A deep learning model for translating CT to ventilation imaging: analysis of accuracy and impact on functional avoidance radiotherapy planning.

PURPOSE

Radiotherapy planning incorporating functional lung images has the potential to reduce pulmonary toxicity. Free-breathing 4DCT-derived ventilation image (CTVI) may help quantify lung function. This study introduces a novel deep-learning model directly translating planning CT images into CTVI. We investigated the accuracy of generated images and the impact on functional avoidance planning.

MATERIALS AND METHODS

Paired planning CT and 4DCT scans from 48 patients with NSCLC were randomized to training (n = 41) and testing (n = 7) data sets. The ventilation maps were generated from 4DCT using a Jacobian-based algorithm to provide ground truth labels (CTVI). A 3D U-Net-based model was trained to map CT to synthetic CTVI (CTVI) and validated using fivefold cross-validation. The highest-performing model was applied to the testing set. Spearman's correlation (r) and Dice similarity coefficient (DSC) determined voxel-wise and functional-wise concordance between CTVI and CTVI. Three plans were designed per patient in the testing set: one clinical plan without CTVI and two functional avoidance plans combined with CTVI or CTVI, aimed at sparing high-functional lungs defined as the top 50% of the percentile ventilation ranges. Dose-volume (DVH) parameters regarding the planning target volume (PTV) and organs at risk (OARs) were recorded. Radiation pneumonitis (RP) risk was estimated using a dose-function (DFH)-based normal tissue complication probability (NTCP) model.

RESULTS

CTVI showed a mean rs value of 0.65 ± 0.04 compared to CTVI. Mean DSC values over the top 50% and 60% of ventilation ranges were 0.41 ± 0.07 and 0.52 ± 0.10, respectively. In the test set (n = 7), all patients' RP-risk benefited from CTVI-guided plans (Risk: 29.24% vs. 49.12%, P = 0.016), and six patients benefited from CTVI-guided plans (Risk: 31.13% vs. 49.12%, P = 0.022). There were no significant differences in DVH and DFH metrics between CTVI and CTVI-guided plan (P > 0.05).

CONCLUSION

Using deep-learning techniques, CTVI generated from planning CT exhibited a moderate-to-high correlation with CTVI. The CTVI-guided plans were comparable to the CTVI-guided plans, effectively reducing pulmonary toxicity in patients while maintaining acceptable plan quality. Further prospective trials are needed to validate these findings.