Robust contour propagation using deep learning and image registration for online adaptive proton therapy of prostate cancer

Robust contour propagation using deep learning and image registration for online adaptive proton therapy of prostate cancer

Elmahdy, Mohamed S. (Leiden University Medical Center)
Jagt, Thyrza (Erasmus MC)
Zinkstok, Roel Th. (Leiden University Medical Center)
Qiao, Yuchuan (Leiden University Medical Center)
Shahzad, Rahil (Leiden University Medical Center)
Sokooti, Hessam (Leiden University Medical Center)
Yousefi, Sahar (Leiden University Medical Center)
Incrocci, Luca (Erasmus MC)
Marijnen, C.A.M. (Leiden University Medical Center)
Hoogeman, Mischa (Erasmus MC)
Staring, M. (TU Delft Pattern Recognition and Bioinformatics; Leiden University Medical Center)

2019

Purpose: To develop and validate a robust and accurate registration pipeline for automatic contour propagation for online adaptive Intensity-Modulated Proton Therapy (IMPT) of prostate cancer using elastix software and deep learning. Methods: A three-dimensional (3D) Convolutional Neural Network was trained for automatic bladder segmentation of the computed tomography (CT) scans. The automatic bladder segmentation alongside the computed tomography (CT) scan is jointly optimized to add explicit knowledge about the underlying anatomy to the registration algorithm. We included three datasets from different institutes and CT manufacturers. The first was used for training and testing the ConvNet, where the second and the third were used for evaluation of the proposed pipeline. The system performance was quantified geometrically using the dice similarity coefficient (DSC), the mean surface distance (MSD), and the 95% Hausdorff distance (HD). The propagated contours were validated clinically through generating the associated IMPT plans and compare it with the IMPT plans based on the manual delineations. Propagated contours were considered clinically acceptable if their treatment plans met the dosimetric coverage constraints on the manual contours. Results: The bladder segmentation network achieved a DSC of 88% and 82% on the test datasets. The proposed registration pipeline achieved a MSD of 1.29 ± 0.39, 1.48 ± 1.16, and 1.49 ± 0.44 mm for the prostate, seminal vesicles, and lymph nodes, respectively, on the second dataset and a MSD of 2.31 ± 1.92 and 1.76 ± 1.39 mm for the prostate and seminal vesicles on the third dataset. The automatically propagated contours met the dose coverage constraints in 86%, 91%, and 99% of the cases for the prostate, seminal vesicles, and lymph nodes, respectively. A Conservative Success Rate (CSR) of 80% was obtained, compared to 65% when only using intensity-based registration. Conclusion: The proposed registration pipeline obtained highly promising results for generating treatment plans adapted to the daily anatomy. With 80% of the automatically generated treatment plans directly usable without manual correction, a substantial improvement in system robustness was reached compared to a previous approach. The proposed method therefore facilitates more precise proton therapy of prostate cancer, potentially leading to fewer treatment-related adverse side effects.

convolutional neural networks (CNN)
deformable image registration
distended rectum
generative adversarial network (GAN)
prostate cancer
proton therapy

http://resolver.tudelft.nl/uuid:1d1eb970-61c1-4b2f-b6a7-7f802a85723b

https://doi.org/10.1002/mp.13620

0094-2405

Medical Physics, 46 (8), 3329-3343

Institutional Repository

journal article

© 2019 Mohamed S. Elmahdy, Thyrza Jagt, Roel Th. Zinkstok, Yuchuan Qiao, Rahil Shahzad, Hessam Sokooti, Sahar Yousefi, Luca Incrocci, C.A.M. Marijnen, Mischa Hoogeman, M. Staring