Dosimetric evaluation of synthetic CT for head and neck radiotherapy generated by a patch-based 3D convolutional neural network.

Researchers

Journal

Modalities

Models

Abstract

To develop and evaluate a patch-based convolutional neural network (CNN) to generate synthetic CT (sCT) images for magnetic resonance (MR)-only workflow for radiotherapy of head and neck tumors. A patch-based deep learning method was chosen to improve robustness to abnormal anatomies caused by large tumors, surgical excisions or dental artefacts. In this study we evaluate whether the generated sCT images generated enable accurate MR-based dose calculations in the head and neck region.
We conducted a retrospective study on 34 patients with head and neck cancer who underwent both CT and MR imaging for radiotherapy treatment planning. To generate the sCTs, a large field-of-view T2-weighted Turbo Spin Echo MR sequence was used from the clinical protocol for multiple types of head and neck tumors. To align images as well as possible on a voxel-wise level, CT scans were non-rigidly registered to the MR (CTreg ). The CNN was based on a U-net architecture and consisted of 14 layers with 3x3x3 filters. Patches of 48x48x48 were randomly extracted and fed into the training. sCTs were created for all patients using three-fold cross validation. For each patient, the clinical CT-based treatment plan was recalculated on sCT using Monaco TPS (Elekta). We evaluated mean absolute error (MAE) and mean error (ME) within the body contours and dice scores in air and bone mask. Also, dose differences and gamma pass rates between CT- and sCT-based plans inside the body contours were calculated.
sCT generation took 4 minutes per patient. The MAE over the patient population of the sCT within the intersection of body contours was 75 9 Hounsfield Units (HU) (±1SD), and the ME was 9±11 HU. Dice scores of the air and bone masks (CTreg vs sCT) were 0.79 0.08 and 0.70 0.07 respectively. Dosimetric analysis showed mean deviations of -0.03% ± 0.05% for dose within the body contours and -0.07% 0.22% inside the >90% dose volume. Dental artefacts obscuring the CT, could be circumvented in the sCT by the CNN-based approach in combination with TSE MRI sequence that typically is less prone to susceptibility artefacts.
The presented CNN generated sCTs from conventional MR images without adding scan time to the acquisition. Dosimetric evaluation suggests that dose calculations performed on the sCTs are accurate, and can therefore be used for MR-only radiotherapy treatment planning of the head and neck. This article is protected by copyright. All rights reserved.
This article is protected by copyright. All rights reserved.