Systematisation of spatial uncertainties for comparison between a MR and a CT-based radiotherapy workflow for prostate treatments

Challenges and opportunities in the development and clinical implementation of artificial intelligence based synthetic computed tomography for magnetic resonance only radiotherapy

Synthetic computed tomography (sCT) generated from magnetic resonance imaging (MRI) can serve as a substitute for planning CT in radiation therapy (RT), thereby removing registration uncertainties associated with multi-modality imaging pairing, reducing costs and patient radiation exposure. CE/FDA-approved sCT solutions are nowadays available for pelvis, brain, and head and neck, while more complex deep learning (DL) algorithms are under investigation for other anatomic sites. The main challenge in achieving a widespread clinical implementation of sCT lies in the absence of consensus on sCT commissioning and quality assurance (QA), resulting in variation of sCT approaches across different hospitals. To address this issue, a group of experts gathered at the ESTRO Physics Workshop 2022 to discuss the integration of sCT solutions into clinics and report the process and its outcomes. This position paper focuses on aspects of sCT development and commissioning, outlining key elements crucial for the safe implementation of an MRI-only RT workflow.

3D Unsupervised deep learning method for magnetic resonance imaging-to-computed tomography synthesis in prostate radiotherapy

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.

Clinical Workflow of Cone Beam Computer Tomography-Based Daily Online Adaptive Radiotherapy with Offline Magnetic Resonance Guidance: The Modular Adaptive Radiotherapy System (MARS)

PURPOSE

The Ethos (Varian Medical Systems) radiotherapy device combines semi-automated anatomy detection and plan generation for cone beam computer tomography (CBCT)-based daily online adaptive radiotherapy (oART). However, CBCT offers less soft tissue contrast than magnetic resonance imaging (MRI). This work aims to present the clinical workflow of CBCT-based oART with shuttle-based offline MR guidance.

METHODS

From February to November 2023, 31 patients underwent radiotherapy on the Ethos (Varian, Palo Alto, CA, USA) system with machine learning (ML)-supported daily oART. Moreover, patients received weekly MRI in treatment position, which was utilized for daily plan adaptation, via a shuttle-based system. Initial and adapted treatment plans were generated using the Ethos treatment planning system. Patient clinical data, fractional session times (MRI + shuttle transport + positioning, adaptation, QA, RT delivery) and plan selection were assessed for all fractions in all patients.

RESULTS

In total, 737 oART fractions were applied and 118 MRIs for offline MR guidance were acquired. Primary sites of tumors were prostate (n = 16), lung (n = 7), cervix (n = 5), bladder (n = 1) and endometrium (n = 2). The treatment was completed in all patients. The median MRI acquisition time including shuttle transport and positioning to initiation of the Ethos adaptive session was 53.6 min (IQR 46.5-63.4). The median total treatment time without MRI was 30.7 min (IQR 24.7-39.2). Separately, median adaptation, plan QA and RT times were 24.3 min (IQR 18.6-32.2), 0.4 min (IQR 0.3-1,0) and 5.3 min (IQR 4.5-6.7), respectively. The adapted plan was chosen over the scheduled plan in 97.7% of cases.

CONCLUSION

This study describes the first workflow to date of a CBCT-based oART combined with a shuttle-based offline approach for MR guidance. The oART duration times reported resemble the range shown by previous publications for first clinical experiences with the Ethos system.

Channel-wise attention enhanced and structural similarity constrained cycleGAN for effective synthetic CT generation from head and neck MRI images

BACKGROUND

Magnetic resonance imaging (MRI) plays an increasingly important role in radiotherapy, enhancing the accuracy of target and organs at risk delineation, but the absence of electron density information limits its further clinical application. Therefore, the aim of this study is to develop and evaluate a novel unsupervised network (cycleSimulationGAN) for unpaired MR-to-CT synthesis.

METHODS

The proposed cycleSimulationGAN in this work integrates contour consistency loss function and channel-wise attention mechanism to synthesize high-quality CT-like images. Specially, the proposed cycleSimulationGAN constrains the structural similarity between the synthetic and input images for better structural retention characteristics. Additionally, we propose to equip a novel channel-wise attention mechanism based on the traditional generator of GAN to enhance the feature representation capability of deep network and extract more effective features. The mean absolute error (MAE) of Hounsfield Units (HU), peak signal-to-noise ratio (PSNR), root-mean-square error (RMSE) and structural similarity index (SSIM) were calculated between synthetic CT (sCT) and ground truth (GT) CT images to quantify the overall sCT performance.

RESULTS

One hundred and sixty nasopharyngeal carcinoma (NPC) patients who underwent volumetric-modulated arc radiotherapy (VMAT) were enrolled in this study. The generated sCT of our method were more consistent with the GT compared with other methods in terms of visual inspection. The average MAE, RMSE, PSNR, and SSIM calculated over twenty patients were 61.88 ± 1.42, 116.85 ± 3.42, 36.23 ± 0.52 and 0.985 ± 0.002 for the proposed method. The four image quality assessment metrics were significantly improved by our approach compared to conventional cycleGAN, the proposed cycleSimulationGAN produces significantly better synthetic results except for SSIM in bone.

CONCLUSIONS

We developed a novel cycleSimulationGAN model that can effectively create sCT images, making them comparable to GT images, which could potentially benefit the MRI-based treatment planning.

"sCT-Feasibility" - a feasibility study for deep learning-based MRI-only brain radiotherapy

BACKGROUND

Radiotherapy (RT) is an important treatment modality for patients with brain malignancies. Traditionally, computed tomography (CT) images are used for RT treatment planning whereas magnetic resonance imaging (MRI) images are used for tumor delineation. Therefore, MRI and CT need to be registered, which is an error prone process. The purpose of this clinical study is to investigate the clinical feasibility of a deep learning-based MRI-only workflow for brain radiotherapy, that eliminates the registration uncertainty through calculation of a synthetic CT (sCT) from MRI data.

METHODS

A total of 54 patients with an indication for radiation treatment of the brain and stereotactic mask immobilization will be recruited. All study patients will receive standard therapy and imaging including both CT and MRI. All patients will receive dedicated RT-MRI scans in treatment position. An sCT will be reconstructed from an acquired MRI DIXON-sequence using a commercially available deep learning solution on which subsequent radiotherapy planning will be performed. Through multiple quality assurance (QA) measures and reviews during the course of the study, the feasibility of an MRI-only workflow and comparative parameters between sCT and standard CT workflow will be investigated holistically. These QA measures include feasibility and quality of image guidance (IGRT) at the linear accelerator using sCT derived digitally reconstructed radiographs in addition to potential dosimetric deviations between the CT and sCT plan. The aim of this clinical study is to establish a brain MRI-only workflow as well as to identify risks and QA mechanisms to ensure a safe integration of deep learning-based sCT into radiotherapy planning and delivery.

DISCUSSION

Compared to CT, MRI offers a superior soft tissue contrast without additional radiation dose to the patients. However, up to now, even though the dosimetrical equivalence of CT and sCT has been shown in several retrospective studies, MRI-only workflows have still not been widely adopted. The present study aims to determine feasibility and safety of deep learning-based MRI-only radiotherapy in a holistic manner incorporating the whole radiotherapy workflow.

TRIAL REGISTRATION

NCT06106997.

Incidental findings and safety events from magnetic resonance imaging simulation for head and neck radiation treatment planning: A single institution experience

Purpose

Having dedicated MRI scanners within radiation oncology departments may present unexpected challenges since radiation oncologists and radiation therapists are generally not trained in this modality and there are potential patient safety concerns. This study retrospectively reviews the incidental findings and safety events that were observed at a single institution during introduction of MRI sim for head and neck radiotherapy planning.

Methods

Consecutive patients from March 1, 2020, to May 31, 2022, who were scheduled for MRI sim after having completed CT simulation for head and neck radiotherapy were included for analysis. Patients first underwent a CT simulation with a thermoplastic mask and in most cases with an intraoral stent. The same setup was then reproduced in the MRI simulator. Safety events were instances where scheduled MRI sims were not completed due to the MRI technologist identifying MRI-incompatible devices or objects at the time of sim. Incidental findings were identified during weekly quality assurance rounds as a joint enterprise of head and neck radiation oncology and neuroradiology. Categorical variables between completed and not completed MRI sims were compared using the Chi-Square test and continuous variables were compared using the Mann-Whitney U test with a p-value of < 0.05 considered to be statistically significant.

Results

148 of 169 MRI sims (88 %) were completed as scheduled and 21 (12 %) were not completed (Table 1). Among the 21 aborted MRI sims, the most common reason was due to safety events flagged by the MRI technologist (n = 8, 38 %) because of the presence of metal or a medical device that was not noted at the time of initial screening by the administrative coordinator. Patients who did not complete MRI sim were more likely to be treated for non-squamous head and neck primary tumor (p = 0.016) and were being treated post-operatively (p < 0.001). CT and MRI sim scans each had 17 incidental findings. CT simulation detected 3 cases of new metastases in lungs, which were outside the scan parameters of MRI sim. MRI sim detected one case of dural venous thrombosis and one case of cervical spine epidural abscess, which were not detected by CT simulation.

Conclusions

Radiation oncology departments with dedicated MRI simulation scanners would benefit from diagnostic radiology review for incidental findings and having therapists with MRI safety credentialing to catch near-miss events.

Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO)

BACKGROUND

It is not unusual to see some parts of tissues are excluded in the field of view of CT simulation images. A typical mitigation is to avoid beams entering the missing body parts at the cost of sub-optimal planning.

METHODS

This study is to solve the problem by developing 3 methods, (1) deep learning (DL) mechanism for missing tissue generation, (2) using patient body outline (PBO) based on surface imaging, and (3) hybrid method combining DL and PBO. The DL model was built upon a Globally and Locally Consistent Image Completion to learn features by Convolutional Neural Networks-based inpainting, based on Generative Adversarial Network. The database used comprised 10,005 CT training slices of 322 lung cancer patients and 166 CT evaluation test slices of 15 patients. CT images were from the publicly available database of the Cancer Imaging Archive. Since existing data were used PBOs were acquired from the CT images. For evaluation, Structural Similarity Index Metric (SSIM), Root Mean Square Error (RMSE) and Peak signal-to-noise ratio (PSNR) were evaluated. For dosimetric validation, dynamic conformal arc plans were made with the ground truth images and images generated by the proposed method. Gamma analysis was conducted at relatively strict criteria of 1%/1 mm (dose difference/distance to agreement) and 2%/2 mm under three dose thresholds of 1%, 10% and 50% of the maximum dose in the plans made on the ground truth image sets.

RESULTS

The average SSIM in generation part only was 0.06 at epoch 100 but reached 0.86 at epoch 1500. Accordingly, the average SSIM in the whole image also improved from 0.86 to 0.97. At epoch 1500, the average values of RMSE and PSNR in the whole image were 7.4 and 30.9, respectively. Gamma analysis showed excellent agreement with the hybrid method (equal to or higher than 96.6% of the mean of pass rates for all scenarios).

CONCLUSIONS

It was first demonstrated that missing tissues in simulation imaging could be generated with high similarity, and dosimetric limitation could be overcome. The benefit of this study can be significantly enlarged when MR-only simulation is considered.

Toward a deep learning-based magnetic resonance imaging only workflow for postimplant dosimetry in I-125 seed brachytherapy for prostate cancer

BACKGROUND AND PURPOSE

The current standard imaging-technique for creating postplans in seed prostate brachytherapy is computed tomography (CT), that is associated with additional radiation exposure and poor soft tissue contrast. To establish a magnetic resonance imaging (MRI) only workflow combining improved tissue contrast and high seed detectability, a deep learning-approach for automatic seed segmentation on MRI-scans was developed.

MATERIAL AND METHODS

Patients treated with I-125 seed brachytherapy received a postplan-CT and a 1.5 T MRI-scan on nominal day 30 after implantation. For MRI-based seed visualization, DIXON-sequences were acquired and deep learning-based quantitative susceptibility maps (QSM) were generated from 3D-gradient-echo-sequences from 20 patients. Seed segmentations created on CT served as ground truth. For automatic seed segmentation on MRI, a 3D nnU-net model was trained using QSM and DIXON, both solely and combined.

RESULTS

Of the implanted seeds 94.8 ± 2.4% were detected with deep learning automatic segmentation entrained on both QSM and DIXON data. Models trained on the individual sequence data-sets performed worse with detection rates of 87.5 ± 2.6% or 88.6 ± 7.5% for QSM and DIXON respectively. The seed centers identified on CT versus QSM and DIXON were on average 1.8 ± 1.3 mm apart. Postimplant dosimetry for evaluation of positioning inaccuracies revealed only small variations of up to 0.4 ± 4.26 Gy in D90 (dose 90% of the prostate receives) between the standard CT-approach and our MRI-only workflow.

CONCLUSION

The proposed deep learning-based MRI-only workflow provided a promisingly accurate and robust seed localization and thus has the potential to compete with current state-of-the-art CT-based postimplant dosimetry in the future.

Bony structure enhanced synthetic CT generation using Dixon sequences for pelvis MR-only radiotherapy

BACKGROUND

MRI-only radiotherapy planning (MROP) is beneficial to patients by avoiding MRI/CT registration errors, simplifying the radiation treatment simulation workflow and reducing exposure to ionizing radiation. MRI is the primary imaging modality for soft tissue delineation. Treatment planning CTs (i.e., CT simulation scan) are redundant if a synthetic CT (sCT) can be generated from the MRI to provide the patient positioning and electron density information. Unsupervised deep learning (DL) models like CycleGAN are widely used in MR-to-sCT conversion, when paired patient CT and MR image datasets are not available for model training. However, compared to supervised DL models, they cannot guarantee anatomic consistency, especially around bone.

PURPOSE

The purpose of this work was to improve the sCT accuracy generated from MRI around bone for MROP.

METHODS

To generate more reliable bony structures on sCT images, we proposed to add bony structure constraints in the unsupervised CycleGAN model's loss function and leverage Dixon constructed fat and in-phase (IP) MR images. Dixon images provide better bone contrast than T2-weighted images as inputs to a modified multi-channel CycleGAN. A private dataset with a total of 31 prostate cancer patients were used for training (20) and testing (11).

RESULTS

We compared model performance with and without bony structure constraints using single- and multi-channel inputs. Among all the models, multi-channel CycleGAN with bony structure constraints had the lowest mean absolute error, both inside the bone and whole body (50.7 and 145.2 HU). This approach also resulted in the highest Dice similarity coefficient (0.88) of all bony structures compared with the planning CT.

CONCLUSION

Modified multi-channel CycleGAN with bony structure constraints, taking Dixon-constructed fat and IP images as inputs, can generate clinically suitable sCT images in both bone and soft tissue. The generated sCT images have the potential to be used for accurate dose calculation and patient positioning in MROP radiation therapy.

Computed tomography synthesis from magnetic resonance imaging using cycle Generative Adversarial Networks with multicenter learning

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.

Comparing adaptation strategies in MRI-guided online adaptive radiotherapy for prostate cancer: Implications for treatment margins

PURPOSE

To quantify the difference in accuracy of adapt-to-position (ATP), adapt-to-rotation (ATR) and adapt-to-shape (ATS) workflows used in MRI-guided online adaptive radiotherapy for prostate carcinoma (PCa) by evaluating the margins required to accommodate intra-fraction motion of the clinical target volumes for prostate (CTVpros), prostate including seminal vesicles (CTVpros + sv) and gross tumor volume (GTV).

MATERIALS AND METHODS

Clinical delineations of the CTVpros, CTVpros + sv and GTV of 24 patients with intermediate- and high-risk PCa, treated using ATS on a 1.5 T MR-Linac, were used for analysis. Delineations were available pre- and during beam-on. To simulate ATP and ATR workflows, we automatically generated the structures associated with these workflows using rigid transformations from the planning-MRI to the daily online MRIs. Clinical GTVs were analyzed as ATR GTVs and only ATP GTVs were simulated. Planning target volumes (PTVs) were generated with isotropic margins ranging 0.0-5.0 mm. The volumetric overlap was calculated between these PTVs and their corresponding clinical delineation on the MRI acquired during beam-on and averaged over all treatment fractions.

RESULTS

The PTV margin required to cover > 95% of the CTVpros was equal (2.5 mm) for all workflows. For the CTVpros + sv, this margin increased to 5.0, 4.0 and 3.5 mm in the ATP, ATR and ATS workflow, respectively. GTV coverage improved from ATP to ATR for margins up to 4.0 mm.

CONCLUSION

ATP, ATR and ATS workflows ensure equal coverage of the CTVpros for the current clinical margins. For the CTVpros + sv, ATS showed optimal performance. GTV coverage improves by additional adaptations to prostate rotations.

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.

Synthetic computed tomography based dose calculation in prostate cancer patients with hip prostheses for magnetic resonance imaging-only radiotherapy

Background and purpose

Metallic hip prostheses cause substantial artefacts in both computed tomography (CT) and magnetic resonance (MR) images used in radiotherapy treatment planning (RTP) for prostate cancer patients. The aim of this study was to evaluate the dose calculation accuracy of a synthetic CT (sCT) generation workflow and the improvement in implant visibility using metal artefact reduction sequences.

Materials and methods

The study included 23 patients with prostate cancer who had hip prostheses, of which 10 patients had bilateral hip implants. An in-house protocol was applied to create sCT images for dose calculation comparison. The study compared prostheses volumes and resulting avoidance sectors against planning target volume (PTV) dose uniformity and organs at risk (OAR) sparing.

Results

Median PTV dose difference between sCT and CT-based dose calculation among all patients was 0.1 % (-0.4 to 0.4%) (median(range)). Bladder and rectum differences (V_50Gy) were 0.2 % (-0.3 to 1.1%) and 0.1 % (-0.9 to 0.5%). The median 3D local gamma pass rate for partial arc cases using a Dixon MR sequence was Γ_20%^2mm/2% = 99.9%. For the bilateral full arc cases, using a metal artefact reconstruction sequence, the pass rate was Γ_20%^2mm/2% = 99.0%.

Conclusions

An in-house protocol for generating sCT images for dose calculation provided clinically feasible dose calculation accuracy for prostate cancer patients with hip implants. PTV median dose difference for uni- and bilateral patients with avoidance sectors remained <0.4%. The Outphase images enhanced implant visibility resulting in smaller avoidance sectors, better OAR sparing, and improved PTV uniformity.

Cone beam computed tomography image guidance within a magnetic resonance imaging-only planning workflow

Background and purpose

Magnetic Resonance Imaging (MRI)-only planning workflows offer many advantages but raises challenges regarding image guidance. The study aimed to assess the viability of MRI to Cone Beam Computed Tomography (CBCT) based image guidance for MRI-only planning treatment workflows.

Materials and methods

An MRI matching training package was developed. Ten radiation therapists, with a range of clinical image guidance experience and experience with MRI, completed the training package prior to matching assessment. The matching assessment was performed on four match regions: prostate gold seed, prostate soft tissue, rectum/anal canal and gynaecological. Each match region consisted of five patients, with three CBCTs per patient, resulting in fifteen CBCTs for each match region. The ten radiation therapists performed the CBCT image matching to CT and to MRI for all regions and recorded the match values.

Results

The median inter-observer variation for MRI-CBCT matching and CT-CBCT matching for all regions were within 2 mm and 1 degree. There was no statistically significant association in the inter-observer variation in mean match values and radiation therapist image guidance experience levels. There was no statistically significant association in inter-observer variation in mean match values for MRI experience levels for prostate soft tissue and gynaecological match regions, while there was a statistically significant difference for prostate gold seed and rectum match regions.

Conclusion

The results of this study support the concept that with focussed training, an MRI to CBCT image guidance approach can be successfully implemented in a clinical planning workflow.

Deep Learning Architecture to Improve Edge Accuracy of Auto-Contouring for Head and Neck Radiotherapy

Deep learning (DL) methods have shown great promise in auto-segmentation problems. However, for head and neck cancer, we show that DL methods fail at the axial edges of the gross tumor volume (GTV) where the segmentation is dependent on information closer to the center of the tumor. These failures may decrease trust and usage of proposed auto-contouring systems. To increase performance at the axial edges, we propose the spatially adjusted recurrent convolution U-Net (SARC U-Net). Our method uses convolutional recurrent neural networks and spatial transformer networks to push information from salient regions out to the axial edges. On average, our model increased the Sørensen-Dice coefficient (DSC) at the axial edges of the GTV by 11% inferiorly and 19.3% superiorly over a baseline 2D U-Net, which has no inherent way to capture information between adjacent slices. Over all slices, our proposed architecture achieved a DSC of 0.613, whereas a 3D and 2D U-Net achieved a DSC of 0.586 and 0.540, respectively. SARC U-Net can increase accuracy at the axial edges of GTV contours while also increasing accuracy over baseline models, creating a more robust contour.

Comprehensive dose evaluation of a Deep Learning based synthetic Computed Tomography algorithm for pelvic Magnetic Resonance-only radiotherapy

BACKGROUND AND PURPOSE

Magnetic Resonance (MR)-only radiotherapy enables the use of MR without the uncertainty of MR-Computed Tomography (CT) registration. This requires a synthetic CT (sCT) for dose calculations, which can be facilitated by a novel Zero Echo Time (ZTE) sequence where bones are visible and images are acquired in 65 seconds. This study evaluated the dose calculation accuracy for pelvic sites of a ZTE-based Deep Learning sCT algorithm developed by GE Healthcare.

MATERIALS AND METHODS

ZTE and CT images were acquired in 56 pelvic radiotherapy patients in the radiotherapy position. A 2D U-net convolutional neural network was trained using pairs of deformably registered CT and ZTE images from 36 patients. In the remaining 20 patients the dosimetric accuracy of the sCT was assessed using cylindrical dummy Planning Target Volumes (PTVs) positioned at four different central axial locations, as well as the clinical treatment plans (for prostate (n=10), rectum (n=4) and anus (n=6) cancers). The sCT was rigidly and deformably registered, the plan recalculated and the doses compared using mean differences and gamma analysis.

RESULTS

Mean dose differences to the PTV D98% were ≤ 0.5% for all dummy PTVs and clinical plans (rigid registration). Mean gamma pass rates at 1%/1 mm were 98.0 ± 0.4% (rigid) and 100.0 ± 0.0% (deformable), 96.5 ± 0.8% and 99.8 ± 0.1%, and 95.4 ± 0.6% and 99.4 ± 0.4% for the clinical prostate, rectum and anus plans respectively.

CONCLUSIONS

A ZTE-based sCT algorithm with high dose accuracy throughout the pelvis has been developed. This suggests the algorithm is sufficiently accurate for MR-only radiotherapy for all pelvic sites.

Generation of synthetic megavoltage CT for MRI-only radiotherapy treatment planning using a 3D deep convolutional neural network

BACKGROUND

Megavoltage computed tomography (MVCT) has been implemented on many radiotherapy treatment machines for on-board anatomical visualization, localization, and adaptive dose calculation. Implementing an MR-only workflow by synthesizing MVCT from magnetic resonance imaging (MRI) would offer numerous advantages for treatment planning and online adaptation.

PURPOSE

In this work, we sought to synthesize MVCT (sMVCT) datasets from MRI using deep learning to demonstrate the feasibility of MRI-MVCT only treatment planning.

METHODS

MVCTs and T1-weighted MRIs for 120 patients treated for head-and-neck cancer were retrospectively acquired and co-registered. A deep neural network based on a fully-convolutional 3D U-Net architecture was implemented to map MRI intensity to MVCT HU. Input to the model were volumetric patches generated from paired MRI and MVCT datasets. The U-Net was initialized with random parameters and trained on a mean absolute error (MAE) objective function. Model accuracy was evaluated on 18 withheld test exams. sMVCTs were compared to respective MVCTs. Intensity-modulated volumetric radiotherapy (IMRT) plans were generated on MVCTs of four different disease sites and compared to plans calculated onto corresponding sMVCTs using the gamma metric and dose-volume-histograms (DVHs).

RESULTS

MAE values between sMVCT and MVCT datasets were 93.3 ± 27.5, 78.2 ± 27.5, and 138.0 ± 43.4 HU for whole body, soft tissue, and bone volumes, respectively. Overall, there was good agreement between sMVCT and MVCT, with bone and air posing the greatest challenges. The retrospective dataset introduced additional deviations due to sinus filling or tumor growth/shrinkage between scans, differences in external contours due to variability in patient positioning, or when immobilization devices were absent from diagnostic MRIs. Dose distributions of IMRT plans evaluated for four test cases showed close agreement between sMVCT and MVCT images when evaluated using DVHs and gamma dose metrics, which averaged to 98.9 ± 1.0% and 96.8 ± 2.6% analyzed at 3%/3 mm and 2%/2 mm, respectively.

CONCLUSIONS

MVCT datasets can be generated from T1-weighted MRI using a 3D deep convolutional neural network with dose calculation on a sample sMVCT in close agreement with the MVCT. These results demonstrate the feasibility of using MRI-derived sMVCT in an MR-only treatment planning workflow.

Rates of MRI simulator utilisation in a tertiary cancer therapy centre

Magnetic resonance imaging (MRI) is increasingly being integrated into the radiation oncology workflow, due to its improved soft tissue contrast without additional exposure to ionising radiation. A review of MRI utilisation according to evidence based departmental guidelines was performed. Guideline utilisation rates were calculated to be 50% (true utilisation rate was 46%) of all new cancer patients treated with adjuvant or curative intent, excluding simple skin and breast cancer patients. Guideline utilisation rates were highest in the lower gastrointestinal and gynaecological subsites, with the lowest being in the upper gastrointestinal and thorax subsites. Head and neck (38% vs 45%) and CNS (46% vs 67%) cancers had the largest discrepancy between true and guideline utilisation rates due to unnamed reasons and non-contemporaneous diagnostic imaging respectively. This report outlines approximate MRI utilisation rates in a tertiary radiation oncology service and may help guide planning for future departments contemplating installation of an MRI simulator.

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.

MR-guided radiotherapy for prostate cancer: state of the art and future perspectives

Advances in radiotherapy technology have increased precision of treatment delivery and in some tumour types, improved cure rates and decreased side effects. A new generation of radiotherapy machines, hybrids of an MRI scanner and a linear accelerator, has the potential to further transform the practice of radiation therapy in some cancers. Facilitating superior image quality and the ability to change the dose distribution online on a daily basis (termed "daily adaptive replanning"), MRI-guided radiotherapy machines allow for new possibilities including increasing dose, for hard to treat cancers, and more selective sparing of healthy tissues, where toxicity reduction is the key priority.These machines have already been used to treat most types of cancer, although experience is still in its infancy. This review summarises the potential and current evidence for MRI-guided radiotherapy, with a predominant focus on prostate cancer. Current advantages and disadvantages are discussed including a realistic appraisal of the likely potential to improve patient outcomes. In addition, horizon scanning for near-term possibilities for research and development will hopefully delineate the potential role for this technology over the next decade.

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.

Proton Therapy for Prostate Cancer: Challenges and Opportunities

Simple Summary

Reported clinical outcomes of proton therapy (PT) for localized prostate cancer are similar to photon-based external beam radiotherapy. Apparently, the dosimetric advantages of PT have yet to be translated to clinical benefits. The suboptimal clinical outcomes of PT might be attributable to inadequate dose prescription, as indicated by the ASCENDE-RT trial. Moreover, uncertainties involved in the treatment planning and delivery processes, as well as technological limitations in PT treatment systems, may lead to discrepancies between planned doses and actual doses delivered to patients. In this article, we reviewed the current status of PT for prostate cancer and discussed different clinical implementations that could potentially improve the clinical outcome of PT for prostate cancer. Various technological advancements under which uncertainties in dose calculations can be minimized, including MRI-guided PT, dual-energy photon-counting CT and high-resolution Monte Carlo-based treatment planning systems, are highlighted.

Abstract

The dosimetric advantages of proton therapy (PT) treatment plans are demonstrably superior to photon-based external beam radiotherapy (EBRT) for localized prostate cancer, but the reported clinical outcomes are similar. This may be due to inadequate dose prescription, especially in high-risk disease, as indicated by the ASCENDE-RT trial. Alternatively, the lack of clinical benefits with PT may be attributable to improper dose delivery, mainly due to geometric and dosimetric uncertainties during treatment planning, as well as delivery procedures that compromise the dose conformity of treatments. Advanced high-precision PT technologies, and treatment planning and beam delivery techniques are being developed to address these uncertainties. For instance, external magnetic resonance imaging (MRI)-guided patient setup rooms are being developed to improve the accuracy of patient positioning for treatment. In-room MRI-guided patient positioning systems are also being investigated to improve the geometric accuracy of PT. Soon, high-dose rate beam delivery systems will shorten beam delivery time to within one breath hold, minimizing the effects of organ motion and patient movements. Dual-energy photon-counting computed tomography and high-resolution Monte Carlo-based treatment planning systems are available to minimize uncertainties in dose planning calculations. Advanced in-room treatment verification tools such as prompt gamma detector systems will be used to verify the depth of PT. Clinical implementation of these new technologies is expected to improve the accuracy and dose conformity of PT in the treatment of localized prostate cancers, and lead to better clinical outcomes. Improvement in dose conformity may also facilitate dose escalation, improving local control and implementation of hypofractionation treatment schemes to improve patient throughput and make PT more cost effective.

Feasibility of Synthetic Computed Tomography Images Generated from Magnetic Resonance Imaging Scans Using Various Deep Learning Methods in the Planning of Radiation Therapy for Prostate Cancer

Simple Summary

MRI-only simulation in radiation therapy (RT) planning has received attention because the CT scan can be omitted. For MRI-only simulation, synthetic CT (sCT) is necessary for the dose calculation. Various methodologies have been suggested for the generation of sCT and, recently, methods using the deep learning approaches are actively investigated. GAN and cycle-consistent GAN (CycGAN) have been mainly tested, however, very limited studies compared the qualities of sCTs generated from these methods or suggested other models for sCT generation. We have compared GAN, CycGAN, and, reference-guided GAN (RgGAN), a new model of deep learning method. We found that the performance in the HU conservation for soft tissue was poorest for GAN. All methods could generate sCTs feasible for VMAT planning with the trend that sCT generated from the RgGAN showed best performance in dosimetric conservation D_98% and D_95% than sCTs from other methodologies.

Abstract

We aimed to evaluate and compare the qualities of synthetic computed tomography (sCT) generated by various deep-learning methods in volumetric modulated arc therapy (VMAT) planning for prostate cancer. Simulation computed tomography (CT) and T2-weighted simulation magnetic resonance image from 113 patients were used in the sCT generation by three deep-learning approaches: generative adversarial network (GAN), cycle-consistent GAN (CycGAN), and reference-guided CycGAN (RgGAN), a new model which performed further adjustment of sCTs generated by CycGAN with available paired images. VMAT plans on the original simulation CT images were recalculated on the sCTs and the dosimetric differences were evaluated. For soft tissue, a significant difference in the mean Hounsfield unites (HUs) was observed between the original CT images and only sCTs from GAN (p = 0.03). The mean relative dose differences for planning target volumes or organs at risk were within 2% among the sCTs from the three deep-learning approaches. The differences in dosimetric parameters for D_98% and D_95% from original CT were lowest in sCT from RgGAN. In conclusion, HU conservation for soft tissue was poorest for GAN. There was the trend that sCT generated from the RgGAN showed best performance in dosimetric conservation D_98% and D_95% than sCTs from other methodologies.

Artificial intelligence-based bone-enhanced magnetic resonance image-a computed tomography/magnetic resonance image composite image modality in nasopharyngeal carcinoma radiotherapy

Background

In the radiotherapy of nasopharyngeal carcinoma (NPC), magnetic resonance imaging (MRI) is widely used to delineate tumor area more accurately. While MRI offers the higher soft tissue contrast, patient positioning and couch correction based on bony image fusion of computed tomography (CT) is also necessary. There is thus an urgent need to obtain a high image contrast between bone and soft tissue to facilitate target delineation and patient positioning for NPC radiotherapy. In this paper, our aim is to develop a novel image conversion between the CT and MRI modalities to obtain clear bone and soft tissue images simultaneously, here called bone-enhanced MRI (BeMRI).

Methods

Thirty-five patients were retrospectively selected for this study. All patients underwent clinical CT simulation and 1.5T MRI within the same week in Shenzhen Second People's Hospital. To synthesize BeMRI, two deep learning networks, U-Net and CycleGAN, were constructed to transform MRI to synthetic CT (sCT) images. Each network used 28 patients' images as the training set, while the remaining 7 patients were used as the test set (~1/5 of all datasets). The bone structure from the sCT was then extracted by the threshold-based method and embedded in the corresponding part of the MRI image to generate the BeMRI image. To evaluate the performance of these networks, the following metrics were applied: mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR).

Results

In our experiments, both deep learning models achieved good performance and were able to effectively extract bone structure from MRI. Specifically, the supervised U-Net model achieved the best results with the lowest overall average MAE of 125.55 (P<0.05) and produced the highest SSIM of 0.89 and PSNR of 23.84. These results indicate that BeMRI can display bone structure in higher contrast than conventional MRI.

Conclusions

A new image modality BeMRI, which is a composite image of CT and MRI, was proposed. With high image contrast of both bone structure and soft tissues, BeMRI will facilitate tumor localization and patient positioning and eliminate the need to frequently check between separate MRI and CT images during NPC radiotherapy.

Robustness and Generalizability of Deep Learning Synthetic Computed Tomography for Positron Emission Tomography/Magnetic Resonance Imaging-Based Radiation Therapy Planning of Patients With Head and Neck Cancer

Purpose

Radiotherapy planning based only on positron emission tomography/magnetic resonance imaging (PET/MRI) lacks computed tomography (CT) information required for dose calculations. In this study, a previously developed deep learning model for creating synthetic CT (sCT) from MRI in patients with head and neck cancer was evaluated in 2 scenarios: (1) using an independent external dataset, and (2) using a local dataset after an update of the model related to scanner software-induced changes to the input MRI.

Methods and Materials

Six patients from an external site and 17 patients from a local cohort were analyzed separately. Each patient underwent a CT and a PET/MRI with a Dixon MRI sequence over either one (external) or 2 (local) bed positions. For the external cohort, a previously developed deep learning model for deriving sCT from Dixon MRI was directly applied. For the local cohort, we adapted the model for an upgraded MRI acquisition using transfer learning and evaluated it in a leave-one-out process. The sCT mean absolute error for each patient was assessed. Radiotherapy dose plans based on sCT and CT were compared by assessing relevant absorbed dose differences in target volumes and organs at risk.

Results

The MAEs were 78 ± 13 HU and 76 ± 12 HU for the external and local cohort, respectively. For the external cohort, absorbed dose differences in target volumes were within ± 2.3% and within ± 1% in 95% of the cases. Differences in organs at risk were <2%. Similar results were obtained for the local cohort.

Conclusions

We have demonstrated a robust performance of a deep learning model for deriving sCT from MRI when applied to an independent external dataset. We updated the model to accommodate a larger axial field of view and software-induced changes to the input MRI. In both scenarios dose calculations based on sCT were similar to those of CT suggesting a robust and reliable 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.

Investigation of the clinical inter-observer bias in prostate fiducial marker image registration between CT and MR images

Background and purpose

Inter-modality image registration between computed tomography (CT) and magnetic resonance (MR) images is associated with systematic uncertainties and the magnitude of these uncertainties is not well documented. The purpose of this study was to investigate the potential uncertainty of gold fiducial marker (GFM) registration for localized prostate cancer and to estimate the inter-observer bias in a clinical setting.

Methods

Four experienced observers registered CT and MR images for 42 prostate cancer patients. Manual GFM identification was followed by a landmark-based registration. The absolute difference between observers in GFM identification and the displacement of the clinical target volume (CTV) was investigated. The CTV center of mass (CoM) vector displacements, DICE-index and Hausdorff distances for the observer registrations were compared against a clinical baseline registration. The time allocated for the manual registrations was compared.

Results

Absolute difference in GFM identification between observers ranged from 0.0 to 3.0 mm. The maximum CTV CoM displacement from the clinical baseline was 3.1 mm. Displacements larger than or equal to 1 mm, 2 mm and 3 mm were 46%, 18% and 4%, respectively. No statistically significant difference was detected between observers in terms of CTV displacement. Median DICE-index and Hausdorff distance for the CTV, with their respective ranges were 0.94 [0.70–1.00] and 2.5 mm [0.7–8.7].

Conclusions

Registration of CT and MR images using GFMs for localized prostate cancer patients was subject to inter-observer bias on an individual patient level. A CTV displacement as large as 3 mm occurred for individual patients. These results show that GFM registration in a clinical setting is associated with uncertainties, which motivates the removal of inter-modality registrations in the radiotherapy workflow and a transition to an MRI-only workflow for localized prostate cancer.

Are cone beam CT image matching skills transferrable from planning CT to planning MRI for MR-only prostate radiotherapy?

Objectives:

Treatment verification for MR-only planning has focused on fiducial marker matching, however, these are difficult to identify on MR. An alternative is using the MRI for soft-tissue matching with cone beam computed tomography images (MR-CBCT). However, therapeutic radiographers have limited experience of MRI. This study aimed to assess transferability of therapeutic radiographers CT-CBCT prostate image matching skills to MR-CBCT image matching.

Methods:

23 therapeutic radiographers with 3 months–5 years’ experience of online daily CT-CBCT soft-tissue matching prostate cancer patients participated. Each observer completed a baseline assessment of 10 CT-CBCT prostate soft-tissue image matches, followed by 10 MR-CBCT prostate soft-tissue image match assessment. A MRI anatomy training intervention was delivered and the 10 MR-CBCT prostate soft-tissue image match assessment was repeated. Limits of agreement were calculated as the disagreement of the observers with mean of all observers.

Results:

Limits of agreement at CT-CBCT baseline were 2.8 mm, 2.8 mm, 0.7 mm (vertical, longitudinal, lateral). MR-CBCT matches prior to training were 3.3 mm, 3.1 mm, 0.9 mm, and after training 2.6 mm, 2.4 mm, 1.1 mm (vertical, longitudinal, lateral). Results show similar limits of agreement across the assessments, and variation reduced following the training intervention.

Conclusion:

This suggests therapeutic radiographers’ prostate CBCT image matching skills are transferrable to a MRI planning scan, since MR-CBCT matching has comparable observer variation to CT-CBCT matching.

Advances in knowledge:

This is the first publication assessing interobserver MR-CBCT prostate soft tissue matching in an MR-only pathway.

Evaluation of a commercial synthetic computed tomography generation solution for magnetic resonance imaging-only radiotherapy

Purpose

To evaluate the Siemens solution generating Synthetic computed tomography (sCT) for magnetic resonance imaging (MRI)‐only radiotherapy (RT).

Method

A retrospective study was conducted on 47 patients treated with external beam RT for brain or prostate cancer who underwent both MRI and CT for treatment planning. sCT images were generated from MRI using automatic bulk densities segmentation. The geometric accuracy of the sCT was assessed by comparing the Hounsfield Units (HU) difference between sCT and CT for bone structures, soft‐tissue, and full body contour. VMAT plans were computed on the CT for treatment preparation and then copied and recalculated with the same monitor units on the sCT using the AcurosXB algorithm. A 1%‐1mm gamma analysis was performed and DVH metrics for the Planning Target Volume (PTV) like the D_mean and the D_98% were compared. In addition, we evaluate the usability of sCT for daily position verification with cone beam computed tomography (CBCT) for 14 prostate patients by comparing sCT/CBCT registration results to CT/CBCT.

Results

Mean HU differences were small except for the skull (207 HU) and right femoral head of four patients where significant aberrations were found. The mean gamma pass rate was 73.2% for the brain and 84.7% for the prostate and D_mean were smaller than 0.5%. Large differences for the D_98% of the prostate group could be correlated to low Dice index of the PTV. The mean difference of translations and rotations were inferior to 3.5 mm and 0.2° in all directions with a major difference in the anterior‐posterior direction.

Conclusion

The performances of the software were shown to be similar to other sCT generation algorithms in terms of HU difference, dose comparison and daily image localization.

Improving generalization in MR-to-CT synthesis in radiotherapy by using an augmented cycle generative adversarial network with unpaired data

PURPOSE

MR-to-CT synthesis is one of the first steps in the establishment of an MRI-only workflow in radiotherapy. Current MR-to-CT synthesis methods in deep learning use unpaired MR and CT training images with a cycle generative adversarial network (CycleGAN) to minimize the effect of misalignment between paired images. However, this approach critically assumes that the underlying interdomain mapping is approximately deterministic and one-to-one. In the current study, we use an Augmented CycleGAN (AugCGAN) model to create a robust model that can be applied to different scanners and sequences using unpaired data.

MATERIALS AND METHODS

This study included T2-weighted MR and CT pelvic images of 38 patients in treatment position from five different centers. The AugCGAN was trained on 2D transverse slices of 19 patients from three different sites. The network was then used to generate synthetic CT (sCT) images of 19 patients from the two other sites. Mean absolute errors (MAEs) for each patient were evaluated between real and synthetic CT images. Original treatment plans of nine patients were recalculated using sCT images to assess the dose distribution in terms of voxel-wise dose difference, gamma, and dose-volume histogram analysis.

RESULTS

The mean MAEs were 59.8 Hounsfield units ( HU ) and 65.8 HU for the first and second test sites, respectively. The maximum dose difference to the target was 1.2 % with a gamma pass rate using the 3%, 3 mm criteria above 99%. The average time required to generate a complete sCT image for a patient on our GPU was 8.5 s.

CONCLUSION

This study suggests that our unpaired approach achieves good performance in generalization with respect to sCT image generation.

Dosimetric Validation of a GAN-Based Pseudo-CT Generation for MRI-Only Stereotactic Brain Radiotherapy

PURPOSE

Stereotactic radiotherapy (SRT) has become widely accepted as a treatment of choice for patients with a small number of brain metastases that are of an acceptable size, allowing for better target dose conformity, resulting in high local control rates and better sparing of organs at risk. An MRI-only workflow could reduce the risk of misalignment between magnetic resonance imaging (MRI) brain studies and computed tomography (CT) scanning for SRT planning, while shortening delays in planning. Given the absence of a calibrated electronic density in MRI, we aimed to assess the equivalence of synthetic CTs generated by a generative adversarial network (GAN) for planning in the brain SRT setting.

METHODS

All patients with available MRIs and treated with intra-cranial SRT for brain metastases from 2014 to 2018 in our institution were included. After co-registration between the diagnostic MRI and the planning CT, a synthetic CT was generated using a 2D-GAN (2D U-Net). Using the initial treatment plan (Pinnacle v9.10, Philips Healthcare), dosimetric comparison was performed using main dose-volume histogram (DVH) endpoints in respect to ICRU 91 guidelines (Dmax, Dmean, D2%, D50%, D98%) as well as local and global gamma analysis with 1%/1 mm, 2%/1 mm and 2%/2 mm criteria and a 10% threshold to the maximum dose. t-test analysis was used for comparison between the two cohorts (initial and synthetic dose maps).

RESULTS

184 patients were included, with 290 treated brain metastases. The mean number of treated lesions per patient was 1 (range 1-6) and the median planning target volume (PTV) was 6.44 cc (range 0.12-45.41). Local and global gamma passing rates (2%/2 mm) were 99.1 CI95% (98.1-99.4) and 99.7 CI95% (99.6-99.7) respectively (CI: confidence interval). DVHs were comparable, with no significant statistical differences regarding ICRU 91's endpoints.

CONCLUSIONS

Our study is the first to compare GAN-generated CT scans from diagnostic brain MRIs with initial CT scans for the planning of brain stereotactic radiotherapy. We found high similarity between the planning CT and the synthetic CT for both the organs at risk and the target volumes. Prospective validation is under investigation at our institution.

Dosimetric evaluation of synthetic CT image generated using a neural network for MR-only brain radiotherapy

PURPOSE AND BACKGROUND

The magnetic resonance (MR)-only radiotherapy workflow is urged by the increasing use of MR image for the identification and delineation of tumors, while a fast generation of synthetic computer tomography (sCT) image from MR image for dose calculation remains one of the key challenges to the workflow. This study aimed to develop a neural network to generate the sCT in brain site and evaluate the dosimetry accuracy.

MATERIALS AND METHODS

A generative adversarial network (GAN) was developed to translate T1-weighted MRI to sCT. First, the "U-net" shaped encoder-decoder network with some image translation-specific modifications was trained to generate sCT, then the discriminator network was adversarially trained to distinguish between synthetic and real CT images. We enrolled 37 brain cancer patients acquiring both CT and MRI for treatment position simulation. Twenty-seven pairs of 2D T1-weighted MR images and rigidly registered CT image were used to train the GAN model, and the remaining 10 pairs were used to evaluate the model performance through the metric of mean absolute error. Furthermore, the clinical Volume Modulated Arc Therapy plan was calculated on both sCT and real CT, followed by gamma analysis and comparison of dose-volume histogram.

RESULTS

On average, only 15 s were needed to generate one sCT from one T1-weighted MRI. The mean absolute error between synthetic and real CT was 60.52 ± 13.32 Housefield Unit over 5-fold cross validation. For dose distribution on sCT and CT, the average pass rates of gamma analysis using the 3%/3 mm and 2%/2 mm criteria were 99.76% and 97.25% over testing patients, respectively. For parameters of dose-volume histogram for both target and organs at risk, no significant differences were found between both plans.

CONCLUSION

The GAN model can generate synthetic CT from one single MRI sequence within seconds, and a state-of-art accuracy of CT number and dosimetry was achieved.

Accuracy of an MR-only workflow for prostate radiotherapy using semi-automatically burned-in fiducial markers

BACKGROUND

The benefit of MR-only workflow compared to current CT-based workflow for prostate radiotherapy is reduction of systematic errors in the radiotherapy chain by 2-3 mm. Nowadays, MRI is used for target delineation while CT is needed for position verification. In MR-only workflows, MRI based synthetic CT (sCT) replaces CT. Intraprostatic fiducial markers (FMs) are used as a surrogate for the position of the prostate improving targeting. However, FMs are not visible on sCT. Therefore, a semi-automatic method for burning-in FMs on sCT was developed. Accuracy of MR-only workflow using semi-automatically burned-in FMs was assessed and compared to CT/MR workflow.

METHODS

Thirty-one prostate cancer patients receiving radiotherapy, underwent an additional MR sequence (mDIXON) to create an sCT for MR-only workflow simulation. Three sources of accuracy in the CT/MR- and MR-only workflow were investigated. To compare image registrations for target delineation, the inter-observer error (IOE) of FM-based CT-to-MR image registrations and soft-tissue-based MR-to-MR image registrations were determined on twenty patients. Secondly, the inter-observer variation of the resulting FM positions was determined on twenty patients. Thirdly, on 26 patients CBCTs were retrospectively registered on sCT with burned-in FMs and compared to CT-CBCT registrations.

RESULTS

Image registration for target delineation shows a three times smaller IOE for MR-only workflow compared to CT/MR workflow. All observers agreed in correctly identifying all FMs for 18 out of 20 patients (90%). The IOE in CC direction of the center of mass (COM) position of the markers was within the CT slice thickness (2.5 mm), the IOE in AP and RL direction were below 1.0 mm and 1.5 mm, respectively. Registrations for IGRT position verification in MR-only workflow compared to CT/MR workflow were equivalent in RL-, CC- and AP-direction, except for a significant difference for random error in rotation.

CONCLUSIONS

MR-only workflow using sCT with burned-in FMs is an improvement compared to the current CT/MR workflow, with a three times smaller inter observer error in CT-MR registration and comparable CBCT registration results between CT and sCT reference scans. Trial registry Medical Research Involving Human Subjects Act (WMO) does apply to this study and was approved by the Medical Ethics review Committee of the Academic Medical Center. Registration number: NL65414.018.18. Date of registration: 21-08-2018.

Cone beam computed tomography for dose calculation quality assurance for magnetic resonance-only radiotherapy

•

Clinical Magnetic Resonance (MR)-only radiotherapy requires a dose quality assurance method.

•

Doses calculated on Cone Beam Computed Tomography (CBCT) were within 2% of MR-only doses calculated using synthetic CT.

•

CBCT with asymmetric dose difference tolerances of [−2%,1%] appears clinically feasible for quality assurance of prostate MR-only radiotherapy.

Background and purpose

Magnetic Resonance (MR)-only prostate radiotherapy using synthetic Computed Tomography (sCT) algorithms with high dose accuracy has been clinically implemented. MR images can suffer from geometric distortions so Quality Assurance (QA) using an independent, geometrically accurate, image could be required. The first-fraction Cone Beam CT (CBCT) has demonstrated potential but has not been evaluated in a clinical MR-only pathway. This study evaluated the clinical use of CBCT for dose accuracy QA of MR-only radiotherapy.

Materials and methods

A total of 49 patients treated with MR-only prostate radiotherapy were divided into two cohorts. Cohort 1 (20 patients) received a back-up CT, whilst Cohort 2 (29 patients) did not. All patients were planned using the sCT and received daily CBCT imaging with MR-CBCT soft-tissue matching. Each CBCT was calibrated using a patient-specific stepwise Hounsfield Units-to-mass density curve. The treatment plan was recalculated on the first-fraction CBCT using the clinically applied soft-tissue match and the doses compared. For Cohort 1 the sCT was rigidly registered to the back-up CT, the plan recalculated and doses compared.

Results

Mean sCT-CBCT dose difference across both cohorts was -0.6±0.1% (standard error of the mean, range −2.3%,2.3%), with 47/49 patients within [-2%,1%]. The sCT-CBCT dose difference was systematically lower than the sCT-CT by -0.7±0.6% (±95% limits of agreement). The mean sCT-CBCT gamma pass rate (2%/2mm) was 96.1±0.4% (85.4%,99.7%).

Conclusions

CBCT-based dose accuracy QA for MR-only radiotherapy appears clinically feasible. There was a small systematic sCT-CBCT dose difference implying asymmetric tolerances of [-2%,1%] would be appropriate.

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.

Development and evaluation of a deep learning based artificial intelligence for automatic identification of gold fiducial markers in an MRI-only prostate radiotherapy workflow

Identification of prostate gold fiducial markers in magnetic resonance imaging (MRI) images is challenging when CT images are not available, due to misclassifications from intra-prostatic calcifications. It is also a time consuming task and automated identification methods have been suggested as an improvement for both objectives. Multi-echo gradient echo (MEGRE) images have been utilized for manual fiducial identification with 100% detection accuracy. The aim is therefore to develop an automatic deep learning based method for fiducial identification in MRI images intended for MRI-only prostate radiotherapy. MEGRE images from 326 prostate cancer patients with fiducials were acquired on a 3T MRI, post-processed with N4 bias correction, and the fiducial center of mass (CoM) was identified. A 9 mm radius sphere was created around the CoM as ground truth. A deep learning HighRes3DNet model for semantic segmentation was trained using image augmentation. The model was applied to 39 MRI-only patients and 3D probability maps for fiducial location and segmentation were produced and spatially smoothed. In each of the three largest probability peaks, a 9 mm radius sphere was defined. Detection sensitivity and geometric accuracy was assessed. To raise awareness of potential false findings a 'BeAware' score was developed, calculated from the total number and quality of the probability peaks. All datasets, annotations and source code used were made publicly available. The detection sensitivity for all fiducials were 97.4%. Thirty-six out of thirty-nine patients had all fiducial markers correctly identified. All three failed patients generated a user notification using the BeAware score. The mean absolute difference between the detected fiducial and ground truth CoM was 0.7 ± 0.9 [0 3.1] mm. A deep learning method for automatic fiducial identification in MRI images was developed and evaluated with state-of-the-art results. The BeAware score has the potential to notify the user regarding patients where the proposed method is uncertain.

Dosimetric effects of adaptive prostate cancer radiotherapy in an MR-linac workflow

BACKGROUND

The purpose was to evaluate the dosimetric effects in prostate cancer treatment caused by anatomical changes occurring during the time frame of adaptive replanning in a magnetic resonance linear accelerator (MR-linac) workflow.

METHODS

Two MR images (MR1 and MR2) were acquired with 30 min apart for each of the 35 patients enrolled in this study. The clinical target volume (CTV) and organs at risk (OARs) were delineated based on MR1. Using a synthetic CT (sCT), ultra-hypofractionated VMAT treatment plans were created for MR1, with three different planning target volume (PTV) margins of 7 mm, 5 mm and 3 mm. The three treatment plans of MR1, were recalculated onto MR2 using its corresponding sCT. The dose distribution of MR2 represented delivered dose to the patient after 30 min of adaptive replanning, omitting motion correction before beam on. MR2 was registered to MR1, using deformable registration. Using the inverse deformation, the structures of MR1 was deformed to fit MR2 and anatomical changes were quantified. For dose distribution comparison the dose distribution of MR2 was warped to the geometry MR1.

RESULTS

The mean center of mass vector offset for the CTV was 1.92 mm [0.13 - 9.79 mm]. Bladder volume increase ranged from 12.4 to 133.0% and rectum volume difference varied between -10.9 and 38.8%. Using the conventional 7 mm planning target volume (PTV) margin the dose reduction to the CTV was 1.1%. Corresponding values for 5 mm and 3 mm PTV margin were 2.0% and 4.2% respectively. The dose to the PTV and OARs also decreased from D1 to D2, for all PTV margins evaluated. Statistically significant difference was found for CTV Dmin between D1 and D2 for the 3 mm PTV margin (p < 0.01).

CONCLUSIONS

A target underdosage caused by anatomical changes occurring during the reported time frame for adaptive replanning MR-linac workflows was found. Volume changes in both bladder and rectum caused large prostate displacements. This indicates the importance of thorough position verification before treatment delivery and that the workflow needs to speed up before introducing margin reduction.

Audit feasibility for geometric distortion in magnetic resonance imaging for radiotherapy

BACKGROUND AND PURPOSE

Magnetic Resonance Imaging (MRI) is increasingly being used in radiotherapy (RT). However, geometric distortions are a known challenge of using MRI in RT. The aim of this study was to demonstrate feasibility of a national audit of MRI geometric distortions. This was achieved by assessing large field of view (FOV) MRI distortions on a number of scanners used clinically for RT.

MATERIALS AND METHODS

MRI scans of a large FOV MRI geometric distortion phantom were acquired on 11 MRI scanners that are used clinically for RT in the UK. The mean and maximum distortions and variance between scanners were reported at different distances from the isocentre.

RESULTS

For a small FOV representing a brain (100-150 mm from isocentre) all distortions were < 2 mm except for the maximum distortion of one scanner. For a large FOV representing a head and neck/pelvis (200-250 mm from isocentre) mean distortions were < 2 mm except for one scanner, maximum distortions were > 10 mm in some cases. The variance between scanners was low and was found to increase with distance from isocentre.

CONCLUSIONS

This study demonstrated feasibility of the technique to be repeated in a country wide geometric distortion audit of all MRI scanners used clinically for RT. Recommendations were made for performing such an audit and how to derive acceptable limits of distortion in such an audit.

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.

MR-PROTECT: Clinical feasibility of a prostate MRI-only radiotherapy treatment workflow and investigation of acceptance criteria

BACKGROUND

Retrospective studies on MRI-only radiotherapy have been presented. Widespread clinical implementations of MRI-only workflows are however limited by the absence of guidelines. The MR-PROTECT trial presents an MRI-only radiotherapy workflow for prostate cancer using a new single sequence strategy. The workflow incorporated the commercial synthetic CT (sCT) generation software MriPlanner™ (Spectronic Medical, Helsingborg, Sweden). Feasibility of the workflow and limits for acceptance criteria were investigated for the suggested workflow with the aim to facilitate future clinical implementations.

METHODS

An MRI-only workflow including imaging, post imaging tasks, treatment plan creation, quality assurance and treatment delivery was created with questionnaires. All tasks were performed in a single MR-sequence geometry, eliminating image registrations. Prospective CT-quality assurance (QA) was performed prior treatment comparing the PTV mean dose between sCT and CT dose-distributions. Retrospective analysis of the MRI-only gold fiducial marker (GFM) identification, DVH- analysis, gamma evaluation and patient set-up verification using GFMs and cone beam CT were performed.

RESULTS

An MRI-only treatment was delivered to 39 out of 40 patients. The excluded patient was too large for the predefined imaging field-of-view. All tasks could successfully be performed for the treated patients. There was a maximum deviation of 1.2% in PTV mean dose was seen in the prospective CT-QA. Retrospective analysis showed a maximum deviation below 2% in the DVH-analysis after correction for rectal gas and gamma pass-rates above 98%. MRI-only patient set-up deviation was below 2 mm for all but one investigated case and a maximum of 2.2 mm deviation in the GFM-identification compared to CT.

CONCLUSIONS

The MR-PROTECT trial shows the feasibility of an MRI-only prostate radiotherapy workflow. A major advantage with the presented workflow is the incorporation of a sCT-generation method with multi-vendor capability. The presented single sequence approach are easily adapted by other clinics and the general implementation procedure can be replicated. The dose deviation and the gamma pass-rate acceptance criteria earlier suggested was achievable, and these limits can thereby be confirmed. GFM-identification acceptance criteria are depending on the choice of identification method and slice thickness. Patient positioning strategies needs further investigations to establish acceptance criteria.

Magnetic resonance image-based tomotherapy planning for prostate cancer

Purpose

To evaluate and compare the feasibilities of magnetic resonance (MR) image-based planning using synthetic computed tomography (sCT) versus CT (pCT)-based planning in helical tomotherapy for prostate cancer.

Materials and Methods

A retrospective evaluation was performed in 16 patients with prostate cancer who had been treated with helical tomotherapy. MR images were acquired using a dedicated therapy sequence; sCT images were generated using magnetic resonance for calculating attenuation (MRCAT). The three-dimensional dose distribution according to sCT was recalculated using a previously optimized plan and was compared with the doses calculated using pCT.

Results

The mean planning target volume doses calculated by sCT and pCT differed by 0.65% ± 1.11% (p = 0.03). Three-dimensional gamma analysis at a 2%/2 mm dose difference/distance to agreement yielded a pass rate of 0.976 (range, 0.658 to 0.986).

Conclusion

The dose distribution results obtained using tomotherapy from MR-only simulations were in good agreement with the dose distribution results from simulation CT, with mean dose differences of less than 1% for target volume and normal organs in patients with prostate cancer.

Multimodality image registration in the head-and-neck using a deep learning-derived synthetic CT as a bridge

PURPOSE

To develop and demonstrate the efficacy of a novel head-and-neck multimodality image registration technique using deep-learning-based cross-modality synthesis.

METHODS AND MATERIALS

Twenty-five head-and-neck patients received magnetic resonance (MR) and computed tomography (CT) (CTaligned ) scans on the same day with the same immobilization. Fivefold cross validation was used with all of the MR-CT pairs to train a neural network to generate synthetic CTs from MR images. Twenty-four of 25 patients also had a separate CT without immobilization (CTnon-aligned ) and were used for testing. CTnon-aligned 's were deformed to the synthetic CT, and compared to CTnon-aligned registered to MR. The same registrations were performed from MR to CTnon-aligned and from synthetic CT to CTnon-aligned . All registrations used B-splines for modeling the deformation, and mutual information for the objective. Results were evaluated using the 95% Hausdorff distance among spinal cord contours, landmark error, inverse consistency, and Jacobian determinant of the estimated deformation fields.

RESULTS

When large initial rigid misalignment is present, registering CT to MRI-derived synthetic CT aligns the cord better than a direct registration. The average landmark error decreased from 9.8 ± 3.1 mm in MR→CTnon-aligned to 6.0 ± 2.1 mm in CTsynth →CTnon-aligned deformable registrations. In the CT to MR direction, the landmark error decreased from 10.0 ± 4.3 mm in CTnon-aligned →MR deformable registrations to 6.6 ± 2.0 mm in CTnon-aligned →CTsynth deformable registrations. The Jacobian determinant had an average value of 0.98. The proposed method also demonstrated improved inverse consistency over the direct method.

CONCLUSIONS

We showed that using a deep learning-derived synthetic CT in lieu of an MR for MR→CT and CT→MR deformable registration offers superior results to direct multimodal registration.

Multi-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapy

PURPOSE

The purpose of this study is to investigate the effect of different magnetic resonance (MR) sequences on the accuracy of deep learning-based synthetic computed tomography (sCT) generation in the complex head and neck region.

METHODS

Four sequences of MR images (T1, T2, T1C, and T1DixonC-water) were collected from 45 patients with nasopharyngeal carcinoma. Seven conditional generative adversarial network (cGAN) models were trained with different sequences (single channel) and different combinations (multi-channel) as inputs. To further verify the cGAN performance, we also used a U-net network as a comparison. Mean absolute error, structural similarity index, peak signal-to-noise ratio, dice similarity coefficient, and dose distribution were evaluated between the actual CTs and sCTs generated from different models.

RESULTS

The results show that the cGAN model with multi-channel (i.e., T1 + T2 + T1C + T1DixonC-water) as input to predict sCT achieves higher accuracy than any single MR sequence model. The T1-weighted MR model achieves better results than T2, T1C, and T1DixonC-water models. The comparison between cGAN and U-net shows that the sCTs predicted by cGAN retains additional image details are less blurred and more similar to the actual CT.

CONCLUSIONS

Conditional generative adversarial network with multiple MR sequences as model input shows the best accuracy. The T1-weighted MR images provide sufficient image information and are suitable for sCT prediction in clinical scenarios with limited acquisition sequences or limited acquisition time.

Dosimetric evaluation of MR-derived synthetic-CTs for MR-only proton treatment planning

PURPOSE

To evaluate proton dose calculation accuracy of optimized pencil beam scanning (PBS) plans on MR-derived synthetic-CTs for prostate patients.

MATERIAL AND METHODS

Ten patient datasets with both a CT and an MRI were planned with opposed lateral proton beams optimized to single field uniform dose under an IRB-approved study. The proton plans were created on CT datasets generated by a commercial synthetic CT-based software called MRCAT (MR for Calculating ATtenuation) routinely used in our clinic for photon-based MR-only planning. A standard prescription of 79.2 Gy (RBE) and 68.4 Gy (RBE) was used for intact prostate and prostate bed cases, respectively. Proton plans were first generated and optimized using the MRCAT synthetic-CT (syn-CT), and then recalculated on the planning CT rigidly aligned with the syn-CT (aligned-CT) and a deformed planning CT (deformed-CT), which was deformed to match outer contour between syn-CT and aligned-CT. The same beam arrangement, total MUs, MUs/spot, spot positions were used to recalculate dose on deformed-CT and aligned-CT without renormalization. DVH analysis was performed on aligned-CT, deformed-CT, and syn-CT to compare D_98%, V_100%, V_95% for PTV, PTVeval, and GTV as well as V_70Gy, V_50Gy for OARs.

RESULTS

The relative percentage dose difference between syn-CT and deformed-CT, were (0.17 ± 0.33 %) for PTVeval D_98% and (0.07 ± 0.1 %) for CTV D_98%. Rectum V_70Gy, V_50Gy, and Bladder V_70Gy were (2.76 ± 4.01 %), (11.6 ± 11.2 %), and (3.41 ± 2.86 %), respectively for the syn-CT, and (3.23 ± 3.63 %), (11.3 ± 8.18 %), and (3.29 ± 2.76 %), respectively for the deformed-CT, and (1.37 ± 1.84 %), (8.48 ± 6.67 %), and (4.91 ± 3.65 %), respectively for aligned-CT.

CONCLUSION

Dosimetric analysis shows that MR-only proton planning is feasible using syn-CT based on current clinical margins that account for a range uncertainty.

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.

The accuracy of Magnetic Resonance - Cone Beam Computed Tomography soft-tissue matching for prostate radiotherapy

BACKGROUND AND PURPOSE

Magnetic Resonance (MR)-Only radiotherapy requires a method for matching image with on-treatment Cone Beam Computed Tomography (CBCT). This study aimed to investigate the accuracy of MR-CBCT soft-tissue matching for prostate MR-only radiotherapy.

MATERIALS AND METHODS

Three patient cohorts were used, with all patients receiving MR and CT scans. For the first cohort (10 patients) the first fraction CBCT was automatically rigidly registered to the CT and MR scans and the MR-CT registration predicted using the MR-CBCT and CT-CBCT registrations. This was compared to the automatic MR-CT registration. For the second and third cohorts (five patients each) the first fraction CBCT was independently matched to the CT and MR by four radiographers, the MR-CBCT and CT-CBCT matches compared and the inter-observer variability assessed. The second cohort used a CT-based structure set and the third a MR-based structure set with the MR relabelled as a 'CT'.

RESULTS

The mean difference between predicted and actual MR-CT registrations was Δ R All = - 0.1 ± 0.2 mm (s.e.m.). Radiographer MR-CBCT registrations were not significantly different to CT-CBCT, with mean differences in soft-tissue match ⩽ 0.2 mm and all except one difference ⩽ 3.3 mm . This was less than the MR-CBCT inter-observer limits of agreement [ 3.5 , 2.4 , 0.9 ] mm (vertical, longitudinal, lateral), which were similar ( ⩽ 0.5 mm ) to CT-CBCT.

CONCLUSIONS

MR-CBCT soft-tissue matching is not significantly different to CT-CBCT. Relabelling the MR as a 'CT' does not appear to change the automatic registration. This suggests that MR-CBCT soft-tissue matching is feasible and accurate.