GAN-based survival prediction model from CT images of patients with idiopathic pulmonary fibrosis

摘要

We developed a novel survival prediction model for images, called pix2surv, based on a conditional generative adversarialnetwork (cGAN), and evaluated its performance based on chest CT images of patients with idiopathic pulmonary fibrosis(IPF). The architecture of the pix2surv model has a time-generator network that consists of an encoding convolutionalnetwork, a fully connected prediction network, and a discriminator network. The fully connected prediction network istrained to generate survival-time images from the chest CT images of each patient. The discriminator network is a patchbasedconvolutional network that is trained to differentiate the “fake pair” of a chest CT image and a generated survivaltimeimage from the “true pair” of an input CT image and the observed survival-time image of a patient. For evaluation,we retrospectively collected 75 IPF patients with high-resolution chest CT and pulmonary function tests. The survivalpredictions of the pix2surv model on these patients were compared with those of an established clinical prognosticbiomarker known as the gender, age, and physiology (GAP) index by use of a two-sided t-test with bootstrapping.Concordance index (C-index) and relative absolute error (RAE) were used as measures of the prediction performance.Preliminary results showed that the survival prediction by the pix2surv model yielded more than 15% higher C-index valueand more than 10% lower RAE values than those of the GAP index. The improvement in survival prediction by thepix2surv model was statistically significant (P < 0.0001). Also, the separation between the survival curves for the low- andhigh-risk groups was larger with pix2surv than that of the GAP index. These results show that the pix2surv modeloutperforms the GAP index in the prediction of the survival time and risk stratification of patients with IPF, indicating thatthe pix2surv model can be an effective predictor of the overall survival of patients with IPF.