Pulmonary Function Prediction Method Based on Convolutional Surface Modeling and Computational Fluid Dynamics Simulation.

The pulmonary function test holds significant clinical value in assessing the severity, prognosis, and treatment efficacy of respiratory diseases. However, the test is limited by patient compliance, thereby limiting its practical application. Moreover, it only reflects the current state of the patient and cannot directly indicate future health trends or prognosis. Computational fluid dynamics (CFD), combined with airway models built from medical image data, can assist in analyzing a patient's ventilation function, thus addressing the aforementioned issues. However, current airway models have shortcomings in accurately representing the structural features of a patient's airway. Additionally, these models exhibit geometric defects such as low smoothness, topological errors, and noise, which further reduce their usability. This study generates airway skeletons based on CT data and, in combination with convolutional surface technology, proposes an individualized airway modeling method to solve these deficiencies. This study also provides a method for predicting a patient's lung function based on the constructed airway model and using CFD simulation technology. This study also explores the application of this method in preoperative prediction of the required extent of airway expansion for patients with large airway stenosis. Based on airway skeleton data extracted from patient CT images, a personalized airway model is constructed using convolutional surface technology. The airway model is simulated according to the patient's clinical statistical values of pulmonary function to obtain airway simulation data. Finally, a regression equation is constructed between the patient's measured pulmonary function values and the airway simulation data to predict the patient's pulmonary function values based on the airway simulation data. To preliminarily demonstrate the above method, this study used the prediction of FEV1 in patients with large airway stenosis as an example for a proof-of-concept study. A linear regression model was constructed between the outlet flow rate from the simulation of the stenosed airway and the patient's measured FEV1 values. The linear regression model achieved a prediction result of RMSE = 0.0246 and R = 0.9822 for the test set. Additionally, preoperative predictions were made for the degree of airway dilation needed for patients with large airway stenosis. According to the linear regression model, the proportion of airway radius expansion required at the stenotic position to achieve normal FEV1 was calculated as 72.86%. This study provides a method for predicting patient pulmonary function based on CFD simulation technology and convolutional surface technology. This approach addresses, to some extent, the limitations in pulmonary function testing and accuracy caused by patient compliance. Meanwhile, this study provides a method for preoperative evaluation of airway dilation therapy.