ABSTRACT
BACKGROUND: Magnetic resonance-guided radiotherapy with an MR-guided LINAC represents potential clinical benefits in abdominal treatments due to the superior soft-tissue contrast compared to kV-based images in conventional treatment units. However, due to the high cost associated with this technology, only a few centers have access to it. As an alternative, synthetic 4D MRI generation based on artificial intelligence methods could be implemented. Nevertheless, appropriate MRI texture generation from CT images might be challenging and prone to hallucinations, compromising motion accuracy. PURPOSE: To evaluate the feasibility of on-board synthetic motion-resolved 4D MRI generation from prior 4D MRI, on-board 4D cone beam CT (CBCT) images, motion modeling information, and deep learning models using the digital anthropomorphic phantom XCAT. METHODS: The synthetic 4D MRI corresponds to phases from on-board 4D CBCT. Each synthetic MRI volume in the 4D MRI was generated by warping a reference 3D MRI (MRIref, end of expiration phase from a prior 4D MRI) with a deformation field map (DFM) determined by (I) the eigenvectors from the principal component analysis (PCA) motion-modeling of the prior 4D MRI, and (II) the corresponding eigenvalues predicted by a convolutional neural network (CNN) model using the on-board 4D CBCT images as input. The CNN was trained with 1000 deformations of one reference CT (CTref, same conditions as MRIref) generated by applying 1000 DFMs computed by randomly sampling the original eigenvalues from the prior 4D MRI PCA model. The evaluation metrics for the CNN model were root-mean-square error (RMSE) and mean absolute error (MAE). Finally, different on-board 4D-MRI generation scenarios were assessed by changing the respiratory period, the amplitude of the diaphragm, and the chest wall motion of the 4D CBCT using normalized root-mean-square error (nRMSE) and structural similarity index measure (SSIM) for image-based evaluation, and volume dice coefficient (VDC), volume percent difference (VPD), and center-of-mass shift (COMS) for contour-based evaluation of liver and target volumes. RESULTS: The RMSE and MAE values of the CNN model reported 0.012 ± 0.001 and 0.010 ± 0.001, respectively for the first eigenvalue predictions. SSIM and nRMSE were 0.96 ± 0.06 and 0.22 ± 0.08, respectively. VDC, VPD, and COMS were 0.92 ± 0.06, 3.08 ± 3.73 %, and 2.3 ± 2.1 mm, respectively, for the target volume. The more challenging synthetic 4D-MRI generation scenario was for one 4D-CBCT with increased chest wall motion amplitude, reporting SSIM and nRMSE of 0.82 and 0.51, respectively. CONCLUSIONS: On-board synthetic 4D-MRI generation based on predicting actual treatment deformation from on-board 4D-CBCT represents a method that can potentially improve the treatment-setup localization in abdominal radiotherapy treatments with a conventional kV-based LINAC.
ABSTRACT
BACKGROUND: Electromagnetic transponders bronchoscopically implanted near the tumor can be used to monitor deep inspiration breath hold (DIBH) for thoracic radiation therapy (RT). The feasibility and safety of this approach require further study. METHODS: We enrolled patients with primary lung cancer or lung metastases. Three transponders were implanted near the tumor, followed by simulation with DIBH, free breathing, and 4D-CT as backup. The initial gating window for treatment was ±5 mm; in a second cohort, the window was incrementally reduced to determine the smallest feasible gating window. The primary endpoint was feasibility, defined as completion of RT using transponder-guided DIBH. Patients were followed for assessment of transponder- and RT-related toxicity. RESULTS: We enrolled 48 patients (35 with primary lung cancer and 13 with lung metastases). The median distance of transponders to tumor was 1.6 cm (IQR 0.6-2.8 cm). RT delivery ranged from 3 to 35 fractions. Transponder-guided DIBH was feasible in all but two patients (96% feasible), where it failed because the distance between the transponders and the antenna was >19 cm. Among the remaining 46 patients, 6 were treated prone to keep the transponders within 19 cm of the antenna, and 40 were treated supine. The smallest feasible gating window was identified as ±3 mm. Thirty-nine (85%) patients completed one year of follow-up. Toxicities at least possibly related to transponders or the implantation procedure were grade 2 in six patients (six incidences, cough and hemoptysis), grade 3 in three patients (five incidences, cough, dyspnea, pneumonia, and supraventricular tachycardia), and grade 4 pneumonia in one patient (occurring a few days after implantation but recovered fully and completed RT). Toxicities at least possibly related to RT were grade 2 in 18 patients (41 incidences, most commonly cough, fatigue, and pneumonitis) and grade 3 in four patients (seven incidences, most commonly pneumonia), and no patients had grade 4 or higher toxicity. CONCLUSIONS: Bronchoscopically implanted electromagnetic transponder-guided DIBH lung RT is feasible and safe, allowing for precise tumor targeting and reduced normal tissue exposure. Transponder-antenna distance was the most common challenge due to a limited antenna range, which could sometimes be circumvented by prone positioning.