Evaluation of deformable image registration algorithm for determination of accumulated dose for brachytherapy of cervical cancer patients

Abstract

PurposeThis study was designed to assess the dose accumulation (DA) of bladder and rectum between brachytherapy fractions using hybrid-based deformable image registration (DIR) and compare it with the simple summation (SS) approach of GEC-ESTRO in cervical cancer patients.Material and methodsPatients (n = 137) with cervical cancer treated with 3D conformal radiotherapy and three fractions of high-dose-rate brachytherapy were selected. CT images were acquired to delineate organs at risk and targets according to GEC-ESTRO recommendations. In order to determine the DA for the bladder and rectum, hybrid-based DIR was done for three different fractions of brachytherapy and the results were compared with the standard GEC-ESTRO method. Also, we performed a phantom study to calculate the uncertainty of the hybrid-based DIR algorithm for contour matching and dose mapping.ResultsThe mean ± standard deviation (SD) of the Dice similarity coefficient (DICE), Jaccard, Hausdorff distance (HD) and mean distance to agreement (MDA) in the DIR process were 0.94 ±0.02, 0.89 ±0.03, 8.44 ±3.56 and 0.72 ±0.22 for bladder and 0.89 ±0.05, 0.80 ±0.07, 15.46 ±10.14 and 1.19 ±0.59 for rectum, respectively. The median (Q1, Q3; maximum) GyEQD2 differences of total D2cc between DIR-based and SS methods for the bladder and rectum were reduced by –1.53 (–0.86, –2.98; –9.17) and –1.38 (–0.80, –2.14; –7.11), respectively. The mean ± SD of DICE, Jaccard, HD, and MDA for contour matching were 0.98 ±0.008, 0.97 ±0.01, 2.00 ±0.70 and 0.20 ±0.04, respectively for large deformation. Maximum uncertainty of dose mapping was about 3.58%.ConclusionsThe hybrid-based DIR algorithm demonstrated low registration uncertainty for both contour matching and dose mapping. The DA difference between DIR-based and SS approaches was statistically significant for both bladder and rectum and hybrid-based DIR showed potential to assess DA between brachytherapy fractions.

Deep learning-based auto-segmentation of organs at risk in high-dose rate brachytherapy of cervical cancer

“…ABAS algorithms use deformable image registration to transform OAR contours from the atlas into the new image. There is a lack of certainty in deformable registration algorithms [15][16][17], particularly when intensity-based algorithms are used. In addition, there are a number of issues that must be considered when using ABAS since there is a large variability in the pelvic region owing to internal organs motion, bladder filling, and presence of gas in the rectum.…”

“…In addition, there are a number of issues that must be considered when using ABAS since there is a large variability in the pelvic region owing to internal organs motion, bladder filling, and presence of gas in the rectum. These factors result in sub-optimal performance of ABAS, in particular when a small number of atlases (typically [10][11][12][13][14][15][16][17][18][19][20] are used [18][19][20][21]. Moreover, the presence of applicators and CT markers for brachytherapy implantation tends to decrease contrast to noise ratio and to increase high-density…”

Accuracy of registrations between cone-beam computed tomography and conventional computed tomography images and dose mapping methods in RaySearch software for the bladder during brachytherapy of cervical cancer patients

“…Therefore, to map BRT doses in the bladder visualized in CT images (EBRT), advanced image registration methods need to be applied. For the sake of clinical utility, it is important to measure the error caused by those transformations., and for that reason, the present study did not raise issues related to combining doses deposited in particular BRT fractions [21] or combining doses between BRT and EBRT [5]. The study only evaluated the accuracy of image registration and dose-based transformations performed.…”

Automatic contouring using deformable image registration for tandem-ring or tandem-ovoid brachytherapy

“…Virtual phantoms were generally preferred for verification. Mohammadi et al [38] evaluated hybrid-based DIR algorithm using a virtual phantom, and demonstrated a low registration uncertainty for both contour matching and dose mapping. On the other hand, DIR is particularly challenging in the pelvic region due to large and complex deformations caused by organ motions, applicator displacement, and differences in the rectum and bladder filling [23,28,39].…”