Fibro-CoSANet: Pulmonary Fibrosis Prognosis Prediction using a Convolutional Self Attention Network
This work addresses prognostic accuracy for idiopathic pulmonary fibrosis patients, representing an incremental improvement in a domain-specific medical imaging task.
The paper tackled predicting forced vital capacity (FVC) decline in idiopathic pulmonary fibrosis using CT images and demographic data, achieving a state-of-the-art modified Laplace Log-Likelihood score of -6.68.
Idiopathic pulmonary fibrosis (IPF) is a restrictive interstitial lung disease that causes lung function decline by lung tissue scarring. Although lung function decline is assessed by the forced vital capacity (FVC), determining the accurate progression of IPF remains a challenge. To address this challenge, we proposed Fibro-CoSANet, a novel end-to-end multi-modal learning-based approach, to predict the FVC decline. Fibro-CoSANet utilized CT images and demographic information in convolutional neural network frameworks with a stacked attention layer. Extensive experiments on the OSIC Pulmonary Fibrosis Progression Dataset demonstrated the superiority of our proposed Fibro-CoSANet by achieving the new state-of-the-art modified Laplace Log-Likelihood score of -6.68. This network may benefit research areas concerned with designing networks to improve the prognostic accuracy of IPF. The source-code for Fibro-CoSANet is available at: \url{https://github.com/zabir-nabil/Fibro-CoSANet}.