Idiopathic pulmonary fibrosis (IPF) is a devastating disease of unknown etiology occurring in older adults. IPF is ultimately fatal with a median survival of 2 to 5 years, and exhibits a highly heterogeneous natural history. Broad categories of disease progression have been defined, but are not predictable at the time of diagnosis. Diagnosis and stratification of disease phenotypes are important in order to decipher the effects of novel therapies among individuals with biologically dissimilar natural histories and to better tailor therapy to individuals. Few computerized diagnostic tools have been developed for IPF that correlate with visual and surgical lung biopsy; most use clinical and functional variables independent of imaging findings. Prognostic determinants based on imaging features rely largely on subjective visual assessment of disease. In contrast, no good predictive models with localized region exist that anticipate the natural history of disease in advance of significant functional decline. Given the indispensable role of high resolution computed tomography (HRCT) in the diagnosis and surveillance of IPF, we propose to mine the rich information in HRCT data sets to develop robust, quantitative features that can anticipate disease progression in advance of debilitating respiratory compromise. We propose to use as a derivative dataset the anonymized clinical data and source images on 234 patients with IPF and 266 patients with IPF suspected, but not IPF based on HRCT and the surgical biopsy who have participated in multicenter trials, and whose data are archived at the UCLA Computer Vision and Imaging Biomarkers Laboratory. Using an image processing pipeline developed in our laboratory for high through-put quantitative image analysis, we will train a classifier with features of anatomic distribution and reproducible imaging features expressed with a quantitative lung fibrosis (QLF) score, testing on separate data from in an independent institutional registry of clinical and image data on patients with IPF seen in the UCLA Interstitial Lung Disease Program. Furthermore, the second aim is to develop a rate of progression at local region and to aggregate predictive models using Cox proportional regression models, which will be derived using only clinical covariates and combined clinical and imaging covariates, correlating these models with progression free survival. Our objectives are centered on the goals of using preexisting datasets to develop clinically meaningful models that diagnose and anticipate disease course in patients with IPF and subdividing patients into more homogeneous groups prior to the development of significant respiratory impairment. We anticipate that models can be used clinically at the individual patient level to enable more informed and timely management decisions to define more homogeneous cohorts for purposes of testing new targeted therapies and to better elucidate the effects of therapies in patients with biologically heterogeneous disease progression.
to Public Health: Idiopathic pulmonary fibrosis (IPF) is a devastating disease of older adults that now has a few treatment options: The natural history of IPF and its rate of progression is highly variables, which hampers timely decisions about referral for lung transplantation or treatments using new drug therapies. This research takes advantage of clinical and imaging datasets previously collected for research or clinical purposes, and will define image features using computer analysis of computed tomography (CT) images to diagnose and predict disease course robustly in advance of respiratory deterioration. The success of this research will enable us to distinguish between patients with IPF and non-IPF with reducing chance of lung biopsy and predict slowly versus rapidly progressive disease, leading to more time to treat patients and timely management decisions, and may help us to understand which patients might benefit from novel promising therapies or treatments and which may not.
