Comparison of CBCT‐based dose calculation methods in head and neck cancer radiotherapy: from Hounsfield unit to density calibration curve to deep learning

Abstract

Purpose: Anatomical variations occur during head and neck (H&N) radiotherapy treatment. kV cone-beam computed tomography (CBCT) images can be used for daily dose monitoring to assess dose variations owing to anatomic changes. Deep learning methods (DLMs) have recently been proposed to generate pseudo-CT (pCT) from CBCT to perform dose calculation. This study aims to evaluate the accuracy of a DLM and to compare this method with three existing methods of dose calculation from CBCT in H&N cancer radiotherapy. Methods: Forty-four patients received VMAT for H&N cancer (70-63-56 Gy). For each patient, reference CT (Bigbore, Philips) and CBCT images (XVI, Elekta) were acquired. The DLM was based on a generative adversarial network. The three compared methods were: (a) a method using a density to Hounsfield Unit (HU) relation from phantom CBCT image (HU-D curve method), (b) a water-airbone density assignment method (DAM), and iii) a method using deformable image registration (DIR). The imaging endpoints were the mean absolute error (MAE) and mean error (ME) of HU from pCT and reference CT (CT ref). The dosimetric endpoints were dose discrepancies and 3D gamma analyses (local, 2%/2 mm, 30% dose threshold). Dose discrepancies were defined as the mean absolute differences between DVHs calculated from the CT ref and pCT of each method. Results: In the entire body, the MAEs and MEs of the DLM, HU-D curve method, DAM, and DIR method were 82.4 and 17.1 HU, 266.6 and 208.9 HU, 113.2 and 14.2 HU, and 95.5 and −36.6 HU, respectively. The MAE obtained using the DLM differed significantly from those of other methods (Wilcoxon, P ≤ 0.05). The DLM dose discrepancies were 7 AE 8 cGy (maximum = 44 cGy) for the ipsilateral parotid gland D mean and 5 AE 6 cGy (max = 26 cGy) for the contralateral parotid gland mean dose (D mean). For the parotid gland D mean , no significant dose difference was observed between the DLM and other methods. The mean 3D gamma pass rate AE standard deviation was 98.1 AE 1.2%, 91.0 AE 5.3%, 97.9 AE 1.6%, and 98.8 AE 0.7% for the DLM, HU-D method, DAM, and DIR method, respectively. The gamma pass rates and mean gamma results of the HU-D curve method, DAM, and DIR method differed significantly from those of the DLM. The mean calculation time to generate one pCT was 30 sec for the deep learning and DIR methods. Conclusions: For H&N radiotherapy, DIR method and DLM appears as the most appealing CBCTbased dose calculation methods among the four methods in terms of dose accuracy as well as calculation time. Using the DIR method or DLM with CBCT images enables dose monitoring in the parotid glands during the treatment course and may be used to trigger replanning.

Evaluation of a cycle-generative adversarial network-based cone-beam CT to synthetic CT conversion algorithm for adaptive radiation therapy

“…The sCT image quality analysis of the H&N yielded ME/MAE values of the body contour and bone ROI of 1.4/77.2HU and 24/163HU, respectively. These results were lower than those reported by Barateau et al [35] with 17.1/82.4HU and 64.9/207.6HU that also used the Elekta XVI system for CBCT acquisition. Other studies using GAN for CBCT image processing presented values of − 6HU for the ME and 29.9HU and 51HU for the MAE of the body contour ROI [22,25].…”

“…Comparably large dose deviations were also obtained by a DIR-based CBCT correction approach with − 5.55% ± 14.3% for the thoracic spinal cord [48]. For the H&N body site, absolute mean dose differences for the parotid gland and the spinal cord were reported as 0.05-0.07 Gy and 0.42 Gy [35] which compares to our results by a factor of approximately 0.5. This discrepancy arises from the fact that the related study used rigid and deformable image registrations between the CBCT and pCT to minimize the negative effects of anatomic variations.…”

“…Regarding target volume dose metrics, two related studies reported dosimetric differences between the sCT and CT with a comparable accuracy to our study. A V 95 of 0.2-0.7% for the H&N body site [35] and an absolute difference of D 98 , D 50 and D 2 of − 1 to 0 Gy for the pelvic body site [30] were obtained, respectively. For the thoracic body region, D 98 showed the largest deviations and for the D 50 and D 2 outliers were observed which can be attributed to remaining uncertainties due to the breathing pattern.…”

“…The mean gamma pass rate for a 2%/2mm criterion for the H&N patients was over 95%. Three related studies working with GAN-based sCT reported values of 98.1% [35], 98.4% [22] and 95.3% [49] but were only indirectly relatable on account of differing dose thresholds or various types of reference images. In this sCT study, most dosimetric deviations were found in the regions of air cavities or PTV parts close to the daily varying patient outline.…”

Alert system for monitoring changes in patient anatomy during radiation therapy of head and neck cancer

“…The gamma maps and MQP could also be generated from comparisons of a synthetic CT created from CBCT. Work has been performed in this area using machine learning approaches 16 as well as deformable image registration. 17 These methods require preprocessing steps to generate the synthetic CT but have the potential for dose calculation.…”