Fibro-CoSANet: Pulmonary Fibrosis Prognosis Prediction using a Convolutional Self Attention Network

TL;DR

Fibro-CoSANet is a novel multi-modal deep learning model that predicts pulmonary fibrosis progression by analyzing CT images and demographic data, achieving state-of-the-art accuracy.

Contribution

Introduces Fibro-CoSANet, a new end-to-end convolutional self-attention network that improves prognosis prediction of IPF using multi-modal data.

Findings

Achieved a new state-of-the-art score of -6.68 on the OSIC dataset.

Demonstrated superior performance over existing methods.

Validated effectiveness with extensive experiments.

Abstract

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}.