Prediction of progression in idiopathic pulmonary fibrosis using CT scans at baseline: A quantum particle swarm optimization - Random forest approach
作者：
Highlights：
• This wrapper algorithm can predict the disease progression of Idiopathic Pulmonary Fibrosis using Computed Tomography (CT).
• The novel wrapper algorithm hybridized Quantum Particle Swarm Optimization and Random Forest (QPSO-RF).
• The algorithm achieves high accuracy with a small number of texture features, outperforming other adopted algorithms.
• The data acquisition enabled us to build a predictive model using single time point CT scans.
• This work is the first to show that a single point CT scan can predict progressive regions at 6 months to 1 year follow-up.
摘要
•This wrapper algorithm can predict the disease progression of Idiopathic Pulmonary Fibrosis using Computed Tomography (CT).•The novel wrapper algorithm hybridized Quantum Particle Swarm Optimization and Random Forest (QPSO-RF).•The algorithm achieves high accuracy with a small number of texture features, outperforming other adopted algorithms.•The data acquisition enabled us to build a predictive model using single time point CT scans.•This work is the first to show that a single point CT scan can predict progressive regions at 6 months to 1 year follow-up.
论文关键词：Biomedical imaging,Texture features,Wrapper methods
论文评审过程：Received 28 November 2018, Revised 10 August 2019, Accepted 19 August 2019, Available online 28 August 2019, Version of Record 24 September 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2019.101709
