Automatic tandem and ring reconstruction using MRI for cervical cancer brachytherapy

Abstract

Purpose The MRI‐guided cervical cancer brachytherapy provides unparalleled soft‐tissue contrast for target and normal tissue contouring, but eliminates the ability to use conventional metallic fiducials for radiation source path reconstruction as required for treatment planning. Instead, the source path is reconstructed by manually aligning a library model to the signal void produced by the applicator, which takes time intraoperatively and precludes fully automated treatment planning. The purpose of this study is to present and validate an algorithm to automatically reconstruct tandem and ring applicators using MRI for cervical cancer brachytherapy treatment planning. Methods Applicators were reconstructed using T2‐weighted MR images acquired at 1.5 T from 33 brachytherapy fractions including 10 patients using a model‐to‐image registration algorithm. The algorithm involves (a) image filtering and maximum intensity projection to highlight the applicator, (b) ring center identification using the circular Hough transform, and (c) three‐dimensional surface model registration, optimized by maximizing the image intensity gradient normal to the model surface. Two independent observers manually reconstructed all applicators, enabling the calculation of interobserver variability and establishing a ground truth. Algorithm variability was calculated by comparing algorithm results to each individual observer, and algorithm accuracy was calculated by comparing algorithm results to the ground truth. The algorithm variability and accuracy were compared to the interobserver variability using paired t‐tests. Results Mean ± SD interobserver variability was 0.83 ± 0.31 mm and 0.78 ± 0.29 mm for the ring and tandem, respectively. The algorithm had mean ± SD variability and accuracy of 0.72 ± 0.32 mm (P = 0.02) and 0.60 ± 0.24 mm (P = 0.0005) for the ring, and 0.70 ± 0.29 mm (P = 0.11) and 0.58 ± 0.24 mm (P = 0.004) for the tandem, respectively. Conclusions The algorithm variability and accuracy were within the interobserver variability measured in this study. The algorithm accuracy and mean execution time of 10.0 s are sufficient for clinical tandem and ring reconstruction, and are a step toward fully automated tandem and ring brachytherapy treatment planning.

The Fusion of MRI and CT in the Planning of Brachytherapy for Cancer of the Uterine Cervix

“…The beginning of this practice has already been described in older methodological works, which, although they used image fusion, have not yet provided for the 3D volumetric planning of radiation dose application [6,8,22]. In order to use the automatic fusion of MRI and CT [23], these anatomical changes must be taken into account. That is why a vaginal applicator in situ cannot be dispensed with in scanning MRI.…”

Deep learning applications in automatic segmentation and reconstruction in CT-based cervix brachytherapy

“…Hrinivich et al studied an image model algorithm to reconstruct the applicator in cervical cancer guided by MRI. The average reconstruction accuracy of ring applicator and tandem applicator were 0.83 mm and 0.78 mm, respectively [9]. Based on the U-Net, Jung et al proposed a deep learning-assisted applicators and interstitial needles digitization method for 3D CT image-based brachytherapy.…”

“…Before deep learning, researchers usually used threshold-based method to segment the applicator; however, this method still requires planners to define some points manually in clinical practice [5]. In recent years, more studies on automatic applicator reconstruction have been conducted based on deep learning [6][7][8][9][10][11][12].…”

Deep‐learning‐assisted algorithm for catheter reconstruction during MR‐only gynecological interstitial brachytherapy

“…13 Hrinivich et al reconstructed ring-shaped and oval applicators in MRI images through a model-to-image registration algorithm. 14 Recently, the use of deep learning for catheter segmentation has been reported during brachytherapy procedures in CT, 15 MRI, 16 and US. 14 Jung et al proposed a deep-learning assisted approach to reconstruct ring and tandem applicators in gynecological HDR brachytherapy.…”

“…14 Recently, the use of deep learning for catheter segmentation has been reported during brachytherapy procedures in CT, 15 MRI, 16 and US. 14 Jung et al proposed a deep-learning assisted approach to reconstruct ring and tandem applicators in gynecological HDR brachytherapy. 17 The proposed method was able to automatically reconstruct the applicator in approximately 15 s per case.…”