Predicting radiation pneumonitis in lung cancer patients using robust 4DCT-ventilation and perfusion imaging.
Authors
Affiliations (7)
Affiliations (7)
- Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, PA, United States. Electronic address: [email protected].
- Department of Biomedical Engineering, University of Texas at Austin, Austin, TX, United States. Electronic address: [email protected].
- Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, PA, United States. Electronic address: [email protected].
- MIM Software Inc., Beachwood, OH, United States. Electronic address: [email protected].
- Department of Radiation Oncology, Emory University, Atlanta, GA, United States. Electronic address: [email protected].
- Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, PA, United States. Electronic address: [email protected].
- Department of Radiation Oncology, Thomas Jefferson University, Philadelphia, PA, United States. Electronic address: [email protected].
Abstract
Methods have been developed that apply image processing to 4-Dimension computed tomography (4DCT) to generate lung ventilation (4DCT-ventilation). Traditional methods for 4DCT-ventilation rely on density-change methods and lack reproducibility and do not provide 4DCT-perfusion data. Novel 4DCT-ventilation/perfusion methods have been developed that are robust and provide 4DCT-perfusion information. The purpose of this study was to use prospective clinical trial data to evaluate the ability of novel 4DCT-based lung function imaging methods to predict pneumonitis. Sixty-three advanced-stage lung cancer patients enrolled in a multi-institutional, phase 2 clinical trial on 4DCT-based functional avoidance radiation therapy were used. 4DCTs were used to generate four lung function images: 1) 4DCT-ventilation using the traditional HU approach ('4DCT-vent-HU'), and 3 methods using the 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 ('4DCT-vent-IJF') and 4) 4DCT-perfusion. Dose-function metrics including mean functional lung dose (fMLD), and percentage of functional lung receiving ≥ 5 Gy (fV5), and ≥ 20 Gy (fV20) were calculated using various structure-based thresholds. The ability of dose-function metrics to predict for ≥ grade 2 RP was assessed using logistic regression and machine learning. Model performance was evaluated using the area under the curve (AUC) and validated through 10-fold cross-validation. 10/63 (15.9 %) patients developed grade ≥2 RP. Logistic regression yielded mean AUCs of 0.70 ± 0.02 (p = 0.04), 0.64 ± 0.04 (p = 0.13), 0.60 ± 0.03 (p = 0.27), and 0.63 ± 0.03 (p = 0.20) for 4DCT-vent-MCVC, 4DCT-perfusion, 4DCT-vent-IJF, and 4DCT-vent-HU, respectively, compared to 0.65 ± 0.10 (p > 0.05) for standard lung metrics. Machine learning modeling resulted in AUCs 0.83 ± 0.04, 0.82 ± 0.05, 0.76 ± 0.05, 0.74 ± 0.06, and 0.75 ± 0.02 for 4DCT-vent-MCVC, 4DCT-perfusion, 4DCT-vent-IJF, and 4DCT-vent-HU, and standard lung metrics respectively, with an accuracy of 75-85 %. This is the first study to comprehensively evaluate 4DCT-perfusion and robust 4DCT-ventilation in predicting clinical outcomes. The data showed that on the presented 63-patient study and using classis logistic regression and ML methods, 4DCT-vent-MCVC was the best predictors of RP.