Purpose: Novel methods have been developed for functional avoidance that proposes to use 4DCT to derive lung ventilation and perfusion images. Previous methods for quantifying lung perfusion on non-contrast 4DCT rely either on HU-based physical models or black-box deep learning models. While deep learning typically achieves higher accuracies in image processing tasks, physical models provide a rationale for model predictions. The purpose of this study is to introduce a biophysics-informed machine learning method for estimating pulmonary perfusion from noncontrast 4DCT. Our approach is designed to combine the predictive power of neural networks with the interpretability of physical modeling, with the goal of providing high-fidelity information for radiotherapy functional avoidance planning. Methods: Simulation 4DCT scans and SPECT-Perfusion scans for 42 non-small cell lung cancer patients were used to train and validate a 3-layer, fully connected, artificial neural network (ANN). Similar to existing physics-based models for CT-perfusion, the ANN takes as inputs the spatially corresponding inhale/exhale lung densities and Jacobian measured volume changes for the five lung lobes. The output layer predicts the percent of total lung perfusion within each lobe. SPECT-Perfusion images were used for ground truth. The ANN was trained using the stochastic gradient descent optimizer with grid search. Leave-one-out cross-validation was applied to estimate prediction quality. Results: The average mean square errors resulting from the leave-one-out process was 5.71±2.77%. The median(interquartile range) of the Spearman correlations between ground truth and predictions was 0.7(0.5). Conclusion: Our proposed physics-informed ANN generates spatial correlations with SPECT-Perfusion that provide improved correlation compared to existing methods. Moreover, the approach is based on lung density and volume change measurements which are well-known physical quantities that have been shown to correlate with disease and functional defects. Therefore, the developed ANN represents a novel and interpretable machine learning methodology for quantifying perfusion from non-contrast CT.
Liu Y, Nowacki A, Castillo R, Vinogradskiy Y, Nair G, Stevens C, et al. Physics-informed machine learning for estimating pulmonary perfusion from non-contract 4DCT. Med Phys. 2022 June;49(6):E125