Dosimetric evaluations using cycle-consistent generative adversarial network synthetic CT for MR-guided adaptive radiation therapy

TL;DR

This study shows that synthetic CT images generated using deep learning can accurately support dose calculations in MRI-guided radiation therapy, enabling more efficient treatment planning.

Contribution

The study introduces a Cycle-GAN approach for generating synthetic CT images from MR scans suitable for real-time adaptive radiation therapy.

Findings

Synthetic CT images achieved a mean absolute error of 49.2±13.2 HU compared to deformed CT images.

Dosimetric evaluations showed minimal differences between synthetic CT and deformed CT, supporting their use in treatment planning.

Synthetic CT images showed better structural similarity and alignment with on-table MRI scans than deformed CT.

Abstract

Magnetic resonance (MR) guided radiation therapy combines high-resolution image capabilities of MRI with the precise targeting of radiation therapy. However, MRI does not provide the essential electron density information for accurate dose calculation, which limit the application of MRI. In this presented work, we evaluated the potential for Deep Learning (DL) based synthetic CT (sCT) generation using 3D MRI setup scans acquired during real-time adaptive MRI-guided radiation therapy.

We trained and evaluated a Cycle-consistent Generative Adversarial Network (Cycle-GAN) using paired MRI and deformably registered CT scan slices (dCT) in the context of real-time adaptive MRI-guided radiation therapy. Synthetic CT (sCT) volumes are output from the MR to CT generator of the Cycle-GAN network. A retrospective study was conducted to train and evaluate the DL model using data from patients undergoing treatment for kidney, pancreas, liver, lung, bone, and prostate tumors. Data was partitioned by patients using a stratified k-fold approach to ensure balanced representation of treatment sites in the training and testing sets. Synthetic CT images were evaluated using mean absolute error in Hounsfield Units (HU) relative to dCT, and four image quality metrics (mean absolute error, structural similarity index measure, peak signal-to-noise ratio, and normalized cross correlation) using the deformed CT scans as a reference standard. Synthetic CT volumes were also imported into a clinical treatment planning system and dosimetric calculations re-evaluated for each treatment plan (absolute difference in delivered dose to 3cm radius of PTV).

We trained the model using 8405 frames from 57 patients and evaluated it using a test set of 357 sCT frames from 17 patients. Quantitatively, sCTs were comparable to electron density of dCTs, while improving structural similarity with on-table MRI scans. The MAE between sCT and dCT was 49.2±13.2 HU, sCT NCC outperformed dCT by 0.06, and SSIM and PSNR were 0.97±0.01 and 19.9±1.6 respectively. Furthermore, dosimetric evaluations revealed minimal differences between sCTs and dCTs. Qualitatively, superior reconstruction of air-bubbles in sCT compared to dCT reveal higher alignment between sCT than dCT with the associated MR.

Accuracy of deep learning based synthetic CT generation using setup scans on MR-Linacs was adequate for dose calculation/optimization. This can enable MR-only treatment planning workflows on MR-Linacs, thereby increasing the efficiency of simulation and adaptive planning for MRgRT.

Figures