COPD-FlowNet: Elevating Non-invasive COPD Diagnosis with CFD Simulations
This addresses COPD diagnosis for patients, but appears incremental as it combines existing GAN and CNN methods for a specific medical application.
The paper tackles non-invasive COPD diagnosis by developing COPDFlowNet, a deep-learning framework that uses a custom GAN to generate synthetic CFD velocity flow field images for data augmentation and a custom CNN to predict obstruction sites, but no concrete results or numbers are provided.
Chronic Obstructive Pulmonary Disorder (COPD) is a prevalent respiratory disease that significantly impacts the quality of life of affected individuals. This paper presents COPDFlowNet, a novel deep-learning framework that leverages a custom Generative Adversarial Network (GAN) to generate synthetic Computational Fluid Dynamics (CFD) velocity flow field images specific to the trachea of COPD patients. These synthetic images serve as a valuable resource for data augmentation and model training. Additionally, COPDFlowNet incorporates a custom Convolutional Neural Network (CNN) architecture to predict the location of the obstruction site.