Search

Background and purpose: Magnetic resonance imaging (MRI)-to-computed tomography (CT) synthesis is essential in MRI-only radiotherapy workflows, particularly through deep learning techniques known for their accuracy. However, current supervised methods are limited to specific center’s learnings and depend on registration precision. The aim of this study was to evaluate the accuracy of unsupervised and supervised approaches in the context of prostate MRI-to-CT generation for radiotherapy dose calculation. Methods: CT/MRI image pairs from 99 prostate cancer patients across three different centers were used. A comparison between supervised and unsupervised conditional Generative Adversarial Networks (cGAN) was conducted. Unsupervised training incorporates a style transfer method with. Content and Style Representation for Enhanced Perceptual synthesis (CREPs) loss. For dose evaluation, the photon prescription dose was 60 Gy delivered in volumetric modulated arc therapy (VMAT). Imaging endpoint for sCT evaluation was Mean Absolute Error (MAE). Dosimetric endpoints included absolute dose differences and gamma analysis between CT and sCT dose calculations. Results: The unsupervised paired network exhibited the highest accuracy for the body with a MAE at 33.6 HU, the highest MAE was 45.5 HU obtained with unsupervised unpaired learning. All architectures provided clinically acceptable results for dose calculation with gamma pass rates above 94 % (1 % 1 mm 10 %). Conclusions: This study shows that multicenter data can produce accurate sCTs via unsupervised learning, eliminating CT-MRI registration. The sCTs not only matched HU values but also enabled precise dose calculations, suggesting their potential for wider use in MRI-only radiotherapy workflows.

IntroductionLinear accelerator (linac) incorporating a magnetic resonance (MR) imaging device providing enhanced soft tissue contrast is particularly suited for abdominal radiation therapy. In particular, accurate segmentation for abdominal tumors and organs at risk (OARs) required for the treatment planning is becoming possible. Currently, this segmentation is performed manually by radiation oncologists. This process is very time consuming and subject to inter and intra operator variabilities. In this work, deep learning based automatic segmentation solutions were investigated for abdominal OARs on 0.35 T MR-images.MethodsOne hundred and twenty one sets of abdominal MR images and their corresponding ground truth segmentations were collected and used for this work. The OARs of interest included the liver, the kidneys, the spinal cord, the stomach and the duodenum. Several UNet based models have been trained in 2D (the Classical UNet, the ResAttention UNet, the EfficientNet UNet, and the nnUNet). The best model was then trained with a 3D strategy in order to investigate possible improvements. Geometrical metrics such as Dice Similarity Coefficient (DSC), Intersection over Union (IoU), Hausdorff Distance (HD) and analysis of the calculated volumes (thanks to Bland-Altman plot) were performed to evaluate the results.ResultsThe nnUNet trained in 3D mode achieved the best performance, with DSC scores for the liver, the kidneys, the spinal cord, the stomach, and the duodenum of 0.96 ± 0.01, 0.91 ± 0.02, 0.91 ± 0.01, 0.83 ± 0.10, and 0.69 ± 0.15, respectively. The matching IoU scores were 0.92 ± 0.01, 0.84 ± 0.04, 0.84 ± 0.02, 0.54 ± 0.16 and 0.72 ± 0.13. The corresponding HD scores were 13.0 ± 6.0 mm, 16.0 ± 6.6 mm, 3.3 ± 0.7 mm, 35.0 ± 33.0 mm, and 42.0 ± 24.0 mm. The analysis of the calculated volumes followed the same behavior.DiscussionAlthough the segmentation results for the duodenum were not optimal, these findings imply a potential clinical application of the 3D nnUNet model for the segmentation of abdominal OARs for images from 0.35 T MR-Linac.

IntroductionFor radiotherapy based solely on magnetic resonance imaging (MRI), generating synthetic computed tomography scans (sCT) from MRI is essential for dose calculation. The use of deep learning (DL) methods to generate sCT from MRI has shown encouraging results if the MRI images used for training the deep learning network and the MRI images for sCT generation come from the same MRI device. The objective of this study was to create and evaluate a generic DL model capable of generating sCTs from various MRI devices for prostate radiotherapyMaterials and methodsIn total, 90 patients from three centers (30 CT-MR prostate pairs/center) underwent treatment using volumetric modulated arc therapy for prostate cancer (PCa) (60 Gy in 20 fractions). T2 MRI images were acquired in addition to computed tomography (CT) images for treatment planning. The DL model was a 2D supervised conditional generative adversarial network (Pix2Pix). Patient images underwent preprocessing steps, including nonrigid registration. Seven different supervised models were trained, incorporating patients from one, two, or three centers. Each model was trained on 24 CT-MR prostate pairs. A generic model was trained using patients from all three centers. To compare sCT and CT, the mean absolute error in Hounsfield units was calculated for the entire pelvis, prostate, bladder, rectum, and bones. For dose analysis, mean dose differences of D99% for CTV, V95% for PTV, Dmax for rectum and bladder, and 3D gamma analysis (local, 1%/1 mm) were calculated from CT and sCT. Furthermore, Wilcoxon tests were performed to compare the image and dose results obtained with the generic model to those with the other trained models.ResultsConsidering the image results for the entire pelvis, when the data used for the test comes from the same center as the data used for training, the results were not significantly different from the generic model. Absolute dose differences were less than 1 Gy for the CTV D99% for every trained model and center. The gamma analysis results showed nonsignificant differences between the generic and monocentric models.ConclusionThe accuracy of sCT, in terms of image and dose, is equivalent to whether MRI images are generated using the generic model or the monocentric model. The generic model, using only eight MRI-CT pairs per center, offers robust sCT generation, facilitating PCa MRI-only radiotherapy for routine clinical use.

Background and Purpose: Addressing the need for accurate dose calculation in MRI-only radiotherapy, the generation of synthetic Computed Tomography (sCT) from MRI has emerged. Deep learning (DL) techniques, have shown promising results in achieving high sCT accuracies. However, existing sCT synthesis methods are often center-specific, posing a challenge to their generalizability. To overcome this limitation, recent studies have proposed approaches, such as multicenter training . Material and methods: The purpose of this work was to propose a multicenter sCT synthesis by DL, using a 2D cycle-GAN on 128 prostate cancer patients, from four different centers. Four cases were compared: monocenter cases, monocenter training and test on another center, multicenter trainings and a test on a center not included in the training and multicenter trainings with an included center in the test. Trainings were performed using 20 patients. sCT accuracy evaluation was performed using Mean Absolute Error, Mean Error and Peak-Signal-to-Noise-Ratio. Dose accuracy was assessed with gamma index and Dose Volume Histogram comparison. Results: Qualitative, quantitative and dose results show that the accuracy of sCTs for monocenter trainings and multicenter trainings using a seen center in the test did not differ significantly. However, when the test involved an unseen center, the sCT quality was inferior. Conclusions: The aim of this work was to propose generalizable multicenter training for MR-to-CT synthesis. It was shown that only a few data from one center included in the training cohort allows sCT accuracy equivalent to a monocenter study.

Purpose: The optimal salvage pelvic treatment for nodal recurrences in prostate cancer is not yet clearly defined. We aimed to compare outcomes of salvage involved-field radiation therapy (s-IFRT) and salvage extended-field radiation therapy (s-EFRT) for positron emission tomography/computed tomography–positive nodal-recurrent prostate cancer and to analyze patterns of progressions after salvage nodal radiation therapy. Methods and Materials: Patients with 18F-fluorocholine or 68Ga prostate-specific membrane antigen ligand positron emission tomography/computed tomography–positive nodal-recurrent prostate cancer and treated with s-IFRT or s-EFRT were retrospectively selected. Time to biochemical failure, time to palliative androgen deprivation therapy (ADT), and distant metastasis–free survival were analyzed. Results: Between 2009 and 2019, 86 patients were treated with salvage nodal radiation therapy: 38 with s-IFRT and 48 with s-EFRT. After a median follow-up of 41.9 months (5.4-122.1 months), 47 patients presented a further relapse: 31 after s-IFRT and 16 after s-EFRT, with only 1 in-field relapse. The median time to palliative ADT was 24.8 months (95% confidence interval [CI], 13.3-93.5 months) in the s-IFRT group and not yet reached (95% CI, 40.3 months to not yet reached) in the s-EFRT group (P = .010). The 3-year biochemical failure–free rate was 70.2% (95% CI, 51.5%-82.9%) with s-IFRT and 73.9% (95% CI, 55.4%-85.7%) with s-EFRT (P = .657). The 3-year distant metastasis–free survival was 74.1% (95% CI, 56.0%-85.7%) with s-IFRT and 82.0% (95% CI, 63.0%-91.8%) with s-EFRT (P = .338). Conclusions: s-EFRT and s-IFRT for positron emission tomography–positive nodal-recurrent prostate cancer provide excellent local control. Time to palliative ADT was longer following s-EFRT than following s-IFRT.

MR-Linac is a recent device combining a linear accelerator with an MRI scanner. The improved soft tissue contrast of MR images is used for optimum delineation of tumors or organs at risk (OARs) and precise treatment delivery. Automatic segmentation of OARs can contribute to alleviating the time-consuming process for radiation oncologists and improving the accuracy of radiation delivery by providing faster, more consistent, and more accurate delineation of target structures and organs at risk. It can also help reduce inter-observer variability and improve the consistency of contouring while reducing the time required for treatment planning. In this work, state-of-the-art deep learning techniques were evaluated based on 2D and 2.5D training strategies to develop a comprehensive tool for the accurate segmentation of pelvic OARs dedicated to 0.35 T MR-Linac. In total, 103 cases with 0.35 T MR images of the pelvic region were investigated. Experts considered and contoured the bladder, rectum, and femoral heads as OARs and the prostate as the target volume. For the training of the neural network, 85 patients were randomly selected, and 18 were used for testing. Multiple U-Net-based architectures were considered, and the best model was compared using both 2D and 2.5D training strategies. The evaluation of the models was performed based on two metrics: the Dice similarity coefficient (DSC) and the Hausdorff distance (HD). In the 2D training strategy, Residual Attention U-Net (ResAttU-Net) had the highest scores among the other deep neural networks. Due to the additional contextual information, the configured 2.5D ResAttU-Net performed better. The overall DSC were 0.88 ± 0.09 and 0.86 ± 0.10, and the overall HD was 1.78 ± 3.02 mm and 5.90 ± 7.58 mm for 2.5D and 2D ResAttU-Net, respectively. The 2.5D ResAttU-Net provides accurate segmentation of OARs without affecting the computational cost. The developed end-to-end pipeline will be merged with the treatment planning system for in-time automatic segmentation.

The advent of the 0.35 T MR-Linac (MRIdian, ViewRay) system in radiation therapy allows precise tumor targeting for moving lesions. However, the lack of an automatic volume segmentation function in the MR-Linac’s treatment planning system poses a challenge. In this paper, we propose a deep-learning-based multiorgan segmentation approach for the thoracic region, using EfficientNet as the backbone for the network architecture. The objectives of this approach include accurate segmentation of critical organs, such as the left and right lungs, the heart, the spinal cord, and the esophagus, essential for minimizing radiation toxicity during external radiation therapy. Our proposed approach, when evaluated on an internal dataset comprising 81 patients, demonstrated superior performance compared to other state-of-the-art methods. Specifically, the results for our approach with a 2.5D strategy were as follows: a dice similarity coefficient (DSC) of 0.820 ± 0.041, an intersection over union (IoU) of 0.725 ± 0.052, and a 3D Hausdorff distance (HD) of 10.353 ± 4.974 mm. Notably, the 2.5D strategy surpassed the 2D strategy in all three metrics, exhibiting higher DSC and IoU values, as well as lower HD values. This improvement strongly suggests that our proposed approach with the 2.5D strategy may hold promise in achieving more precise and accurate segmentations when compared to the conventional 2D strategy. Our work has practical implications in the improvement of treatment planning precision, aligning with the evolution of medical imaging and innovative strategies for multiorgan segmentation tasks.