Comprehensive clinical evaluation of novel 4DCT‐based lung function imaging methods

Abstract Purpose Methods have been developed that apply image processing to 4DCTs to generate 4DCT‐ventilation/perfusion lung imaging. Traditional methods for 4DCT‐ventilation rely on Hounsfield‐Unit (HU) density‐change methods and suffer from poor numerical robustness while not providing 4DCT‐perfusion data. The purpose of this work was to evaluate the clinical differences between classic HU‐based 4DCT‐ventilation approaches and novel 4DCT‐ventilation/perfusion approaches. Methods Data from 63 lung cancer patients enrolled in a functional avoidance clinical trial were analyzed. 4DCT‐data were used to generate four lung‐function images: (1) classical HU‐based 4DCT‐ventilation (“4DCT‐vent‐HU”), and three novel, statistically robust methods: (2) 4DCT‐ventilation based on the Mass Conserving Volume Change (“4DCT‐vent‐MCVC”), (3) 4DCT‐ventilation using the Integrated Jacobian Formulation, and (4) 4DCT‐perfusion. A radiologist reviewed all images for ventilation/perfusion defects (scored as yes/no) and the scores for the novel approaches were compared to those of 4DCT‐vent‐HU using receiver operating characteristic (ROC) analysis. Functional contours were generated using thresholding methods, and the contours from the three novel 4DCT‐ventilation methods were compared against that from 4DCT‐vent‐HU (Dice similarity coefficients [DSC]). Functional mean lung dose (fMLD) and dose‐function metrics were compared against dose‐function metrics using 4DCT‐vent‐HU. Results ROC analysis revealed accuracy in the range of 0.55 to 0.73 comparing radiologist interpretations of 4DCT‐vent‐HU against the three novel approaches. Average DSC values were 0.41 ± 0.19, 0.44 ± 0.16, and 0.42 ± 0.17 comparing 4DCT‐vent‐HU to 4DCT‐vent‐IJF, 4DCT‐vent‐MCVC, and 4DCT‐perf, respectively. All novel imaging methods showed significant differences ( p < 0.01) in dose‐function metrics compared to those of 4DCT‐vent‐HU. 4DCT‐vent‐MCVC and 4DCT‐Perf depicted the smallest and largest differences from 4DCT‐vent‐HU in fMLD (3.51 ± 3.20 Gy and 5.90 ± 5.29 Gy, respectively). Conclusion This is the first work to comprehensively compare novel 4DCT‐ventilation/perfusion methods against classical formulations. Our data show that significant differences between the 4DCT‐based functional imaging methods exist, suggesting that studies are needed to evaluate which methods provide the most robust clinical results.