Treatment planning using MRI data: an analysis of the dose calculation accuracy for different treatment regions

The Use of Magnetic Resonance Imaging in Radiation Therapy Treatment Simulation and Planning

Ever since its introduction as a diagnostic imaging tool the potential of magnetic resonance imaging (MRI) in radiation therapy (RT) treatment simulation and planning has been recognized. Recent technical advances have addressed many of the impediments to use of this technology and as a result have resulted in rapid and growing adoption of MRI in RT. The purpose of this article is to provide a broad review of the multiple uses of MR in the RT treatment simulation and planning process, identify several of the most used clinical scenarios in which MR is integral to the simulation and planning process, highlight existing limitations and provide multiple unmet needs thereby highlighting opportunities for the diagnostic MR imaging community to contribute and collaborate with our oncology colleagues. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 5.

Synthetic CT for gamma knife radiosurgery dose calculation: A feasibility study

PURPOSE

To determine if MRI-based synthetic CTs (sCT), generated with no predefined pulse sequence, can be used for inhomogeneity correction in routine gamma knife radiosurgery (GKRS) treatment planning dose calculation.

METHODS

Two sets of sCTs were generated from T1post and T2 images using cycleGAN. Twenty-eight patients (18 training, 10 validation) were retrospectively selected. The image quality of the generated sCTs was compared with the original CT (oCT) regarding the HU value preservation using histogram comparison, RMSE and MAE, and structural integrity. Dosimetric comparisons were also made among GKRS plans from 3 calculation approaches: TMR10 (oCT), and convolution (oCT and sCT), at four locations: original disease site, bone/tissue interface, air/tissue interface, and mid-brain.

RESULTS

The study showed that sCTs and oCTs' HU were similar, with T2-sCT performing better. TMR10 significantly underdosed the target by a mean of 5.4% compared to the convolution algorithm. There was no significant difference in convolution algorithm shot time between the oCT and sCT generated with T2. The highest and lowest dosimetric differences between the two CTs were observed in the bone and air interface, respectively. Dosimetric differences of 3.3% were observed in sCT predicted from MRI with stereotactic frames, which was not included in the training sets.

CONCLUSIONS

MRI-based sCT can be utilized for GKRS convolution dose calculation without the unnecessary radiation dose, and sCT without metal artifacts could be generated in framed cases. Larger datasets inclusive of all pulse sequences can improve the training set. Further investigation and validation studies are needed before clinical implementation.

A body mass index-based method for "MR-only" abdominal MR-guided adaptive radiotherapy

PURPOSE

Dose calculation for MR-guided radiotherapy (MRgRT) at the 0.35 T MR-Linac is currently based on deformation of planning CTs (defCT) acquired for each patient. We present a simple and robust bulk density overwrite synthetic CT (sCT) method for abdominal treatments in order to streamline clinical workflows.

METHOD

Fifty-six abdominal patient treatment plans were retrospectively evaluated. All patients had been treated at the MR-Linac using MR datasets for treatment planning and plan adaption and defCT for dose calculation. Bulk density CTs (4M-sCT) were generated from MR images with four material compartments (bone, lung, air, soft tissue). The relative electron densities (RED) for bone and lung were extracted from contoured CT structure average REDs. For soft tissue, a correlation between BMI and RED was evaluated. Dose was recalculated on 4M-sCT and compared to dose distributions on defCTs assessing dose differences in the PTV and organs at risk (OAR).

RESULTS

Mean RED of bone was 1.17 ± 0.02, mean RED of lung 0.17 ± 0.05. The correlation between BMI and RED for soft tissue was statistically significant (p < 0.01). PTV dose differences between 4M-sCT and defCT were Dmean: -0.4 ± 1.0%, D1%: -0.3 ± 1.1% and D95%: -0.5 ± 1.0%. OARs showed D2%: -0.3 ± 1.9% and Dmean: -0.1 ± 1.4% differences. Local 3D gamma index pass rates (2%/2mm) between dose calculated using 4M-sCT and defCT were 96.8 ± 2.6% (range 89.9-99.6%).

CONCLUSION

The presented method for sCT generation enables precise dose calculation for MR-only abdominal MRgRT.

Application of MR images in radiotherapy planning for brain tumor based on deep learning

PURPOSE

Explore the function and dose calculation accuracy of MRI images in radiotherapy planning through deep learning methods.

METHODS

131 brain tumor patients undergoing radiotherapy with previous MR and CT images were recruited for this study. A new series of MRI from the aligned MR was firstly registered to CT images strictly using MIM software and then resampled. A deep learning method (U-NET) was used to establish a MRI-to-CT conversion model, for which 105 patient images were used as the training set and 26 patient images were used as the tuning set. Data from additional 8 patients were collected as the test set, and the accuracy of the model was evaluated from a dosimetric standpoint.

RESULTS

Comparing the synthetic CT images with the original CT images, the difference in dosimetric parameters D98, D95, D2 and Dmean of PTV in 8 patients was less than 0.5%. The gamma passed rates of PTV and whole body volume were: 1%/1 mm: 93.96%±6.75%, 2%/2 mm: 99.87%±0.30%, 3%/3 mm: 100.00%±0.00%; and 1%/1 mm: 99.14%±0.80%, 2%/2 mm: 99.92%±0.08%, 3%/3 mm: 99.99%±0.01%.

CONCLUSION

MR images can be used both in delineation and treatment efficacy evaluation and in dose calculation. Using the deep learning way to convert MR image to CT image is a viable method and can be further used in dose calculation.

A systematic literature review: deep learning techniques for synthetic medical image generation and their applications in radiotherapy

The aim of this systematic review is to determine whether Deep Learning (DL) algorithms can provide a clinically feasible alternative to classic algorithms for synthetic Computer Tomography (sCT). The following categories are presented in this study: ∙ MR-based treatment planning and synthetic CT generation techniques. ∙ Generation of synthetic CT images based on Cone Beam CT images. ∙ Low-dose CT to High-dose CT generation. ∙ Attenuation correction for PET images. To perform appropriate database searches, we reviewed journal articles published between January 2018 and June 2023. Current methodology, study strategies, and results with relevant clinical applications were analyzed as we outlined the state-of-the-art of deep learning based approaches to inter-modality and intra-modality image synthesis. This was accomplished by contrasting the provided methodologies with traditional research approaches. The key contributions of each category were highlighted, specific challenges were identified, and accomplishments were summarized. As a final step, the statistics of all the cited works from various aspects were analyzed, which revealed that DL-based sCTs have achieved considerable popularity, while also showing the potential of this technology. In order to assess the clinical readiness of the presented methods, we examined the current status of DL-based sCT generation.

CT-based generation of synthetic-pseudo MR images with different weightings for human knee

Synthetic MR images are generated for their high soft-tissue contrast avoiding the discomfort by the long acquisition time and placing claustrophobic patients in the MR scanner's confined space. The aim of this study is to generate synthetic pseudo-MR images from a real CT image for the knee region in vivo. 19 healthy subjects were scanned for model training, while 13 other healthy subjects were imaged for testing. The approach used in this work is novel such that the registration was performed between the MR and CT images, and the femur bone, patella, and the surrounding soft tissue were segmented on the CT image. The tissue type was mapped to its corresponding mean and standard deviation values of the CT# of a window moving on each pixel in the reconstructed CT images, which enabled the remapping of the tissue to its MRI intrinsic parameters: T1, T2, and proton density (ρ). To generate the synthetic MR image of a knee slice, a classic spin-echo sequence was simulated using proper intrinsic and contrast parameters. Results showed that the synthetic MR images were comparable to the real images acquired with the same TE and TR values, and the average slope between them (for all knee segments) was 0.98, while the average percentage root mean square difference (PRD) was 25.7%. In conclusion, this study has shown the feasibility and validity of accurately generating synthetic MR images of the knee region in vivo with different weightings from a single real CT image.

The Use of MR-Guided Radiation Therapy for Head and Neck Cancer and Recommended Reporting Guidance

Although magnetic resonance imaging (MRI) has become standard diagnostic workup for head and neck malignancies and is currently recommended by most radiological societies for pharyngeal and oral carcinomas, its utilization in radiotherapy has been heterogeneous during the last decades. However, few would argue that implementing MRI for annotation of target volumes and organs at risk provides several advantages, so that implementation of the modality for this purpose is widely accepted. Today, the term MR-guidance has received a much broader meaning, including MRI for adaptive treatments, MR-gating and tracking during radiotherapy application, MR-features as biomarkers and finally MR-only workflows. First studies on treatment of head and neck cancer on commercially available dedicated hybrid-platforms (MR-linacs), with distinct common features but also differences amongst them, have also been recently reported, as well as "biological adaptation" based on evaluation of early treatment response via functional MRI-sequences such as diffusion weighted ones. Yet, all of these approaches towards head and neck treatment remain at their infancy, especially when compared to other radiotherapy indications. Moreover, the lack of standardization for reporting MR-guided radiotherapy is a major obstacle both to further progress in the field and to conduct and compare clinical trials. Goals of this article is to present and explain all different aspects of MR-guidance for radiotherapy of head and neck cancer, summarize evidence, as well as possible advantages and challenges of the method and finally provide a comprehensive reporting guidance for use in clinical routine and trials.

Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis

BACKGROUND

Synthetic computed tomography (sCT) has been proposed and increasingly clinically adopted to enable magnetic resonance imaging (MRI)-based radiotherapy. Deep learning (DL) has recently demonstrated the ability to generate accurate sCT from fixed MRI acquisitions. However, MRI protocols may change over time or differ between centres resulting in low-quality sCT due to poor model generalisation.

PURPOSE

investigating domain randomisation (DR) to increase the generalisation of a DL model for brain sCT generation.

METHODS

CT and corresponding T1-weighted MRI with/without contrast, T2-weighted, and FLAIR MRI from 95 patients undergoing RT were collected, considering FLAIR the unseen sequence where to investigate generalisation. A "Baseline" generative adversarial network was trained with/without the FLAIR sequence to test how a model performs without DR. Image similarity and accuracy of sCT-based dose plans were assessed against CT to select the best-performing DR approach against the Baseline.

RESULTS

The Baseline model had the poorest performance on FLAIR, with mean absolute error (MAE) = 106 ± 20.7 HU (mean ±σ). Performance on FLAIR significantly improved for the DR model with MAE = 99.0 ± 14.9 HU, but still inferior to the performance of the Baseline+FLAIR model (MAE = 72.6 ± 10.1 HU). Similarly, an improvement in γ-pass rate was obtained for DR vs Baseline.

CONCLUSION

DR improved image similarity and dose accuracy on the unseen sequence compared to training only on acquired MRI. DR makes the model more robust, reducing the need for re-training when applying a model on sequences unseen and unavailable for retraining.

Feasibility study of adaptive radiotherapy for esophageal cancer using artificial intelligence autosegmentation based on MR-Linac

Objective

We proposed a scheme for automatic patient-specific segmentation in Magnetic Resonance (MR)-guided online adaptive radiotherapy based on daily updated, small-sample deep learning models to address the time-consuming delineation of the region of interest (ROI) in the adapt-to-shape (ATS) workflow. Additionally, we verified its feasibility in adaptive radiation therapy for esophageal cancer (EC).

Methods

Nine patients with EC who were treated with an MR-Linac were prospectively enrolled. The actual adapt-to-position (ATP) workflow and simulated ATS workflow were performed, the latter of which was embedded with a deep learning autosegmentation (AS) model. The first three treatment fractions of the manual delineations were used as input data to predict the next fraction segmentation, which was modified and then used as training data to update the model daily, forming a cyclic training process. Then, the system was validated in terms of delineation accuracy, time, and dosimetric benefit. Additionally, the air cavity in the esophagus and sternum were added to the ATS workflow (producing ATS+), and the dosimetric variations were assessed.

Results

The mean AS time was 1.40 [1.10-1.78 min]. The Dice similarity coefficient (DSC) of the AS model gradually approached 1; after four training sessions, the DSCs of all ROIs reached a mean value of 0.9 or more. Furthermore, the planning target volume (PTV) of the ATS plan showed a smaller heterogeneity index than that of the ATP plan. Additionally, V5 and V10 in the lungs and heart were greater in the ATS+ group than in the ATS group.

Conclusion

The accuracy and speed of artificial intelligence-based AS in the ATS workflow met the clinical radiation therapy needs of EC. This allowed the ATS workflow to achieve a similar speed to the ATP workflow while maintaining its dosimetric advantage. Fast and precise online ATS treatment ensured an adequate dose to the PTV while reducing the dose to the heart and lungs.

Segmentation of multiple Organs-at-Risk associated with brain tumors based on coarse-to-fine stratified networks

BACKGROUND

Delineation of Organs-at-Risks (OARs) is an important step in radiotherapy treatment planning. As manual delineation is time-consuming, labor-intensive and affected by inter- and intra-observer variability, a robust and efficient automatic segmentation algorithm is highly desirable for improving the efficiency and repeatability of OAR delineation.

PURPOSE

Automatic segmentation of OARs in medical images is challenged by low contrast, various shapes and imbalanced sizes of different organs. We aim to overcome these challenges and develop a high-performance method for automatic segmentation of 10 OARs required in radiotherapy planning for brain tumors.

METHODS

A novel two-stage segmentation framework is proposed, where a coarse and simultaneous localization of all the target organs is obtained in the first stage, and a fine segmentation is achieved for each organ, respectively, in the second stage. To deal with organs with various sizes and shapes, a stratified segmentation strategy is proposed, where a High- and Low-Resolution Residual Network (HLRNet) that consists of a multiresolution branch and a high-resolution branch is introduced to segment medium-sized organs, and a High-Resolution Residual Network (HRRNet) is used to segment small organs. In addition, a label fusion strategy is proposed to better deal with symmetric pairs of organs like the left and right cochleas and lacrimal glands.

RESULTS

Our method was validated on the dataset of MICCAI ABCs 2020 challenge for OAR segmentation. It obtained an average Dice of 75.8% for 10 OARs, and significantly outperformed several state-of-the-art models including nnU-Net (71.6%) and FocusNet (72.4%). Our proposed HLRNet and HRRNet improved the segmentation accuracy for medium-sized and small organs, respectively. The label fusion strategy led to higher accuracy for symmetric pairs of organs.

CONCLUSIONS

Our proposed method is effective for the segmentation of OARs of brain tumors, with a better performance than existing methods, especially on medium-sized and small organs. It has a potential for improving the efficiency of radiotherapy planning with high segmentation accuracy.

Dose accumulation for MR-guided adaptive radiotherapy: From practical considerations to state-of-the-art clinical implementation

MRI-linear accelerator (MR-linac) devices have been introduced into clinical practice in recent years and have enabled MR-guided adaptive radiation therapy (MRgART). However, by accounting for anatomical changes throughout radiation therapy (RT) and delivering different treatment plans at each fraction, adaptive radiation therapy (ART) highlights several challenges in terms of calculating the total delivered dose. Dose accumulation strategies-which typically involve deformable image registration between planning images, deformable dose mapping, and voxel-wise dose summation-can be employed for ART to estimate the delivered dose. In MRgART, plan adaptation on MRI instead of CT necessitates additional considerations in the dose accumulation process because MRI pixel values do not contain the quantitative information used for dose calculation. In this review, we discuss considerations for dose accumulation specific to MRgART and in relation to current MR-linac clinical workflows. We present a general dose accumulation framework for MRgART and discuss relevant quality assurance criteria. Finally, we highlight the clinical importance of dose accumulation in the ART era as well as the possible ways in which dose accumulation can transform clinical practice and improve our ability to deliver personalized RT.

Synthetic computed tomography generation for abdominal adaptive radiotherapy using low-field magnetic resonance imaging

Background and Purpose

Magnetic Resonance guided Radiotherapy (MRgRT) still needs the acquisition of Computed Tomography (CT) images and co-registration between CT and Magnetic Resonance Imaging (MRI). The generation of synthetic CT (sCT) images from the MR data can overcome this limitation. In this study we aim to propose a Deep Learning (DL) based approach for sCT image generation for abdominal Radiotherapy using low field MR images.

Materials and methods

CT and MR images were collected from 76 patients treated on abdominal sites. U-Net and conditional Generative Adversarial Network (cGAN) architectures were used to generate sCT images. Additionally, sCT images composed of only six bulk densities were generated with the aim of having a Simplified sCT.Radiotherapy plans calculated using the generated images were compared to the original plan in terms of gamma pass rate and Dose Volume Histogram (DVH) parameters.

Results

sCT images were generated in 2 s and 2.5 s with U-Net and cGAN architectures respectively.Gamma pass rates for 2%/2mm and 3%/3mm criteria were 91% and 95% respectively. Dose differences within 1% for DVH parameters on the target volume and organs at risk were obtained.

Conclusion

U-Net and cGAN architectures are able to generate abdominal sCT images fast and accurately from low field MRI.

Emergence of MR-Linac in Radiation Oncology: Successes and Challenges of Riding on the MRgRT Bandwagon

The special issue of JCM on “Advances of MRI in Radiation Oncology” provides a unique forum for scientific literature related to MR imaging in radiation oncology. This issue covered many aspects, such as MR technology, motion management, economics, soft-tissue–air interface issues, and disease sites such as the pancreas, spine, sarcoma, prostate, head and neck, and rectum from both camps—the Unity and MRIdian systems. This paper provides additional information on the success and challenges of the two systems. A challenging aspect of this technology is low throughput and the monumental task of education and training that hinders its use for the majority of therapy centers. Additionally, the cost of this technology is too high for most institutions, and hence widespread use is still limited. This article highlights some of the difficulties and how to resolve them.

Improving the clinical workflow of a MR-Linac by dosimetric evaluation of synthetic CT

Adaptive radiotherapy performed on the daily magnetic resonance imaging (MRI) is an option to improve the treatment quality. In the adapt-to-shape workflow of 1.5-T MR-Linac, the contours of structures are adjusted on the basis of patient daily MRI, and the adapted plan is recalculated on the MRI-based synthetic computed tomography (syCT) generated by bulk density assignment. Because dosimetric accuracy of this strategy is a priority and requires evaluation, this study aims to explore the usefulness of adding an assessment of dosimetric errors associated with recalculation on syCT to the clinical workflow. Sixty-one patients, with various tumor sites, treated using a 1.5-T MR-Linac were included in this study. In Monaco V5.4, the target and organs at risk (OARs) were contoured, and a reference CT plan that contains information about the outlined contours, their average electron density (ED), and the priority of ED assignment was generated. To evaluate the dosimetric error of syCT caused by the inherent approximation within bulk density assignment, the reference CT plan was recalculated on the syCT obtained from the reference CT by forcing all contoured structures to their mean ED defined on the reference plan. The dose–volume histogram (DVH) and dose distribution of the CT and syCT plan were compared. The causes of dosimetric discrepancies were investigated, and the reference plan was reworked to minimize errors if needed. For 54 patients, gamma analysis of the dose distribution on syCT and CT show a median pass rate of 99.7% and 98.5% with the criteria of 3%/3 mm and 2%/2 mm, respectively. DVH difference of targets and OARs remained less than 1.5% or 1 Gy. For the remaining patients, factors (i.e., inappropriate ED assignments) influenced the dosimetric agreement of the syCT vs. CT reference DVH by up to 21%. The causes of the errors were promptly identified, and the DVH dosimetry was realigned except for two lung treatments for which a significant discrepancy remained. The recalculation on the syCT obtained from the planning CT is a powerful tool to assess and decrease the minimal error committed during the adaptive plan on the MRI-based syCT.

Artificial intelligence in multi-parametric magnetic resonance imaging: A review

Multi-parametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availability of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI. This article is protected by copyright. All rights reserved.

Synthesis of magnetic resonance images from computed tomography data using convolutional neural network with contextual loss function

BACKGROUND

Magnetic resonance imaging (MRI) images synthesized from computed tomography (CT) data can provide more detailed information on pathological structures than that of CT data alone; thus, the synthesis of MRI has received increased attention especially in medical scenarios where only CT images are available. A novel convolutional neural network (CNN) combined with a contextual loss function was proposed for synthesis of T1- and T2-weighted images (T1WI and T2WI) from CT data.

METHODS

A total of 5,053 and 5,081 slices of T1WI and T2WI, respectively were selected for the dataset of CT and MRI image pairs. Affine registration, image denoising, and contrast enhancement were done on the aforementioned multi-modality medical image dataset comprising T1WI, T2WI, and CT images of the brain. A deep CNN was then proposed by modifying the ResNet structure to constitute the encoder and decoder of U-Net, called double ResNet-U-Net (DRUNet). Three different loss functions were utilized to optimize the parameters of the proposed models: mean squared error (MSE) loss, binary crossentropy (BCE) loss, and contextual loss. Statistical analysis of the independent-sample t-test was conducted by comparing DRUNets with different loss functions and different network layers.

RESULTS

DRUNet-101 with contextual loss yielded higher values of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Tenengrad function (i.e., 34.25±2.06, 0.97±0.03, and 17.03±2.75 for T1WI and 33.50±1.08, 0.98±0.05, and 19.76±3.54 for T2WI respectively). The results were statistically significant at P<0.001 with a narrow confidence interval of difference, indicating the superiority of DRUNet-101 with contextual loss. In addition, both image zooming and difference maps presented for the final synthetic MR images visually reflected the robustness of DRUNet-101 with contextual loss. The visualization of convolution filters and feature maps showed that the proposed model can generate synthetic MR images with high-frequency information.

CONCLUSIONS

The results demonstrated that DRUNet-101 with contextual loss function provided better high-frequency information in synthetic MR images compared with the other two functions. The proposed DRUNet model has a distinct advantage over previous models in terms of PSNR, SSIM, and Tenengrad score. Overall, DRUNet-101 with contextual loss is recommended for synthesizing MR images from CT scans.

Generation of Synthetic-Pseudo MR Images from Real CT Images

This study aimed to generate synthetic MR images from real CT images. CT# mean and standard deviation of a moving window across every pixel in the reconstructed CT images were mapped to their corresponding tissue-mimicking types. Identification of the tissue enabled remapping it to its corresponding intrinsic parameters: T1, T2, and proton density (ρ). Lastly, synthetic weighted MR images of a selected slice were generated by simulating a spin-echo sequence using the intrinsic parameters and proper contrast parameters (TE and TR). Experiments were performed on a 3D multimodality abdominal phantom and on human knees at different TE and TR parameters to confirm the clinical effectiveness of the approach. Results demonstrated the validity of the approach of generating synthetic MR images at different weightings using only CT images and the three predefined mapping functions. The slope of the fitting line and percentage root-mean-square difference (PRD) between real and synthetic image vector representations were (0.73, 10%), (0.9, 18%), and (0.2, 8.7%) for T1-, T2-, and ρ-weighted images of the phantom, respectively. The slope and PRD for human knee images, on average, were 0.89% and 18.8%, respectively. The generated MR images provide valuable guidance for physicians with regard to deciding whether acquiring real MR images is crucial.

Pseudo computed tomography image generation from brain magnetic resonance image using integration of PCA & DCNN-UNET: A comparative analysis

MRI-Only Radiation (RT) now avoids some of the issues associated with employing Computed Tomography(CT) in RT chains, such as MRI registration to a separate CT, excess dosage administration, and the cost of recurrent imaging. The fact that MRI signal intensities are unrelated to the biological tissue’s attenuation coefficient poses a problem. This raises workloads, creates uncertainty as a result of the required inter-modality image registrations, and exposes patients to needless radiation. While using only MRI would be preferable, a method for estimating a pseudo-CT (pCT)or synthetic-CT(sCT) for producing electron density maps and patient positioning reference images is required. As Deep Learning(DL) is revolutionized in so many fields these days, an effective and accurate model is required for generating pCT from MRI. So, this paper depicts an efficient DL model in which the following are the stages: a) Data Acquisition where CT and MRI images are collected b) preprocessing these to avoid the anomalies and noises using techniques like outlier elimination, data smoothening and data normalizing c) feature extraction and selection using Principal Component Analysis (PCA) & regression method d) generating pCT from MRI using Deep Convolutional Neural Network and UNET (DCNN-UNET). We here compare both feature extraction (PCA) and classification model (DCNN-UNET) with other methods such as Discrete Wavelet Tranform(DWT), Independent Component Analysis(ICA), Fourier Transform and VGG16, ResNet, AlexNet, DenseNet, CNN (Convolutional Neural Network)respectively. The performance measures used to evaluate these models are Dice Coefficient(DC), Structured Similarity Index Measure(SSIM), Mean Absolute Error(MAE), Mean Squared Error(MSE), Accuracy, Computation Time in which our proposed system outperforms better with 0.94±0.02 over other state-of-art models.

Multi parametric magnetic resonance imaging for radiation treatment planning

In recent years, multi-parametric magnetic resonance imaging (MpMRI) has played a major role in radiation therapy treatment planning. The superior soft tissue contrast, functional or physiological imaging capabilities and the flexibility of site-specific image sequence development has placed MpMRI at the forefront. In this article, the present status of MpMRI for external beam radiation therapy planning is reviewed. Common MpMRI sequences, preprocessing and QA strategies are briefly discussed, and various image registration techniques and strategies are addressed. Image segmentation methods including automatic segmentation and deep learning techniques for organs at risk and target delineation are reviewed. Due to the advancement in MRI guided online adaptive radiotherapy, treatment planning considerations addressing MRI only planning are also discussed. This article is protected by copyright. All rights reserved.

Head and neck cancer patient positioning using synthetic CT data in MRI-only radiation therapy

Purpose

The accuracy and precision of patient positioning is crucial in radiotherapy; however, there are no publications available using synthetic computed tomography (sCT) that evaluate rotations in head and neck (H&N) patients positioning or the effect of translation and rotation combined. The aim of this work was to evaluate the differences between using sCT with the CT for 2D‐ and 3D‐patient positioning in a magnetic resonance imaging (MRI)‐only workflow.

Methods

This study included 14 H&N cancer patients, with generated sCT data (MRI Planner v2.2) and the CT deformably registered to the MRI. Patient positioning was evaluated by comparing sCT against CT data: 3D cone beam CT (CBCT) was registered to the deformed CT (dCT) and sCT in six degrees of freedom (DoF) with a rigid auto‐registration algorithm and bone threshold, and 2D deformed digital reconstructed radiographs (dDRR) and synthetic DRRs (sDRR) were manually registered to orthogonal projections in five DoF by six blinded observers. The difference in displacement in all DoF were calculated for dCT and sCT, as well as for dDRR and sDRR. The interobserver variation was evaluated by separate application of the paired dDRR and sDRR registration matrices to the original coordinates of the planning target volume (PTV) structures and calculation of the Euclidean distance between the corresponding points. The Dice similarity coefficient (DSC) was calculated between dDRR/sDRR‐registered PTVs.

Results

The mean difference in patient positioning using CBCT was <0.7 mm and <0.3° and using orthogonal projections <0.4 mm and <0.2° in all directions. The maximum Euclidean distance was 5.1 mm, the corresponding mean (1SD) Euclidean distance and mean DSC were 3.5 ± 0.7 mm and 0.93, respectively.

Conclusions

This study shows that the sCT‐based patient positioning gives a comparable result with that based on CT images, allowing sCT to replace CT as reference for patient treatment positioning.

Prospective Clinical Feasibility Study for MRI-Only Brain Radiotherapy

OBJECTIVES

MRI-only radiotherapy (RT) provides a workflow to decrease the geometric uncertainty introduced by the image registration process between MRI and CT data and to streamline the RT planning. Despite the recent availability of validated synthetic CT (sCT) methods for the head region, there are no clinical implementations reported for brain tumors. Based on a preceding validation study of sCT, this study aims to investigate MRI-only brain RT through a prospective clinical feasibility study with endpoints for dosimetry and patient setup.

MATERIAL AND METHODS

Twenty-one glioma patients were included. MRI Dixon images were used to generate sCT images using a CE-marked deep learning-based software. RT treatment plans were generated based on MRI delineated anatomical structures and sCT for absorbed dose calculations. CT scans were acquired but strictly used for sCT quality assurance (QA). Prospective QA was performed prior to MRI-only treatment approval, comparing sCT and CT image characteristics and calculated dose distributions. Additional retrospective analysis of patient positioning and dose distribution gamma evaluation was performed.

RESULTS

Twenty out of 21 patients were treated using the MRI-only workflow. A single patient was excluded due to an MRI artifact caused by a hemostatic substance injected near the target during surgery preceding radiotherapy. All other patients fulfilled the acceptance criteria. Dose deviations in target were within ±1% for all patients in the prospective analysis. Retrospective analysis yielded gamma pass rates (2%, 2 mm) above 99%. Patient positioning using CBCT images was within ± 1 mm for registrations with sCT compared to CT.

CONCLUSION

We report a successful clinical study of MRI-only brain radiotherapy, conducted using both prospective and retrospective analysis. Synthetic CT images generated using the CE-marked deep learning-based software were clinically robust based on endpoints for dosimetry and patient positioning.

Phantom assessment of three-dimensional geometric distortion of a dedicated wide-bore MR-simulator for radiotherapy

This study evaluated the machine-dependent three-dimensional geometric distortion images acquired from a 1.5T 700mm-wide bore MR-simulator based on a large geometric accuracy phantom. With the consideration of radiation therapy (RT) application requirements, every sequence was examined in various combinations of acquisition-orientations and receiver-bandwidths with console-integrated distortion correction enabled. Distortion was repeatedly measured over a six-month period. The distortion measured from the images acquired at the beginning of this period was employed to retrospectively correct the distortion in the subsequent acquisitions. Geometric distortion was analyzed within the largest field-of-view allowed. Six sequences were examined for comprehensive distortion analysis - VIBE, SPACE, TSE, FLASH, BLADE and PETRA. Based on optimal acquisition parameters, their diameter-sphere-volumes (DSVs) of CT-comparable geometric fidelity (where 1mm distortion was allowed) were 333.6mm, 315.1mm, 316.0mm, 318.9mm, 306.2mm and 314.5mm respectively. This was a significant increase from 254.0mm, 245.5mm, 228.9mm, 256.6mm, 230.8mm and 254.2mm DSVs respectively, when images were acquired using un-optimized parameters. The longitudinal stability of geometric distortion and the efficacy of retrospective correction of console-corrected images, based on prior distortion measurements, were inspected using VIBE and SPACE. The retrospectively corrected images achieved over 500mm DSVs with 1mm distortion allowed. The median distortion was below 1mm after retrospective correction, proving that obtaining prior distortion map for subsequent retrospective distortion correction is beneficial. The systematic evaluation of distortion using various combinations of sequence-type, acquisition-orientation and receiver-bandwidth in a six-month time span would be a valuable guideline for optimizing sequence for various RT applications.

Synthetic digital reconstructed radiographs for MR-only robotic stereotactic radiation therapy: A proof of concept

PURPOSE

To create synthetic CTs and digital reconstructed radiographs (DRRs) from MR images that allow for fiducial visualization and accurate dose calculation for MR-only radiosurgery.

METHODS

We developed a machine learning model to create synthetic CTs from pelvic MRs for prostate treatments. This model has been previously proven to generate synthetic CTs with accuracy on par or better than alternate methods, such as atlas-based registration. Our dataset consisted of 11 paired CT and conventional MR (T2) images used for previous CyberKnife (Accuray, Inc) radiotherapy treatments. The MR images were pre-processed to mimic the appearance of fiducial-enhancing images. Two models were trained for each parameter case, using a sub-set of the available image pairs, with the remaining images set aside for testing and validation of the model to identify the optimal patch size and number of image pairs used for training. Four models were then trained using the identified parameters and used to generate synthetic CTs, which in turn were used to generate DRRs at angles 45° and 315°, as would be used for a CyberKnife treatment. The synthetic CTs and DRRs were compared visually and using the mean squared error and peak signal-to-noise ratio against the ground-truth images to evaluate their similarity.

RESULTS

The synthetic CTs, as well as the DRRs generated from them, gave similar visualization of the fiducial markers in the prostate as the true counterparts. There was no significant difference found for the fiducial localization for the CTs and DRRs. Across the 8 DRRs analyzed, the mean MSE between the normalized true and synthetic DRRs was 0.66 ± 0.42% and the mean PSNR for this region was 22.9 ± 3.7 dB. For the full CTs, the mean MAE was 72.9 ± 88.1 HU and the mean PSNR was 31.2 ± 2.2 dB.

CONCLUSIONS

Our machine learning-based method provides a proof of concept of a way to generate synthetic CTs and DRRs for accurate dose calculation and fiducial localization for use in radiation treatment of the prostate.

A practical methodology to improve the dosimetric accuracy of MR-based radiotherapy simulation for brain tumors

PURPOSE

To investigate the dosimetric accuracy of synthetic computed tomography (sCT) images generated by a clinically-ready voxel-based MRI simulation package, and to develop a simple and feasible method to improve the accuracy.

METHODS

20 patients with brain tumor were selected to undergo CT and MRI simulation. sCT images were generated by a clinical MRI simulation package. The discrepancy between planning CT and sCT in CT number and body contour were evaluated. To resolve the discrepancies, an sCT specific CT-relative electron density (RED) calibration curve was used, and a layer of pseudo-skin was created on the sCT. The dosimetric impact of these discrepancies, and the improvement brought about by the modifications, were evaluated by a planning study. Volumetric modulated arc therapy (VMAT) treatment plans for each patient were created and optimized on the planning CT, which were then transferred to the original sCT and the modified-sCT for dose re-calculation. Dosimetric comparisons and gamma analysis between the calculated doses in different images were performed.

RESULTS

The average gamma passing rate with 1%/1 mm criteria was only 70.8% for the comparison of dose distribution between planning CT and original sCT. The mean dose difference between the planning CT and the original sCT were -1.2% for PTV D₉₅ and -1.7% for PTV D_max, while the mean dose difference was within 0.7 Gy for all relevant OARs. After applying the modifications on the sCT, the average gamma passing rate was increased to 92.2%. Mean dose difference in PTV D₉₅ and D_max were reduced to -0.1% and -0.3% respectively. The mean dose difference was within 0.2 Gy for all OAR structures and no statistically significant difference were found.

CONCLUSIONS

The modified-sCT demonstrated improved dosimetric agreement with the planning CT. These results indicated the overall dosimetric accuracy and practicality of this improved MR-based treatment planning method.

Deep learning based synthetic-CT generation in radiotherapy and PET: A review

Recently,deep learning (DL)-based methods for the generation of synthetic computed tomography (sCT) have received significant research attention as an alternative to classical ones. We present here a systematic review of these methods by grouping them into three categories, according to their clinical applications: (i) to replace computed tomography in magnetic resonance (MR) based treatment planning, (ii) facilitate cone-beam computed tomography based image-guided adaptive radiotherapy, and (iii) derive attenuation maps for the correction of positron emission tomography. Appropriate database searching was performed on journal articles published between January 2014 and December 2020. The DL methods' key characteristics were extracted from each eligible study, and a comprehensive comparison among network architectures and metrics was reported. A detailed review of each category was given, highlighting essential contributions, identifying specific challenges, and summarizing the achievements. Lastly, the statistics of all the cited works from various aspects were analyzed, revealing the popularity and future trends and the potential of DL-based sCT generation. The current status of DL-based sCT generation was evaluated, assessing the clinical readiness of the presented methods.

Deep learning-based synthetic CT generation for MR-only radiotherapy of prostate cancer patients with 0.35T MRI linear accelerator

PURPOSE

To develop a deep learning model to generate synthetic CT for MR-only radiotherapy of prostate cancer patients treated with 0.35 T MRI linear accelerator.

MATERIALS AND METHODS

A U-NET convolutional neural network was developed to translate 0.35 T TRUFI MRI into electron density map using a novel cost function equalizing the contribution of various tissue types including fat, muscle, bone, and background air in training. The impact of training time, dataset size, image standardization, and data augmentation approaches was also quantified. Mean absolute error (MAE) between synthetic and planning CTs was calculated to measure the goodness of the model.

RESULTS

With 20 patients in training, our U-NET model has the potential to generate synthetic CT with a MAE of about 29.68 ± 4.41, 16.34 ± 2.67, 23.36 ± 2.85, and 105.90 ± 22.80 HU over the entire body, fat, muscle, and bone tissues, respectively. As expected, we found that the number of patients used for training and MAE are nonlinearly correlated. Data augmentation and our proposed loss function were effective to improve MAE by ~9% and ~18% in bony voxels, respectively. Increasing the training time and image standardization did not improve the accuracy of the model.

CONCLUSION

A U-NET model has been developed and tested numerically to generate synthetic CT from 0.35T TRUFI MRI for MR-only radiotherapy of prostate cancer patients. Dosimetric evaluation using a large and independent dataset warrants the validity of the proposed model and the actual number of patients needed for the safe usage of the model in routine clinical workflow.

Effects of MR imaging time reduction on substitute CT generation for prostate MRI-only treatment planning

The introduction of MRI linear accelerators (MR-linacs) and the increased use of MR imaging in radiotherapy, requires improved approaches to MRI-only radiotherapy. MRI provides excellent soft tissue visualisation but does not provide any electron density information required for radiotherapy dose calculation, instead MRI is registered to CT images to enable dose calculations. MRI-only radiotherapy eliminates registration errors and reduces patient discomfort, workload and cost. Electron density requirements may be addressed in different ways, from manually applying bulk density corrections, to more computationally intensive methods to produce substitute CT datasets (sCT), requiring additional sequences, increasing overall imaging time. Reducing MR imaging time would reduce potential artefacts from intrafraction motion and patient discomfort. The aim of this study was to assess the impact of reducing MR imaging time on a hybrid atlas-voxel sCT conversion for prostate MRI-only treatment planning, considering both anatomical and dosimetric parameters. 10 volunteers were scanned on a Siemens Skyra 3T MRI. Sequences included the 3D T2-weighted (T2-w) SPACE sequence used for sCT conversion as previously validated against CT, along with variations to this sequence in repetition time (TR), turbo factor, and combinations of these to reduce the imaging time. All scans were converted to sCT and were compared to the sCT from the original SPACE sequence, evaluating for anatomical changes and dosimetric differences for a standard prostate VMAT plan. Compared to the previously validated T2-w SPACE sequence, scan times were reduced by up to 80%. The external volume and bony anatomy were compared, with all but one sequence meeting a DICE coefficient of 0.9 or better, with the largest variations occurring at the edges of the external body volume. The generated sCT agreed with the gold standard sCT within an isocentre dose of 1% and a gamma pass rate of 99% for a 1%/1 mm gamma tolerance for all but one sequence. This study demonstrates that the MR imaging sequence time was able to be reduced by approximately 80% with similar dosimetric results.

Cone beam CT based validation of neural network generated synthetic CTs for radiotherapy in the head region

PURPOSE

In the past years, many different neural network-based conversion techniques for synthesizing computed tomographys (sCTs) from MR images have been published. While the model's performance can be checked during the training against the test set, test datasets can never represent the whole population. Conversion errors can still occur for special cases, for example, for unusual anatomical situations. Therefore, the performance of sCT conversion needs to be verified on a patient specific level, especially in the absence of a planning CT (pCT). In this study, the capability of cone-beam CTs (CBCTs) for the validation of sCTs generated by a neural network was investigated.

METHODS

41 patients with tumors in the head region were selected. 20 of them were used for model training and 10 for validation. Different implementations of CycleGAN (with/without identity and feature loss) were used to generate sCTs. The pixel (MAE, RMSE, PSNR) and geometric error (DICE, Sensitivity, Specificity) values were reported to identify the best model. VMAT plans were created for the remaining 11 patients on the pCTs. These plans were re-calculated on sCTs and CBCTs. An automatic density overriding method ( C B C T RS ) and a population-based dose calculation method ( C B C T Pop ) were employed for CBCT-based dose calculation. The dose distributions were analysed using 3D global gamma analysis, applying a threshold of 10% with respect to the prescribed dose. Differences in DVH metrics for the PTV and the organs-at-risk were compared among the dose distributions based on pCTs, sCTs, and CBCTs.

RESULTS

The best model was the CycleGAN without identity and feature matching loss. Including the identity loss led to a metric decrease of 10% for DICE and a metric increase of 20-60 HU for MAE. Using the 2%/2 mm gamma criterion and pCT as reference, the mean gamma pass rates were 99.0  ±  0.4% for sCTs. Mean gamma pass rate values comparing pCT and CBCT were 99.0  ±  0.8% and 99.1  ±  0.8% for the C B C T RS and C B C T Pop , respectively. The mean gamma pass rates comparing sCT and CBCT resulted in 98.4  ±  1.6% and 99.2  ±  0.6% for C B C T RS and C B C T Pop , respectively. The differences between the gamma-pass-rates of the sCT and two CBCT-based methods were not significant. The majority of deviations of the investigated DVH metrices between sCTs and CBCTs were within 2%.

CONCLUSION

The dosimetric results demonstrate good agreement between sCT, CBCT, and pCT based calculations. A properly applied CBCT conversion method can serve as a tool for quality assurance procedures in an MR only radiotherapy workflow for head patients. Dosimetric deviations of DVH metrics between sCT and CBCTs of larger than 2% should be followed up. A systematic shift of approximately 1% should be taken into account when using the C B C T RS approach in an MR only workflow.

Technical Note: End-to-end verification of an MR-Linac using a dynamic motion phantom

PURPOSE

MR-Linac integrates an MRI scanner and a linear accelerator to provide adaptive radiation treatment. Superior tissue contrast and real-time imaging can give the clinicians confidence to reduce the margins of the planning target volume (PTV). The purpose of this study was to verify the dosimetric accuracy of an MR-Linac system in treating a moving target and assess the error with different motion patterns and adaptation methods.

METHODS

We performed an end-to-end test for Elekta Unity (Elekta) using the 4D Dynamic Thorax Phantom (CIRS MRgRT 008Z), comparing the measured and planned dose. The moving phantom had four measurement locations in the tumor, liver, kidney, and spinal cord regions with a PTW30013 ion chamber. For seven different motion patterns, we first acquired simulation CT using a slow-scanning protocol, based on which we generated reference plans. The treatment technique was the standard intensity-modulated radiation therapy (IMRT). We tested both adaptation workflows: the Adapt-to-Position (ATP) and the Adapt-to-Shape (ATS). The three-dimensional (3D) distribution was measured using a diode array phantom (Sun Nuclear Inc.) to check the dose distribution accuracy as part of the routine QA process. We also performed end-to-end tests on a conventional Linac. Finally, we used SPSS Statistics 22.0 (Inc., Chicago, IL, USA) for data analysis.

RESULTS

All pretreatment reference plans and delivered plans had excellent QA results with a better than 95% passing rate of relative gamma analysis (2%/2 mm criteria). The adaptive planning for MR-Linac produced quality plans. The measured dose in the target agreed with the calculated dose.

CONCLUSIONS

The adaptive treatment on the MR-Linac system investigated met the expected performance with tumor motions. The outline of the target could be visualized and accurately contoured on the 3D MR for online planning. Under different motion patterns, the difference between the measured and calculated dose was acceptable clinically.

Artificial Intelligence in magnetic Resonance guided Radiotherapy: Medical and physical considerations on state of art and future perspectives

Over the last years, technological innovation in Radiotherapy (RT) led to the introduction of Magnetic Resonance-guided RT (MRgRT) systems. Due to the higher soft tissue contrast compared to on-board CT-based systems, MRgRT is expected to significantly improve the treatment in many situations. MRgRT systems may extend the management of inter- and intra-fraction anatomical changes, offering the possibility of online adaptation of the dose distribution according to daily patient anatomy and to directly monitor tumor motion during treatment delivery by means of a continuous cine MR acquisition. Online adaptive treatments require a multidisciplinary and well-trained team, able to perform a series of operations in a safe, precise and fast manner while the patient is waiting on the treatment couch. Artificial Intelligence (AI) is expected to rapidly contribute to MRgRT, primarily by safely and efficiently automatising the various manual operations characterizing online adaptive treatments. Furthermore, AI is finding relevant applications in MRgRT in the fields of image segmentation, synthetic CT reconstruction, automatic (on-line) planning and the development of predictive models based on daily MRI. This review provides a comprehensive overview of the current AI integration in MRgRT from a medical physicist's perspective. Medical physicists are expected to be major actors in solving new tasks and in taking new responsibilities: their traditional role of guardians of the new technology implementation will change with increasing emphasis on the managing of AI tools, processes and advanced systems for imaging and data analysis, gradually replacing many repetitive manual tasks.

Synthetic CT for single-fraction neoadjuvant partial breast irradiation on an MRI-linac

A synthetic computed tomography (sCT) is required for daily plan optimization on an MRI-linac. Yet, only limited information is available on the accuracy of dose calculations on sCT for breast radiotherapy. This work aimed to (1) evaluate dosimetric accuracy of treatment plans for single-fraction neoadjuvant partial breast irradiation (PBI) on a 1.5 T MRI-linac calculated on a) bulk-density sCT mimicking the current MRI-linac workflow and b) deep learning-generated sCT, and (2) investigate the number of bulk-density levels required. For ten breast cancer patients we created three bulk-density sCTs of increasing complexity from the planning-CT, using bulk-density for: (1) body, lungs, and GTV (sCT_BD1); (2) volumes for sCT_BD1plus chest wall and ipsilateral breast (sCT_BD2); (3) volumes for sCT_BD2plus ribs (sCT_BD3); and a deep learning-generated sCT (sCT_DL) from a 1.5 T MRI in supine position. Single-fraction neoadjuvant PBI treatment plans for a 1.5 T MRI-linac were optimized on each sCT and recalculated on the planning-CT. Image evaluation was performed by assessing mean absolute error (MAE) and mean error (ME) in Hounsfield Units (HU) between the sCTs and the planning-CT. Dosimetric evaluation was performed by assessing dose differences, gamma pass rates, and dose-volume histogram (DVH) differences. The following results were obtained (median across patients for sCT_BD1/sCT_BD2/sCT_BD3/sCT_DLrespectively): MAE inside the body contour was 106/104/104/75 HU and ME was 8/9/6/28 HU, mean dose difference in the PTV_GTVwas 0.15/0.00/0.00/-0.07 Gy, median gamma pass rate (2%/2 mm, 10% dose threshold) was 98.9/98.9/98.7/99.4%, and differences in DVH parameters were well below 2% for all structures except for the skin in the sCT_DL. Accurate dose calculations for single-fraction neoadjuvant PBI on an MRI-linac could be performed on both bulk-density and deep learning sCT, facilitating further implementation of MRI-guided radiotherapy for breast cancer. Balancing simplicity and accuracy, sCT_BD2showed the optimal number of bulk-density levels for a bulk-density approach.

Clinical validation of a commercially available deep learning software for synthetic CT generation for brain

BACKGROUND

Most studies on synthetic computed tomography (sCT) generation for brain rely on in-house developed methods. They often focus on performance rather than clinical feasibility. Therefore, the aim of this work was to validate sCT images generated using a commercially available software, based on a convolutional neural network (CNN) algorithm, to enable MRI-only treatment planning for the brain in a clinical setting.

METHODS

This prospective study included 20 patients with brain malignancies of which 14 had areas of resected skull bone due to surgery. A Dixon magnetic resonance (MR) acquisition sequence for sCT generation was added to the clinical brain MR-protocol. The corresponding sCT images were provided by the software MRI Planner (Spectronic Medical AB, Sweden). sCT images were rigidly registered and resampled to CT for each patient. Treatment plans were optimized on CT and recalculated on sCT images for evaluation of dosimetric and geometric endpoints. Further analysis was also performed for the post-surgical cases. Clinical robustness in patient setup verification was assessed by rigidly registering cone beam CT (CBCT) to sCT and CT images, respectively.

RESULTS

All sCT images were successfully generated. Areas of bone resection due to surgery were accurately depicted. Mean absolute error of the sCT images within the body contour for all patients was 62.2 ± 4.1 HU. Average absorbed dose differences were below 0.2% for parameters evaluated for both targets and organs at risk. Mean pass rate of global gamma (1%/1 mm) for all patients was 100.0 ± 0.0% within PTV and 99.1 ± 0.6% for the full dose distribution. No clinically relevant deviations were found in the CBCT-sCT vs CBCT-CT image registrations. In addition, mean values of voxel-wise patient specific geometric distortion in the Dixon images for sCT generation were below 0.1 mm for soft tissue, and below 0.2 mm for air and bone.

CONCLUSIONS

This work successfully validated a commercially available CNN-based software for sCT generation. Results were comparable for sCT and CT images in both dosimetric and geometric evaluation, for both patients with and without anatomical anomalies. Thus, MRI Planner is feasible to use for radiotherapy treatment planning of brain tumours.

Synthesizing CT images from MR images with deep learning: model generalization for different datasets through transfer learning

PURPOSE

Synthetic CT generation is the focus of many studies, however, only models on data with the same dataset were tested. Therefore, how well the trained model will work for data from different hospitals and MR protocols is still unknown. In this study, we addressed the model generalization problem for the MR-to-CT conversion task.

METHODS

Brain T2 MR and corresponding CT images were collected from one hospital and brain T1-FLAIR, T1-POST MR, and corresponding CT images were collected from another hospital. To investigate the model's generalizability ability, four potential solutions were proposed: source model, target model, combined model, and adapted model. All models were trained using the CycleGAN network. The source model was trained with a source domain dataset from scratch and tested with a target domain dataset. The target model was trained with a target domain dataset and tested with a target domain dataset. The combined model was trained with both source domain and target domain datasets, and tested with the target domain dataset. The adapted model used a transfer learning strategy to train a CycleGAN model with a source domain dataset and retrain the pre-trained model with a target domain dataset. MAE, RMSE, PSNR, and SSIM were used to quantitatively evaluate model performance on a target domain dataset.

RESULTS

The adapted model achieved best quantitative results of 74.56±8.61, 193.18±17.98, 28.30±0.83, and 0.84±0.01 for MAE, RMSE, PSNR, and SSIM using the T1-FLAIR dataset and 74.89±15.64, 195.73±31.29, 27.72±1.43, and 0.83±0.04 for MAE, RMSE, PSNR, and SSIM using the T1-POST dataset. The source model had the poorest performance.

CONCLUSIONS

This work indicates high generalization ability to generate synthetic CT images from small training datasets of MR images using pre-trained CycleGAN. The quantitative results of the test data, including different scanning protocols and different acquisition centers, indicated the proof of this concept.

Synthetic computed tomography data allows for accurate absorbed dose calculations in a magnetic resonance imaging only workflow for head and neck radiotherapy

•

The geometry of the synthetic CT is comparable to the CT in the H&N region.

•

Synthetic CT in the H&N region provides similar absorbed dose calculation as the CT.

•

Absorbed dose calculations in the dental region could benefit from using synthetic CT.

Background and purpose

Few studies on magnetic resonance imaging (MRI) only head and neck radiation treatment planning exist, and none using a generally available software. The aim of this study was to evaluate the accuracy of absorbed dose for head and neck synthetic computed tomography data (sCT) generated by a commercial convolutional neural network-based algorithm.

Materials and methods

For 44 head and neck cancer patients, sCT were generated and the geometry was validated against computed tomography data (CT). The clinical CT based treatment plan was transferred to the sCT and recalculated without re-optimization, and differences in relative absorbed dose were determined for dose-volume-histogram (DVH) parameters and the 3D volume.

Results

For overall body, the results of the geometric validation were (Mean ± 1sd): Mean error −5 ± 10 HU, mean absolute error 67 ± 14 HU, Dice similarity coefficient 0.98 ± 0.05, and Hausdorff distance difference 4.2 ± 1.7 mm. Water equivalent depth difference for region Th1-C7, mid mandible and mid nose were −0.3 ± 3.4, 1.1 ± 2.0 and 0.7 ± 3.8 mm respectively. The maximum mean deviation in absorbed dose for all DVH parameters was 0.30% (0.12 Gy). The absorbed doses were considered equivalent (p-value < 0.001) and the mean 3D gamma passing rate was 99.4 (range: 95.7–99.9%).

Conclusions

The convolutional neural network-based algorithm generates sCT which allows for accurate absorbed dose calculations for MRI-only head and neck radiation treatment planning. The sCT allows for statistically equivalent absorbed dose calculations compared to CT based radiotherapy.

A review on medical imaging synthesis using deep learning and its clinical applications

This paper reviewed the deep learning-based studies for medical imaging synthesis and its clinical application. Specifically, we summarized the recent developments of deep learning-based methods in inter- and intra-modality image synthesis by listing and highlighting the proposed methods, study designs, and reported performances with related clinical applications on representative studies. The challenges among the reviewed studies were then summarized with discussion.

Inter- and intra-fractional stability of rectal gas in pelvic cancer patients during MRIgRT

PURPOSE

Due to the electron return effect (ERE) during magnetic resonance imaging guided radiotherapy (MRIgRT), rectal gas during pelvic treatments can result in hot spots of over-dosage in the rectal wall. Determining the clinical impact of this effect on rectal toxicity requires estimation of the amount and mobility (and stability) of rectal gas during treatment. We therefore investigated the amount of rectal gas and local inter- and intra-fractional changes of rectal gas in pelvic cancer patients.

METHODS

To estimate the volume of gas present at treatment planning, the rectal gas contents in the planning computed tomography (CT) scans of 124 bladder, 70 cervical and 2180 prostate cancer patients were calculated. To estimate inter- and intra-fractional variations in rectal gas, 174 and 131 T2-w MRIs for six cervical and eleven bladder cancer patients were used. These scans were acquired during four scan-sessions (~20-25 min each) at various time-points. Additionally, 258 T2-w MRIs of the first five prostate cancer patients treated using MRIgRT at our center, acquired during each fraction, were analyzed. Rectums were delineated on all scans. The area of gas within the rectum delineations was identified on each MRI slice using thresholding techniques. The area of gas on each slice of the rectum was used to calculate the inter- and intra-fractional group mean, systematic and random variations along the length of the rectum. The cumulative dose perturbation as a result of the gas was estimated. Two approaches were explored: accounting or not accounting for the gas at the start of the scan-session.

RESULTS

Intra-fractional variations in rectal gas are small compared to the absolute volume of rectal gas detected for all patient groups. That is, rectal gas is likely to remain stable for periods of 20-25 min. Larger volumes of gas and larger variations in gas volume were observed in bladder cancer patients compared with cervical and prostate cancer patients. For all patients, local cumulative dose perturbations per beam over an entire treatment in the order of 60 % were estimated when gas had not been accounted for in the daily adaption. The calculated dose perturbation over the whole treatment was dramatically reduced in all patients when accounting for the gas in the daily set-up image.

CONCLUSION

Rectal gas in pelvic cancer patients is likely to remain stable over the course of an MRIgRT fraction, and also likely to reappear in the same location in multiple fractions, and can therefore result in clinically relevant over-dosage in the rectal wall. The over-dosage is reduced when accounting for gas in the daily adaption.

The role of radiomics in prostate cancer radiotherapy

"Radiomics," as it refers to the extraction and analysis of a large number of advanced quantitative radiological features from medical images using high-throughput methods, is perfectly suited as an engine for effectively sifting through the multiple series of prostate images from before, during, and after radiotherapy (RT). Multiparametric (mp)MRI, planning CT, and cone beam CT (CBCT) routinely acquired throughout RT and the radiomics pipeline are developed for extraction of thousands of variables. Radiomics data are in a format that is appropriate for building descriptive and predictive models relating image features to diagnostic, prognostic, or predictive information. Prediction of Gleason score, the histopathologic cancer grade, has been the mainstay of the radiomic efforts in prostate cancer. While Gleason score (GS) is still the best predictor of treatment outcome, there are other novel applications of quantitative imaging that are tailored to RT. In this review, we summarize the radiomics efforts and discuss several promising concepts such as delta-radiomics and radiogenomics for utilizing image features for assessment of the aggressiveness of prostate cancer and its outcome. We also discuss opportunities for quantitative imaging with the advance of instrumentation in MRI-guided therapies.

[Uncertainties in the current concept of radiotherapy planning target volume]

The planning target volume is an essential notion in radiotherapy, that requires a new conceptualization. Indeed, the variability and diversity of the uncertainties involved or improved with the development of the new modern technologies and devices in radiotherapy suggest that random and systematic errors cannot be currently generalized. This article attempts to discuss these various uncertainties and tries to demonstrate that a redefinition of the concept of planning target volume toward its personalization for each patient and the robustness notion are likely an improvement basis to take into account the radiotherapy uncertainties.

Technical Note: Efficient and accurate MRI-only based treatment planning of the prostate using bulk density assignment through atlas-based segmentation

PURPOSE

This study investigates the dosimetric accuracy as well as the robustness of a bulk density assignment approach to magnetic resonance imaging (MRI)-only based treatment planning of the prostate, with bulk density regions automatically identified using atlas-based segmentation (ABS).

METHODS

Twenty prostate radiotherapy patients received planning computed tomography (CT) and MRI scans and were treated with volumetric modulated arc therapy (VMAT). Two bulk densities were set, one for bone and one for soft tissue. The bone contours were created by using ABS followed by manual modification if considered necessary. A range of soft tissue and bone density pairs, between 0.95 and 1.03 g/cm³ with increments of 0.01 for soft tissue, and between 1.15 and 1.65 g/cm³ with increments of 0.05 for bone, were evaluated. Using the density pair giving the lowest dose difference compared to the CT-based dose, dose differences were calculated using both the manually modified bone contours and the bone contours from ABS. Contour overlap measurements between the ABS contours and the manually modified contours were calculated.

RESULTS

The dose comparison shows a very good agreement with the CT when using 0.98 g/cm³ for soft tissue and 1.20 g/cm³ for bone, with a dose difference less than 1 % in average dose in all regions of interest. The mean Dice similarity coefficient for bone was 0.94 and the Mean Distance to Agreement was <1 mm in most cases.

CONCLUSIONS

Using bulk density assignment on MR images with suitable densities for bone and soft tissue results in clinically acceptable dose differences compared to dose calculated on the CT, for both atlas-based and manual bone contours. This demonstrates that an integrated MRI-only pathway utilizing a bulk density assignment for two tissue types is a feasible and robust approach for patients with prostate cancer treated with VMAT.

Characterizing local dose perturbations due to gas cavities in magnetic resonance-guided radiotherapy

PURPOSE

Due to differences in attenuation and the electron return effect (ERE), the presence of gas can increase the risk of toxicity in organs at risk (OAR) during magnetic resonance-guided radiotherapy (MRgRT). Current adaptive MRgRT workflows using density overrides negate gas from the dose calculation, meaning that the effects of ERE around gas are not taken into account. In order to achieve an accurate adaptive MRgRT treatment, we should be able to quickly evaluate whether gas present during treatment causes dose constraint violation during an MRgRT fraction. We propose an analytic method for predicting dose perturbations caused by air cavities in OARs during MRgRT.

METHOD

Ten virtual water phantoms were created: nine containing a centrally located spherical air cavity and a reference phantom without an air cavity. Monte Carlo dose calculations were produced to irradiate the phantoms with a single 7 MV photon beam under the influence of a 1.5 T transverse magnetic field (Monaco 5.19.02 Treatment Panning System (TPS) (Elekta AB, Stockholm, Sweden)). Dose distributions of the phantoms with and without air cavities were compared. We used a spherical coordinate system originating in the center of the cavity to sample the dose distributions and calculate the dose perturbation as a result of the presence of each air cavity, ∆D%(θ,Φ)calc . . Dose effects due to ERE and differences in attenuation due to density changes were considered separately. Least squared analysis was used to fit the calculated dose perturbations to mathematical functions. Effects due to ERE were fit to a modulated sinusoidal function and those due to attenuation differences were fit to a 2D Gaussian function. We used the fits to derive a single equation describing dose perturbations around spherical air cavities as a function of angles, θ, Φ, distance from cavity surface, d, and cavity radius, r. We measured the fitting error by calculating the residual error (RE); the difference between the calculated and fitted dose perturbation.

RESULTS

Both ERE and differences in attenuation contribute toward the total dose effects of air cavities in MRgRT. Whereas ERE dominates close to the surface of the cavities, attenuation effects dominate at distances >0.5 cm from the cavities. We showed that dose effects around a spherical air cavity (≤1 cm from the surface) due to ERE fit a modulated sinusoidal function with mean (RE) ≤-1.4E-5% and root mean square error (rms) (RE) ≤4.1%. Effects due to attenuation differences fit a Gaussian function with mean (RE) ≤0.7% and rms (RE) ≤1.8%. Our general equation, which we verified using multiple sizes of spherical and cylindrical air cavity, fits Monte Carlo simulated data with mean (RE) ≤±0.9% and rms (RE) ≤6.9%.

CONCLUSION

We show that local dose perturbations around unplanned spherical air cavities during MRgRT can be well characterized analytically. We present an equation that can be incorporated into the clinical workflow to allow for fast evaluation of dose effects of unplanned gas. We also envision this method contributing to the clinical implementation of real time adaptive radiotherapy (ART) for MRgRT using MRI planning.

Generation of Pseudo-CT using High-Degree Polynomial Regression on Dual-Contrast Pelvic MRI Data

Increasing interests in using magnetic resonance imaging only in radiation therapy require methods for predicting the computed tomography numbers from MRI data. Here we propose a simple voxel method to generate the pseudo-CT (pCT) image using dual-contrast pelvic MRI data. The method is first trained with the CT data and dual-contrast MRI data (two sets of MRI with different sequences) of multiple patients, where the anatomical structures in the images after deformable image registration are segmented into several regions, and after MRI intensity normalizations a regression analysis is used to determine a two-variable polynomial function for each region to relate a voxel's two MRI intensity values to its CT number. We first evaluate the accuracy via the Hounsfield unit (HU) difference between the pseudo-CT and reference-CT (rCT) images and obtain the average mean absolute error as 40.3 ± 2.9 HU from leave-one-out-cross-validation (LOOCV) across all six patients, which is better than most previous results and comparable to another study using the more complicated atlas-based method. We also perform a dosimetric evaluation of the treatment plans based on pCT and rCT images and find the average passing rate within 2% dose difference to be 95.4% in point-to-point dose comparisons. Therefore, our method shows encouraging results in predicting the CT numbers. This polynomial method needs less computer storage than the interpolation method and can be readily extended to the case of more than two MRI sequences.

Development of a hybrid magnetic resonance/computed tomography-compatible phantom for magnetic resonance guided radiotherapy

The purpose of the present study was to develop a hybrid magnetic resonance/computed tomography (MR/CT)-compatible phantom and tissue-equivalent materials for each MR and CT image. Therefore, the essential requirements necessary for the development of a hybrid MR/CT-compatible phantom were determined and the development process is described. A total of 12 different tissue-equivalent materials for each MR and CT image were developed from chemical components. The uniformity of each sample was calculated. The developed phantom was designed to use 14 plugs that contained various tissue-equivalent materials. Measurement using the developed phantom was performed using a 3.0-T scanner with 32 channels and a Somatom Sensation 64. The maximum percentage difference of the signal intensity (SI) value on MR images after adding K2CO3 was 3.31%. Additionally, the uniformity of each tissue was evaluated by calculating the percent image uniformity (%PIU) of the MR image, which was 82.18 ±1.87% with 83% acceptance, and the average circular-shaped regions of interest (ROIs) on CT images for all samples were within ±5 Hounsfield units (HU). Also, dosimetric evaluation was performed. The percentage differences of each tissue-equivalent sample for average dose ranged from -0.76 to 0.21%. A hybrid MR/CT-compatible phantom for MR and CT was investigated as the first trial in this field of radiation oncology and medical physics.

Quantification of fiducial marker visibility for MRI-only prostate radiotherapy simulation

To objectively compare the suitability of MRI pulse sequences and commercially available fiducial markers (FMs) for MRI-only prostate radiotherapy simulation. Most FMs appear as small signal voids in MRI images making them difficult to differentiate from tissue heterogeneities such as calcifications. In this study we use quantitative metrics to objectively evaluate the visibility of FMs in 27 patients and an anthropomorphic phantom with a variety of standard clinical MRI pulse sequences and commercially available FMs. FM visibility was quantified using the local contrast-to-noise-ratio (lCNR), the difference between the 80th and 20th percentile iso-intensity FM volumes (V _fall) and the largest iso-intensity volume that can be distinguished from background: apparent-marker-volume (AMV). A larger lCNR and AMV, and smaller V _fall represents a more easily identifiable FM. The number of non-marker objects visualized by each pulse sequence was calculated using FM-derived template-matching. The FM-based target-registration-error (TRE) between each MRI and the planning-CT image was calculated. Fiducial marker visibility was rated by two medical physicists with over three years of experience examining MRI-only prostate simulation images. The rater's classification accuracy was quantified using the F ₁ score, which is the harmonic mean of the rater's precision and recall. These quantitative metrics and human observer ratings were used to evaluate FM identifiability in images from nine subtypes of T ₁-weighted, T ₂-weighted and gradient echo (GRE) pulse sequences in a 27-patient study. A phantom study was conducted to quantify the visibility of 8 commercially available FMs. In the patient study, the largest mean lCNR and AMV and, smallest normalized V _fall were produced by the 3.0 T multiple-echo GRE pulse sequence (T ₁-VIBE, 2° flip angle, 1.23 ms and 2.45 ms echo-times). This pulse sequence produced no false marker detections and TREs less than 2 mm in the left-right, anterior-posterior and cranial-caudal directions, respectively. Human observers rated the 1.23 ms echo-time GRE images with the best average marker visibility score of 100% and an F ₁ score of 1. In the phantom study, the Gold-Anchor GA-200X-20-B (deployed in a folded configuration) produced the largest sequence averaged lCNR and AMV measurements at 16.1 and 16.7 mm³, respectively. Using quantitative visibility and distinguishability metrics and human observer ratings, the patient study demonstrated that multiple-echo GRE images produced the best gold FM visibility and distinguishability. The phantom study demonstrated that markers manufactured from platinum or iron-doped gold quantitatively produced superior visibility compared to their pure gold counterparts.

Towards a generalised development of synthetic CT images and assessment of their dosimetric accuracy

Background: The interest in generating "synthetic computed tomography (CT) images" from magnetic resonance (MR) images has been increasing over the past years due to advances in MR guidance for radiotherapy. A variety of methods for synthetic CT creation have been developed, from simple bulk density assignment to complex machine learning algorithms.Material and methods: In this study, we present a general method to determine simplistic synthetic CTs and evaluate them according to their dosimetric accuracy. It separates the requirements on the MR image and the associated calculation effort to generate a synthetic CT. To evaluate the significance of the dosimetric accuracy under realistic conditions, clinically common uncertainties including position shifts and Hounsfield lookup table (HLUT) errors were simulated. To illustrate our approach, we first translated CT images from a test set of six pelvic cancer patients to relative electron density (ED) via a clinical HLUT. For each patient, seven simplified ED images (simED) were generated at different levels of complexity, ranging from one to four tissue classes. Then, dose distributions optimised on the reference ED image and the simEDs were compared to each other in terms of gamma pass rates (2 mm/2% criteria) and dose volume metrics.Results: For our test set, best results were obtained for simEDs with four tissue classes representing fat, soft tissue, air, and bone. For this simED, gamma pass rates of 99.95% (range: 99.72-100%) were achieved. The decrease in accuracy from ED simplification was smaller in this case than the influence of the uncertainty scenarios on the reference image, both for gamma pass rates and dose volume metrics.Conclusions: The presented workflow helps to determine the required complexity of synthetic CTs with respect to their dosimetric accuracy. The investigated cases showed potential simplifications, based on which the synthetic CT generation could be faster and more reproducible.

Feasibility of synthetic computed tomography generated with an adversarial network for multi-sequence magnetic resonance-based brain radiotherapy

The aim of this work is to generate synthetic computed tomography (sCT) images from multi-sequence magnetic resonance (MR) images using an adversarial network and to assess the feasibility of sCT-based treatment planning for brain radiotherapy. Datasets for 15 patients with glioblastoma were selected and 580 pairs of CT and MR images were used. T1-weighted, T2-weighted and fluid-attenuated inversion recovery MR sequences were combined to create a three-channel image as input data. A conditional generative adversarial network (cGAN) was trained using image patches. The image quality was evaluated using voxel-wise mean absolute errors (MAEs) of the CT number. For the dosimetric evaluation, 3D conformal radiotherapy (3D-CRT) and volumetric modulated arc therapy (VMAT) plans were generated using the original CT set and recalculated using the sCT images. The isocenter dose and dose-volume parameters were compared for 3D-CRT and VMAT plans, respectively. The equivalent path length was also compared. The mean MAEs for the whole body, soft tissue and bone region were 108.1 ± 24.0, 38.9 ± 10.7 and 366.2 ± 62.0 hounsfield unit, respectively. The dosimetric evaluation revealed no significant difference in the isocenter dose for 3D-CRT plans. The differences in the dose received by 2% of the volume (D2%), D50% and D98% relative to the prescribed dose were <1.0%. The overall equivalent path length was shorter than that for real CT by 0.6 ± 1.9 mm. A treatment planning study using generated sCT detected only small, clinically negligible differences. These findings demonstrated the feasibility of generating sCT images for MR-only radiotherapy from multi-sequence MR images using cGAN.

Virtual 4DCT from 4DMRI for the management of respiratory motion in carbon ion therapy of abdominal tumors

PURPOSE

To evaluate a method for generating virtual four-dimensional computed tomography (4DCT) from four-dimensional magnetic resonance imaging (4DMRI) data in carbon ion radiotherapy with pencil beam scanning for abdominal tumors.

METHODS

Deformable image registration is used to: (a) register each respiratory phase of the 4DMRI to the end-exhale MRI; (b) register the reference end-exhale CT to the end-exhale MRI volume; (c) generate the virtual 4DCT by warping the registered CT according to the obtained deformation fields. A respiratory-gated carbon ion treatment plan is optimized on the planning 4DCT and the corresponding dose distribution is recalculated on the virtual 4DCT. The method was validated on a digital anthropomorphic phantom and tested on eight patients (18 acquisitions). For the phantom, a ground truth dataset was available to assess the method performances from the geometrical and dosimetric standpoints. For the patients, the virtual 4DCT was compared with the planning 4DCT.

RESULTS

In the phantom, the method exhibits a geometrical accuracy within the voxel size and Dose Volume Histograms deviations up to 3.3% for target V_95% (mean dose difference ≤ 0.2% of the prescription dose, gamma pass rate > 98%). For patients, the virtual and the planning 4DCTs show good agreement at end-exhale (3% median D_95% difference), whereas other respiratory phases exhibit moderate motion variability with consequent dose discrepancies, confirming the need for motion mitigation strategies during treatment.

CONCLUSIONS

The virtual 4DCT approach is feasible to evaluate treatment plan robustness against intra- and interfraction motion in carbon ion therapy delivered at the abdominal site.

Magnetic resonance-based computed tomography metal artifact reduction using Bayesian modelling

Metal artifact reduction (MAR) algorithms reduce the errors caused by metal implants in x-ray computed tomography (CT) images and are an important part of error management in radiotherapy. A promising MAR approach is to leverage the information in magnetic resonance (MR) images that can be acquired for organ or tumor delineation. This is however complicated by the ambiguous relationship between CT values and conventional-sequence MR intensities as well as potential co-registration issues. In order to address these issues, this paper proposes a self-tuning Bayesian model for MR-based MAR that combines knowledge of the MR image intensities in local spatial neighborhoods with the information in an initial, corrupted CT reconstructed using filtered back projection. We demonstrate the potential of the resulting model in three widely-used MAR scenarios: image inpainting, sinogram inpainting and model-based iterative reconstruction. Compared to conventional alternatives in a retrospective study on nine head-and-neck patients with CT and T1-weighted MR scans, we find improvements in terms of image quality and quantitative CT value accuracy within each scenario. We conclude that the proposed model provides a versatile way to use the anatomical information in a co-acquired MR scan to boost the performance of MAR algorithms.

Synthetic CT Generation Based on T2 Weighted MRI of Nasopharyngeal Carcinoma (NPC) Using a Deep Convolutional Neural Network (DCNN)

Purpose: There is an emerging interest of applying magnetic resonance imaging (MRI) to radiotherapy (RT) due to its superior soft tissue contrast for accurate target delineation as well as functional information for evaluating treatment response. MRI-based RT planning has great potential to enable dose escalation to tumors while reducing toxicities to surrounding normal tissues in RT treatments of nasopharyngeal carcinoma (NPC). Our study aims to generate synthetic CT from T2-weighted MRI using a deep learning algorithm.

Methods: Thirty-three NPC patients were retrospectively selected for this study with local IRB's approval. All patients underwent clinical CT simulation and 1.5T MRI within the same week in our hospital. Prior to CT/MRI image registration, we had to normalize two different modalities to a similar intensity scale using the histogram matching method. Then CT and T2 weighted MRI were rigidly and deformably registered using intensity-based registration toolbox elastix (version 4.9). A U-net deep learning algorithm with 23 convolutional layers was developed to generate synthetic CT (sCT) using 23 NPC patients' images as the training set. The rest 10 NPC patients were used as the test set (~1/3 of all datasets). Mean absolute error (MAE) and mean error (ME) were calculated to evaluate HU differences between true CT and sCT in bone, soft tissue and overall region.

Results: The proposed U-net algorithm was able to create sCT based on T2-weighted MRI in NPC patients, which took 7 s per patient on average. Compared to true CT, MAE of sCT in all tested patients was 97 ± 13 Hounsfield Unit (HU) in soft tissue, 131 ± 24 HU in overall region, and 357 ± 44 HU in bone, respectively. ME was −48 ± 10 HU in soft tissue, −6 ± 13 HU in overall region, and 247 ± 44 HU in bone, respectively. The majority soft tissue and bone region was reconstructed accurately except the interface between soft tissue and bone and some delicate structures in nasal cavity, where the inaccuracy was induced by imperfect deformable registration. One patient example was shown with almost no difference in dose distribution using true CT vs. sCT in the PTV regions in the sinus area with fine bone structures.

Conclusion: Our study indicates that it is feasible to generate high quality sCT images based on T2-weighted MRI using the deep learning algorithm in patients with nasopharyngeal carcinoma, which may have great clinical potential for MRI-only treatment planning in the future.

On the accuracy of bulk synthetic CT for MR-guided online adaptive radiotherapy

PURPOSE

MR-guided radiotherapy (MRgRT) relies on the daily assignment of a relative electron density (RED) map to allow the fraction specific dose calculation. One approach to assign the RED map consists of segmenting the daily magnetic resonance image into five different density levels and assigning a RED bulk value to each level to generate a synthetic CT (sCT). The aim of this study is to evaluate the dose calculation accuracy of this approach for applications in MRgRT.

METHODS

A planning CT (pCT) was acquired for 26 patients with abdominal and pelvic lesions and segmented in five levels similar to an online approach: air, lung, fat, soft tissue and bone. For each patient, the median RED value was calculated for fat, soft tissue and bone. Two sCTs were generated assigning different bulk values to the segmented levels on pCT: The sCT_ICRU uses the RED values recommended by ICRU46, and the sCT_tailor uses the median patient-specific RED values. The same treatment plan was calculated on two the sCTs and the pCT. The dose calculation accuracy was investigated in terms of gamma analysis and dose volume histogram parameters.

RESULTS

Good agreement was found between dose calculated on sCTs and pCT (gamma passing rate 1%/1 mm equal to 91.2% ± 6.9% for sCT_ICRU and 93.7% ± 5.3% b or sCT_tailor). The mean difference in estimating V95 (PTV) was equal to 0.2% using sCT_tailor and 1.2% using sCT_ICRU, respect to pCT values CONCLUSIONS: The bulk sCT guarantees a high level of dose calculation accuracy also in presence of magnetic field, making this approach suitable to MRgRT. This accuracy can be improved by using patient-specific RED values.