Treatment planning based on lung functional avoidance is not ready for clinical deployment

Integrating local and distant radiation-induced lung injury: Development and validation of a predictive model for ventilation loss

BACKGROUND

Investigations on radiation-induced lung injury (RILI) have predominantly focused on local effects, primarily those associated with radiation damage to lung parenchyma. However, recent studies from our group and others have revealed that radiation-induced damage to branching serial structures such as airways and vessels may also have a substantial impact on post-radiotherapy (RT) lung function. Furthermore, recent results from multiple functional lung avoidance RT trials, although promising, have demonstrated only modest toxicity reduction, likely because they were primarily focused on dose avoidance to lung parenchyma. These observations emphasize the critical need for predictive dose-response models that effectively incorporate both local and distant RILI effects.

PURPOSE

We develop and validate a predictive model for ventilation loss after lung RT. This model, referred to as P+A, integrates local (parenchyma [P]) and distant (central and peripheral airways [A]) radiation-induced damage, modeling partial (narrowing) and complete (collapse) obstruction of airways.

METHODS

In an IRB-approved prospective study, pre-RT breath-hold CTs (BHCTs) and pre- and one-year post-RT 4DCTs were acquired from lung cancer patients treated with definitive RT. Up to 13 generations of airways were automatically segmented on the BHCTs using a research virtual bronchoscopy software. Ventilation maps derived from the 4DCT scans were utilized to quantify pre- and post-RT ventilation, serving, respectively, as input data and reference standard (RS) in model validation. To predict ventilation loss solely due to parenchymal damage (referred to as P model), we used a normal tissue complication probability (NTCP) model. Our model used this NTCP-based estimate and predicted additional loss due radiation-induced partial or complete occlusion of individual airways, applying fluid dynamics principles and a refined version of our previously developed airway radiosensitivity model. Predictions of post-RT ventilation were estimated in the sublobar volumes (SLVs) connected to the terminal airways. To validate the model, we conducted a k-fold cross-validation. Model parameters were optimized as the values that provided the lowest root mean square error (RMSE) between predicted post-RT ventilation and the RS for all SLVs in the training data. The performance of the P+A and the P models was evaluated by comparing their respective post-RT ventilation values with the RS predictions. Additional evaluation using various receiver operating characteristic (ROC) metrics was also performed.

RESULTS

We extracted a dataset of 560 SLVs from four enrolled patients. Our results demonstrated that the P+A model consistently outperformed the P model, exhibiting RMSEs that were nearly half as low across all patients (13 ± 3 percentile for the P+A model vs. 24 ± 3 percentile for the P model on average). Notably, the P+A model aligned closely with the RS in ventilation loss distributions per lobe, particularly in regions exposed to doses ≥13.5 Gy. The ROC analysis further supported the superior performance of the P+A model compared to the P model in sensitivity (0.98 vs. 0.07), accuracy (0.87 vs. 0.25), and balanced predictions.

CONCLUSIONS

These early findings indicate that airway damage is a crucial factor in RILI that should be included in dose-response modeling to enhance predictions of post-RT lung function.

Functional Lung Avoidance Planning Using Multicriteria Optimization

PURPOSE

Functional lung avoidance (FLA) radiation therapy is an evolving field. The aim of FLA planning is to reduce dose to areas of functioning lung, with comparable target coverage and dose to organs at risk. Multicriteria optimization (MCO) is a planning tool that may assist with FLA planning. This study assessed the feasibility of using MCO to adapt radiation therapy plans to avoid functional regions of lung that were identified using a 68Ga-4D-V/Q positron emission tomography/computed tomography.

METHODS AND MATERIALS

A prospective clinical trial U1111-1138-4421 was performed in which patients had a 68Ga-4D-V/Q positron emission tomography/computed tomography before radiation treatment. Of the 72 patients enrolled in this trial, 38 patients had stage III non-small cell lung cancer and were eligible for selection into this planning study. Functional lung target volumes HF lung (highly functioning lung) and F lung (functional lung) were defined using the ventilated and perfused lung. Using knowledge-based planning, a baseline anatomic plan was created, and then a functional adapted plan was generated using multicriteria optimization. The primary aim was to spare dose to HF lung. Using the MCO tools, a clinician selected the final FLA plan. Dose to functional lung, target volumes, organs at risk and measures of plan quality were compared using standard statistical methods.

RESULTS

The HF lung volume was successfully spared in all patients. The F lung volume was successfully spared in 36 of the 38 patients. There were no clinically significant differences in dose to anatomically defined organs at risk. There were differences in the planning target volume near maximum and minimum doses. Across the entire population, there was a statistically significant reduction in the functional mean lung dose but not in the functional volume receiving 20 Gy. All trade-off decisions were made by the clinician.

CONCLUSIONS

Using MCO for FLA was achievable but did result in changes to planning target volume coverage. A distinct advantage in using MCO was that all decisions regarding the cost and benefits of FLA could be made in real time.

Robust quantification of CT-ventilation biomarker techniques and repeatability in a porcine model

BACKGROUND

Biomarkers estimating local lung ventilation have been derived from computed tomography (CT) imaging using various image acquisition and post-processing techniques. CT-ventilation biomarkers have potential clinical use in functional avoidance radiation therapy (RT), in which RT treatment plans are optimized to reduce dose delivered to highly ventilated lung. Widespread clinical implementation of CT-ventilation biomarkers necessitates understanding of biomarker repeatability. Performing imaging within a highly controlled experimental design enables quantification of error associated with remaining variables.

PURPOSE

To characterize CT-ventilation biomarker repeatability and dependence on image acquisition and post-processing methodology in anesthetized and mechanically ventilated pigs.

METHODS

Five mechanically ventilated Wisconsin Miniature Swine (WMS) received multiple consecutive four-dimensional CT (4DCT) and maximum inhale and exhale breath-hold CT (BH-CT) scans on five dates to generate CT-ventilation biomarkers. Breathing maneuvers were controlled with an average tidal volume difference <200 cc. As surrogates for ventilation, multiple local expansion ratios (LERs) were calculated from the acquired CT scans using Jacobian-based post-processing techniques.L E R 2 $LER_2$ measured local expansion between an image pair using either inhale and exhale BH-CT images or two 4DCT breathing phase images.L E R N $LER_N$ measured the maximum local expansion across the 4DCT breathing phase images. Breathing maneuver consistency, intra- and interday biomarker repeatability, image acquisition and post-processing technique dependence were quantitatively analyzed.

RESULTS

Biomarkers showed strong agreement with voxel-wise Spearman correlationρ > 0.9 $\rho > 0.9$ for intraday repeatability andρ > 0.8 $\rho > 0.8$ for all other comparisons, including between image acquisition techniques. Intra- and interday repeatability were significantly different (p < 0.01). LER2 and LERN post-processing did not significantly affect intraday repeatability.

CONCLUSIONS

4DCT and BH-CT ventilation biomarkers derived from consecutive scans show strong agreement in controlled experiments with nonhuman subjects.

A deep learning method for translating 3D-CT to SPECT ventilation imaging: First comparison with 81m Kr-gas SPECT ventilation imaging

PURPOSE

This study aimed to evaluate the accuracy of deep learning (DL)-based computed tomography (CT) ventilation imaging (CTVI).

METHODS

A total of 71 cases who underwent single-photon emission CT ^81m Kr-gas ventilation (SPECT V) and CT imaging were included. Sixty cases were assigned to the training and validation sets and the remaining 11 cases were assigned to the test set. To directly transform 3DCT (free-breathing CT) images to SPECT V images, a DL-based model was implemented based on the U-Net architecture. The input and output data were 3DCT- and SPECT V-masked, respectively, except for whole-lung volumes. These data were rearranged in voxel size, registered rigidly, cropped, and normalized in pre-processing. In addition to a standard estimation method (i.e., without dropout during the estimation process), a Monte-Carlo Dropout (MCD) method (i.e., with dropout during the estimation process) was used to calculate prediction uncertainty. To evaluate the two models' (CTVI_{MCD U-Net} , CTVI_U-Net ) performance, we used five-fold cross-validation for the training and validation sets. To test the final model performances for both approaches, we applied the test set to each trained model and averaged the test prediction results from the five trained models to acquire the mean test result (bagging) for each approach. For the MCD method, the models were predicted repeatedly (sample size = 200), and the average and standard deviation maps were calculated in each voxel from the predicted results: the average maps were defined as test prediction results in each fold. As an evaluation index, the voxel-wise Spearman rank correlation coefficient (Spearman r_s ) and dice similarity coefficient (DSC) were calculated. The DSC was calculated for three functional regions (high, moderate, and low) separated by an almost equal volume. The coefficient of variation was defined as prediction uncertainty, and these average values were calculated within three functional regions. The Wilcoxon signed-rank test was used to test for a significant difference between the two DL-based approaches RESULTS: The average indexes with one standard deviation (1SD) between CTVI_{MCD U-Net} and SPECT V were 0.76 ± 0.06, 0.69 ± 0.07, 0.51 ± 0.06, and 0.75 ± 0.04 for Spearman r_s , DSC_high , DSC_moderate , and DSC_low , respectively. The average indexes with 1SD between CTVI_U-Net and SPECT V were 0.72 ± 0.05, 0.66 ± 0.04, 0.48 ± 0.04, and 0.74 ± 0.06 for Spearman r_s , DSC_high , DSC_moderate , and DSC_low , respectively. These indexes between CTVI_{MCD U-Net} and CTVI_U-Net showed no significance difference (Spearman r_s , p = 0.175; DSC_high , p = 0.123; DSC_moderate , p = 0.278; DSC_low , p = 0.520). The average coefficient of variations with 1SD were 0.27 ± 0.00, 0.27 ± 0.01, and 0.36 ± 0.03 for the high-, moderate-, and low-functional regions, respectively, and the low-functional region showed a tendency to exhibit larger uncertainties than the others.

CONCLUSION

We evaluated DL-based framework for estimating lung-functional ventilation images only from CT images. The results indicated that the DL-based approach could potentially be used for lung-ventilation estimation. This article is protected by copyright. All rights reserved.

Functionally weighted airway sparing (FWAS): a functional avoidance method for preserving post-treatment ventilation in lung radiotherapy

Recent changes to the guidelines for screening and early diagnosis of lung cancer have increased the interest in preserving post-radiotherapy lung function. Current investigational approaches are based on spatially mapping functional regions and generating regional avoidance plans that preferentially spare highly ventilated/perfused lung. A potentially critical, yet overlooked, aspect of functional avoidance is radiation injury to peripheral airways, which serve as gas conduits to and from functional lung regions. Dose redistribution based solely on regional function may cause irreparable damage to the 'supply chain'. To address this deficiency, we propose the functionally weighted airway sparing (FWAS) method. FWAS (i) maps the bronchial pathways to each functional sub-lobar lung volume; (ii) assigns a weighting factor to each airway based on the relative contribution of the sub-volume to overall lung function; and (iii) creates a treatment plan that aims to preserve these functional pathways. To evaluate it, we used four cases from a retrospective cohort of SAbR patients treated for lung cancer. Each patient's airways were auto-segmented from a diagnostic-quality breath-hold CT using a research virtual bronchoscopy software. A ventilation map was generated from the planning 4DCT to map regional lung function. For each terminal airway, as resolved by the segmentation software, the total ventilation within the sub-lobar volume supported by that airway was estimated and used as a function-based weighting factor. Upstream airways were weighted based on the cumulative volumetric ventilation supported by corresponding downstream airways. Using a previously developed model for airway radiosensitivity, dose constraints were determined for each airway corresponding to a <5% probability of airway collapse. Airway dose constraints, ventilation scores, and clinical dose constraints were input to a swarm optimization-based inverse planning engine to create a 3D conformal SAbR plan (CRT). The FWAS plans were compared to the patients' prescribed CRT clinical plans and the inverse-optimized clinical plans. Depending on the size and location of the tumour, the FWAS plan showed superior preservation of ventilation due to airflow preservation through open pathways (i.e. cumulative ventilation score from the sub-lobar volumes of open pathways). Improvements ranged between 3% and 23%, when comparing to the prescribed clinical plans, and between 3% and 35%, when comparing to the inverse-optimized clinical plans. The three plans satisfied clinical requirements for PTV coverage and OAR dose constraints. These initial results suggest that by sparing pathways to high-functioning lung subregions it is possible to reduce post-SAbR loss of respiratory function.

An initial investigation of hyperpolarized gas tagging magnetic resonance imaging in evaluating deformable image registration-based lung ventilation

BACKGROUND

Deformable image registration (DIR)-based lung ventilation mapping is attractive due to its simplicity, and also challenging due to its susceptibility to errors and uncertainties. In this study, we explored the use of 3D Hyperpolarized (HP) gas tagging MRI to evaluate DIR-based lung ventilation.

METHOD AND MATERIAL

Three healthy volunteers included in this study underwent both 3D HP gas tagging MRI (t-MRI) and 3D proton MRI (p-MRI) using balanced steady-state free precession pulse sequence at end of inhalation and end of exhalation. We first obtained the reference displacement vector fields (DVFs) from the t-MRIs by tracking the motion of each tagging grid between the exhalation and the inhalation phases. Then, we determined DIR-based DVFs from the p-MRIs by registering the images at the two phases with two commercial DIR algorithms. Lung ventilations were calculated from both the reference DVFs and the DIR-based DVFs using the Jacobian method and then compared using cross correlation and mutual information.

RESULTS

The DIR-based lung ventilations calculated using p-MRI varied considerably from the reference lung ventilations based on t-MRI among all three subjects. The lung ventilations generated using Velocity AI were preferable for the better spatial homogeneity and accuracy compared to the ones using MIM, with higher average cross correlation (0.328 vs 0.262) and larger average mutual information (0.528 vs 0.323).

CONCLUSION

We demonstrated that different DIR algorithms resulted in different lung ventilation maps due to underlining differences in the DVFs. HP gas tagging MRI provides a unique platform for evaluating DIR-based lung ventilation.