Facilitating MR-Guided Adaptive Proton Therapy in Children Using Deep Learning-Based Synthetic CT

Abstract

Purpose To determine whether self-attention cycle-generative adversarial networks (cycle-GANs), a novel deep-learning method, can generate accurate synthetic computed tomography (sCT) to facilitate adaptive proton therapy in children with brain tumors. Materials and Methods Both CT and T1-weighted magnetic resonance imaging (MRI) of 125 children (ages 1-20 years) with brain tumors were included in the training dataset. A model introducing a self-attention mechanism into the conventional cycle-GAN was created to enhance tissue interfaces and reduce noise. The test dataset consisted of 7 patients (ages 2-14 years) who underwent adaptive planning because of changes in anatomy discovered on MRI during proton therapy. The MRI during proton therapy-based sCT was compared with replanning CT (ground truth). Results The Hounsfield unit-mean absolute error was significantly reduced with self-attention cycle-GAN, as compared with conventional cycle-GAN (65.3 ± 13.9 versus 88.9 ± 19.3, P < .01). The average 3-dimensional gamma passing rates (2%/2 mm criteria) for the original plan on the anatomy of the day and for the adapted plan were high (97.6% ± 1.2% and 98.9 ± 0.9%, respectively) when using sCT generated by self-attention cycle-GAN. The mean absolute differences in clinical target volume (CTV) receiving 95% of the prescription dose and 80% distal falloff along the beam axis were 1.1% ± 0.8% and 1.1 ± 0.9 mm, respectively. Areas of greatest dose difference were distal to the CTV and corresponded to shifts in distal falloff. Plan adaptation was appropriately triggered in all test patients when using sCT. Conclusion The novel cycle-GAN model with self-attention outperforms conventional cycle-GAN for children with brain tumors. Encouraging dosimetric results suggest that sCT generation can be used to identify patients who would benefit from adaptive replanning.

Toward MR‐only proton therapy planning for pediatric brain tumors: Synthesis of relative proton stopping power images with multiple sequence MRI and development of an online quality assurance tool

“…Efforts have been made to derive synthetic CT (sCT) in lieu of a real CT (rCT)for MR-only proton therapy planning. [3][4][5][6][7][8][9] Recent breakthroughs largely stem from deep learning, specifically generative adversarial networks (GANs), [9][10][11][12][13][14][15] which expeditiously transform adult MRI to CT and vice versa. An MR-only proton therapy planning workflow would not only eliminate the cost, time, and radiation exposure associated with CT acquisition, but also eliminate uncertainties involved in MR-to-CT registration, and enable time-efficient adaptive proton therapy.…”

“…An MR-only proton therapy planning workflow would not only eliminate the cost, time, and radiation exposure associated with CT acquisition, but also eliminate uncertainties involved in MR-to-CT registration, and enable time-efficient adaptive proton therapy. 15,16 Multiple barriers remain toward implementing MRonly proton therapy planning. First, it is unclear which MRI sequence or combination of common sequences (T1-weighted (T1W), T2-weighted (T2W), and FLAIR) will result in the most accurate sCT, particularly for children.…”

Adaptive Proton Therapy of Pediatric Head and Neck Cases Using MRI-Based Synthetic CTs: Initial Experience of the Prospective KiAPT Study

“…Other studies report about direct sCTs from MRI (see Refs. [ 58 , 59 , 60 , 61 , 62 ] and references therein). Especially, the machine learning based implementation is gaining popularity.…”

Feasibility of Monte Carlo dropout‐based uncertainty maps to evaluate deep learning‐based synthetic CTs for adaptive proton therapy

“…Besides conventional computed tomography (CT) imaging, which is routinely used for treatment planning and verification, cone beam CT (CBCT) and magnetic resonance imaging (MRI) can provide valuable information within adaptive treatment workflows. 3,4 The direct implementation of CBCT and MRI in adaptive radiotherapy is challenging.In-room CBCT systems offer daily imaging for monitoring patient position and anatomical changes. However, there is a need to enhance the image quality due to the presence of scattering artifacts.…”

“…The availability of large, paired MRI and CT image datasets makes it possible to use deep learning (DL) methods to generate sCTs. In recent years, several DL approaches have been developed to create sCTs from CBCT 5,6 and MRI images, 3,[7][8][9] enabling proton dose calculations in adaptive workflows. 10 A fast sCT conversion process is essential for integration into routine clinical practice.…”