Magnetic resonance imaging-based bone imaging of the lower limb: Strategies for generating high-resolution synthetic computed tomography.

This study aims at assessing approaches for generating high-resolution magnetic resonance imaging- (MRI-) based synthetic computed tomography (sCT) images suitable for orthopedic care using a deep learning model trained on low-resolution computed tomography (CT) data. To that end, paired MRI and CT data of three anatomical regions were used: high-resolution knee and ankle data, and low-resolution hip data. Four experiments were conducted to investigate the impact of low-resolution training CT data on sCT generation and to find ways to train models on low-resolution data while providing high-resolution sCT images. Experiments included resampling of the training data or augmentation of the low-resolution data with high-resolution data. Training sCT generation models using low-resolution CT data resulted in blurry sCT images. By resampling the MRI/CT pairs before the training, models generated sharper images, presumably through an increase in the MRI/CT mutual information. Alternatively, augmenting the low-resolution with high-resolution data improved sCT in terms of mean absolute error proportionally to the amount of high-resolution data. Overall, the morphological accuracy was satisfactory as assessed by an average intermodal distance between joint centers ranging from 0.7 to 1.2 mm and by an average intermodal root-mean-squared distances between bone surfaces under 0.7 mm. Average dice scores ranged from 79.8% to 87.3% for bony structures. To conclude, this paper proposed approaches to generate high-resolution sCT suitable for orthopedic care using low-resolution data. This can generalize the use of sCT for imaging the musculoskeletal system, paving the way for an MR-only imaging with simplified logistics and no ionizing radiation.

Synthetic CT for the planning of MR-HIFU treatment of bone metastases in pelvic and femoral bones: a feasibility study.

OBJECTIVES: Visualization of the bone distribution is an important prerequisite for MRI-guided high-intensity focused ultrasound (MRI-HIFU) treatment planning of bone metastases. In this context, we evaluated MRI-based synthetic CT (sCT) imaging for the visualization of cortical bone. METHODS: MR and CT images of nine patients with pelvic and femoral metastases were retrospectively analyzed in this study. The metastatic lesions were osteolytic, osteoblastic or mixed. sCT were generated from pre-treatment or treatment MR images using a UNet-like neural network. sCT was qualitatively and quantitatively compared to CT in the bone (pelvis or femur) containing the metastasis and in a region of interest placed on the metastasis itself, through mean absolute difference (MAD), mean difference (MD), Dice similarity coefficient (DSC), and root mean square surface distance (RMSD). RESULTS: The dataset consisted of 3 osteolytic, 4 osteoblastic and 2 mixed metastases. For most patients, the general morphology of the bone was well represented in the sCT images and osteolytic, osteoblastic and mixed lesions could be discriminated. Despite an average timespan between MR and CT acquisitions of 61 days, in bone, the average (± standard deviation) MAD was 116 ± 26 HU, MD - 14 ± 66 HU, DSC 0.85 ± 0.05, and RMSD 2.05 ± 0.48 mm and, in the lesion, MAD was 132 ± 62 HU, MD - 31 ± 106 HU, DSC 0.75 ± 0.2, and RMSD 2.73 ± 2.28 mm. CONCLUSIONS: Synthetic CT images adequately depicted the cancellous and cortical bone distribution in the different lesion types, which shows its potential for MRI-HIFU treatment planning. KEY POINTS: • Synthetic computed tomography was able to depict bone distribution in metastatic lesions. • Synthetic computed tomography images intrinsically aligned with treatment MR images may have the potential to facilitate MR-HIFU treatment planning of bone metastases, by combining visualization of soft tissues and cancellous and cortical bone.

Deep learning-enabled MRI-only photon and proton therapy treatment planning for paediatric abdominal tumours.

PURPOSE: To assess the feasibility of magnetic resonance imaging (MRI)-only treatment planning for photon and proton radiotherapy in children with abdominal tumours. MATERIALS AND METHODS: The study was conducted on 66 paediatric patients with Wilms' tumour or neuroblastoma (age 4 ± 2 years) who underwent MR and computed tomography (CT) acquisition on the same day as part of the clinical protocol. MRI intensities were converted to CT Hounsfield units (HU) by means of a UNet-like neural network trained to generate synthetic CT (sCT) from T1- and T2-weighted MR images. The CT-to-sCT image similarity was evaluated by computing the mean error (ME), mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and Dice similarity coefficient (DSC). Synthetic CT dosimetric accuracy was verified against CT-based dose distributions for volumetric-modulated arc therapy (VMAT) and intensity-modulated pencil-beam scanning (PBS). Relative dose differences (Ddiff) in the internal target volume and organs-at-risk were computed and a three-dimensional gamma analysis (2 mm, 2%) was performed. RESULTS: The average ± standard deviation ME was -5 ± 12 HU, MAE was 57 ± 12 HU, PSNR was 30.3 ± 1.6 dB and DSC was 76 ± 8% for bones and 92 ± 9% for lungs. Average Ddiff were <0.5% for both VMAT (range [-2.5; 2.4]%) and PBS (range [-2.7; 3.7]%) dose distributions. The average gamma pass-rates were >99% (range [85; 100]%) for VMAT and >96% (range [87; 100]%) for PBS. CONCLUSION: The deep learning-based model generated accurate sCT from planning T1w- and T2w-MR images. Most dosimetric differences were within clinically acceptable criteria for photon and proton radiotherapy, demonstrating the feasibility of an MRI-only workflow for paediatric patients with abdominal tumours.

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

PURPOSE: To develop and evaluate a patch-based convolutional neural network (CNN) to generate synthetic computed tomography (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 artifacts. In this study, we evaluate whether the generated sCT images enable accurate MR-based dose calculations in the head and neck region. METHODS: 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 nonrigidly registered to the MR (CTreg ). The CNN was based on a U-net architecture and consisted of 14 layers with 3 × 3 × 3 filters. Patches of 48 × 48 × 48 were randomly extracted and fed into the training. sCTs were created for all patients using threefold 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. RESULTS: sCT generation took 4 min per patient. The MAE over the patient population of the sCT within the intersection of body contours was 75 ± 9 Hounsfield Units (HU) (±1 SD), 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 artifacts obscuring the CT could be circumvented in the sCT by the CNN-based approach in combination with Turbo Spin Echo (TSE) magnetic resonance imaging (MRI) sequence that typically is less prone to susceptibility artifacts. CONCLUSIONS: 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.