract at ARRS 2019
2. J. Chan et al., Detection of obstructive and restrictive lung disease on chest radiography using machine learning and integrated pulmonary function data, RSNA 2018