Convolutional LSTM model for cine image prediction of abdominal motion.

Objective.In this study, we tackle the challenge of latency in magnetic resonance linear accelerator (MR-Linac) systems, which compromises target coverage accuracy in gated real-time radiotherapy. Our focus is on enhancing motion prediction precision in abdominal organs to address this issue. We developed a convolutional long short-term memory (convLSTM) model, utilizing 2D cine magnetic resonance (cine-MR) imaging for this purpose.Approach.Our model, featuring a sequence-to-one architecture with six input frames and one output frame, employs structural similarity index measure (SSIM) as loss function. Data was gathered from 17 cine-MRI datasets using the Philips Ingenia MR-sim system and an Elekta Unity MR-Linac equivalent sequence, focusing on regions of interest (ROIs) like the stomach, liver, pancreas, and kidney. The datasets varied in duration from 1 to 10 min.Main results.The study comprised three main phases: hyperparameter optimization, individual training, and transfer learning with or without fine-tuning. Hyperparameters were initially optimized to construct the most effective model. Then, the model was individually applied to each dataset to predict images four frames ahead (1.24-3.28 s). We evaluated the model's performance using metrics such as SSIM, normalized mean square error, normalized correlation coefficient, and peak signal-to-noise ratio, specifically for ROIs with target motion. The average SSIM values achieved were 0.54, 0.64, 0.77, and 0.66 for the stomach, liver, kidney, and pancreas, respectively. In the transfer learning phase with fine-tuning, the model showed improved SSIM values of 0.69 for the liver and 0.78 for the kidney, compared to 0.64 and 0.37 without fine-tuning.Significance. The study's significant contribution is demonstrating the convLSTM model's ability to accurately predict motion for multiple abdominal organs using a Unity-equivalent MR sequence. This advancement is key in mitigating latency issues in MR-Linac radiotherapy, potentially improving the precision and effectiveness of real-time treatment for abdominal cancers.

Initial validation of a diaphragm tracking system for multiple breath-hold volumetric modulated arc therapy of abdominal tumors: A phantom study.

BACKGROUND: The breath-hold radiotherapy has been increasingly used to mitigate interfractional and intrafractional breathing impact on treatment planning and beam delivery. Previous techniques include body surface measurements or radiopaque metal markers, each having known disadvantages. PURPOSE: We recently proposed a new markerless technique without the disadvantages, where diaphragm was registered between DRR and fluoroscopic x-ray projection images every 180 ms during VMAT delivery. An initial validation of the proposed diaphragm tracking system (DiaTrak) was performed using a chest phantom to evaluate its characteristics. METHODS: Diaphragm registration was performed between DRR and projection streaming kV x-ray images of a chest phantom during VMAT delivery. Streaming data including the projection images and the beam angles were transferred from a linac system to an external PC, where the diaphragm registration accuracy and beam-off latency were measured based on image cross correlation between the DRR and the projection images every 180 ms. RESULTS: It was shown that the average of the beam-off latency was 249.5 ms and the average of the diaphragm registration error was 0.84 mm CONCLUSIONS: Initial validation of the proposed DiaTrak system for multiple breath-hold VMAT of abdominal tumors has been successfully completed with a chest phantom. The resulting beam-off latency and the diaphragm registration error were regarded clinically acceptable.

Gating and intrafraction drift correction on a 1.5 T MR-Linac: Clinical dosimetric benefits for upper abdominal tumors.

This work reports on the first seven patients treated with gating and baseline drift correction on the high-field MR-Linac system. Dosimetric analysis showed that the active motion management system improved congruence to the planned dose, efficiently mitigating detrimental effects of intrafraction motion in the upper abdomen.

Automated deep learning auto-segmentation of air volumes for MRI-guided online adaptive radiation therapy of abdominal tumors.

Objective. In the current MR-Linac online adaptive workflow, air regions on the MR images need to be manually delineated for abdominal targets, and then overridden by air density for dose calculation. Auto-delineation of these regions is desirable for speed purposes, but poses a challenge, since unlike computed tomography, they do not occupy all dark regions on the image. The purpose of this study is to develop an automated method to segment the air regions on MRI-guided adaptive radiation therapy (MRgART) of abdominal tumors.Approach. A modified ResUNet3D deep learning (DL)-based auto air delineation model was trained using 102 patients' MR images. The MR images were acquired by a dedicated in-house sequence named 'Air-Scan', which is designed to generate air regions that are especially dark and accentuated. The air volumes generated by the newly developed DL model were compared with the manual air contours using geometric similarity (Dice Similarity Coefficient (DSC)), and dosimetric equivalence using Gamma index and dose-volume parameters.Main results. The average DSC agreement between the DL generated and manual air contours is 99% ± 1%. The gamma index between the dose calculations with overriding the DL versus manual air volumes with density of 0.01 is 97% ± 2% for a local gamma calculation with a tolerance of 2% and 2 mm. The dosimetric parameters from planning target volume-PTV and organs at risk-OARs were all within 1% between when DL versus manual contours were overridden by air density. The model runs in less than five seconds on a PC with 28 Core processor and NVIDIA Quadro®P2000 GPU.Significance: a DL based automated segmentation method was developed to generate air volumes on specialized abdominal MR images and generate results that are practically equivalent to the manual contouring of air volumes.

Accuracy of abdominal organ motion estimation in radiotherapy using the right hemidiaphragm top as a surrogate during prolonged breath-holds quantified with MRI.

BACKGROUND: Respiratory motion presents a challenge in radiotherapy of thoracic and upper abdominal tumors. Techniques to account for respiratory motion include tracking. Using magnetic resonance imaging (MRI) guided radiotherapy systems, tumors can be tracked continuously. Using conventional linear accelerators, tracking of lung tumors is possible by determining tumor motion on kilo voltage (kV) imaging. But tracking of abdominal tumors with kV imaging is hampered by limited contrast. Therefore, surrogates for the tumor are used. One of the possible surrogates is the diaphragm. However, there is no universal method for establishing the error when using a surrogate and there are particular challenges in establishing such errors during free breathing (FB). Prolonged breath-holding might address these challenges. PURPOSE: The aim of this study was to quantify the error when using the right hemidiaphragm top (RHT) as surrogate for abdominal organ motion during prolonged breath-holds (PBH) for possible application in radiation treatments. METHODS: Fifteen healthy volunteers were trained to perform PBHs in two subsequent MRI sessions (PBH-MRI1 and PBH-MRI2). From each MRI acquisition, we selected seven images (dynamics) to determine organ displacement during PBH by using deformable image registration (DIR). On the first dynamic, the RHT, right and left hemidiaphragm, liver, spleen and right and left kidney were segmented. We used the deformation vector fields (DVF), generated by DIR, to determine the displacement of each organ between two dynamics in inferior-superior (IS), anterior-posterior (AP), left-right (LR) direction and we calculated the 3D vector magnitude (|d|). The displacements of the RHT, both hemidiaphragms and the abdominal organs were compared using a linear fit to determine the correlation (R2 of the fit) and the displacement ratio (DR, slope of the fit) between displacements of the RHT and each organ. We quantified the median difference between the DRs of PBH-MRI1 and PBH-MRI2 for each organ. Additionally, we estimated organ displacement in the second PBH by applying the DR from the first PBH to the displacement of the RHT measured during the second PBH. We compared the estimated organ displacement to the measured organ displacement during the second PBH. The difference between the two values was defined as the estimation error of using the RHT as a surrogate and assuming a constant DR over MRI sessions. RESULTS: The linear relationships were confirmed by the high R2 values of the linear fit between the displacements of the RHT and the abdominal organs (R2 > 0.96) in the IS and AP direction and |d|, and high to moderate correlations in the LR direction (0.93 > R2 > 0.64). The median DR difference between PBH-MRI1 and PBH-MRI2 varied between 0.13 and 0.31 for all organs. The median estimation error of the RHT as a surrogate varied between 0.4 and 0.8 mm/min for all organs. CONCLUSION: The RHT could serve as an accurate surrogate for abdominal organ motion during radiation treatments, for example, in tracking, provided the error of the RHT as motion surrogate is taken into account in the margins. TRIAL REGISTRATION: The study was registered in the Netherlands Trial Register (NL7603).

Real-time motion monitoring using orthogonal cine MRI during MR-guided adaptive radiation therapy for abdominal tumors on 1.5T MR-Linac.

BACKGROUND: Real-time motion monitoring (RTMM) is necessary for accurate motion management of intrafraction motions during radiation therapy (RT). PURPOSE: Building upon a previous study, this work develops and tests an improved RTMM technique based on real-time orthogonal cine magnetic resonance imaging (MRI) acquired during magnetic resonance-guided adaptive RT (MRgART) for abdominal tumors on MR-Linac. METHODS: A motion monitoring research package (MMRP) was developed and tested for RTMM based on template rigid registration between beam-on real-time orthogonal cine MRI and pre-beam daily reference 3D-MRI (baseline). The MRI data acquired under free-breathing during the routine MRgART on a 1.5T MR-Linac for 18 patients with abdominal malignancies of 8 liver, 4 adrenal glands (renal fossa), and 6 pancreas cases were used to evaluate the MMRP package. For each patient, a 3D mid-position image derived from an in-house daily 4D-MRI was used to define a target mask or a surrogate sub-region encompassing the target. Additionally, an exploratory case reviewed for an MRI dataset of a healthy volunteer acquired under both free-breathing and deep inspiration breath-hold (DIBH) was used to test how effectively the RTMM using the MMRP can address through-plane motion (TPM). For all cases, the 2D T2/T1-weighted cine MRIs were captured with a temporal resolution of 200 ms interleaved between coronal and sagittal orientations. Manually delineated contours on the cine frames were used as the ground-truth motion. Common visible vessels and segments of target boundaries in proximity to the target were used as anatomical landmarks for reproducible delineations on both the 3D and the cine MRI images. Standard deviation of the error (SDE) between the ground-truth and the measured target motion from the MMRP package were analyzed to evaluate the RTMM accuracy. The maximum target motion (MTM) was measured on the 4D-MRI for all cases during free-breathing. RESULTS: The mean (range) centroid motions for the 13 abdominal tumor cases were 7.69 (4.71-11.15), 1.73 (0.81-3.05), and 2.71 (1.45-3.93) mm with an overall accuracy of <2 mm in the superior-inferior (SI), the left-right (LR), and the anterior-posterior (AP) directions, respectively. The mean (range) of the MTM from the 4D-MRI was 7.38 (2-11) mm in the SI direction, smaller than the monitored motion of centroid, demonstrating the importance of the real-time motion capture. For the remaining patient cases, the ground-truth delineation was challenging under free-breathing due to the target deformation and the large TPM in the AP direction, the implant-induced image artifacts, and/or the suboptimal image plane selection. These cases were evaluated based on visual assessment. For the healthy volunteer, the TPM of the target was significant under free-breathing which degraded the RTMM accuracy. RTMM accuracy of <2 mm was achieved under DIBH, indicating DIBH is an effective method to address large TPM. CONCLUSIONS: We have successfully developed and tested the use of a template-based registration method for an accurate RTMM of abdominal targets during MRgART on a 1.5T MR-Linac without using injected contrast agents or radio-opaque implants. DIBH may be used to effectively reduce or eliminate TPM of abdominal targets during RTMM.

Evaluation of mega-voltage CT images for completed radiotherapy treatments for dogs and cats reveals uncommon but potentially consequential dose deviation in thoracic and abdominal tumors.

As advanced delivery techniques such as intensity-modulated radiation therapy (IMRT) become conventional in veterinary radiotherapy, highly modulated radiation delivery helps to decrease dose to normal tissues. However, IMRT is only effective if patient setup and anatomy are accurately replicated for each treatment. Numerous techniques have been implemented to decrease patient setup error, however tumor shrinkage, variations in the patient's contour and weight loss continue to be hard to control and can result in clinically relevant dose deviation in radiotherapy plans. Adaptive radiotherapy (ART) is often the most effective means to account for gradual changes such as tumor shrinkage and weight loss, however it is often unclear when adaption is necessary. The goal of this retrospective, observational study was to review dose delivery in dogs and cats who received helical radiotherapy at University of Wisconsin, using detector dose data (D2%, D50%, D98%) and daily megavoltage computed tomography (MVCT) images, and to determine whether ART should be considered more frequently than it currently is. A total of 52 treatment plans were evaluated and included cancers of the head and neck, thorax, and abdomen. After evaluation, 6% of the radiotherapy plan delivered had clinically relevant dose deviations in dose delivery. Dose deviations were more common in thoracic and abdominal targets. While adaptation may have been considered in these cases, the decision to adapt can be complex and all factors, such as treatment delay, cost, and imaging modality, must be considered when adaptation is to be pursued.

Dosimetric impact of intrafraction motion under abdominal compression during MR-guided SBRT for (Peri-) pancreatic tumors.

Objective. Intrafraction motion is a major concern for the safety and effectiveness of high dose stereotactic body radiotherapy (SBRT) in the upper abdomen. In this study, the impact of the intrafraction motion on the delivered dose was assessed in a patient group that underwent MR-guided radiotherapy for upper abdominal malignancies with an abdominal corset.Approach. Fast online 2D cine MRI was used to extract tumor motion during beam-on time. These tumor motion profiles were combined with linac log files to reconstruct the delivered dose in 89 fractions of MR-guided SBRT in twenty patients. Aside the measured tumor motion, motion profiles were also simulated for a wide range of respiratory amplitudes and drifts, and their subsequent dosimetric impact was calculated in every fraction.Main results. The average (SD)D99%of the gross tumor volume (GTV), relative to the plannedD99%, was 0.98 (0.03). The average (SD) relativeD0.5ccof the duodenum, small bowel and stomach was 0.99 (0.03), 1.00 (0.03), and 0.97 (0.05), respectively. No correlation of respiratory amplitude with dosimetric impact was observed. Fractions with larger baseline drifts generally led to a larger uncertainty of dosimetric impact on the GTV and organs at risk (OAR). The simulations yielded that the delivered dose is highly dependent on the direction of on baseline drift. Especially in anatomies where the OARs are closely abutting the GTV, even modestLRorAPdrifts can lead to substantial deviations from the planned dose.Significance. The vast majority of the fractions was only modestly impacted by intrafraction motion, increasing our confidence that MR-guided SBRT with abdominal compression can be safely executed for patients with abdominal tumors, without the use of gating or tracking strategies.

Development and implementation of an automatic air delineation technique for MRI-guided adaptive radiation therapy.

Objective.Auto-delineation of air regions on daily MRI for MR-guided online adaptive radiotherapy (MRgOART) of abdominal tumors is challenging since the air packets occur randomly and their MR intensities can be similar to some other tissue types. This work reports a new method to auto-delineate air regions on MRI.Approach.The proposed method (named DIFF method) consists of (1) generating a combined volumeVcomb, which is a union of the air-containing organs on a reference MR image offline, (2) transferringVcombfrom the reference MR to a daily MR via DIR, (3) combining the transferredVcombwith a region of high DIR inaccuracy, and (4) applying a threshold to the obtained final combined volume to generate the air volumes. The high DIR inaccuracy region was calculated from the absolute difference between the deformed daily and the reference images. This method was tested on 36 abdominal daily MRI sets acquired from 7 patients on a 1.5 T MR-Linac. The performance of DIFF was compared with alternative auto-air generation methods that (1) does not account for DIR inaccuracies, and (2) uses rigid registration instead of DIR.Main results.The results show that the proposed DIFF method can be fully automated and can be executed within 25 s. The Dice similarity coefficient of manual and DIFF auto-generated air contours was >92% for all cases, while it was 90% for the alternative auto-delineation methods. Dosimetrically, the auto-generated air regions using DIFF resulted in practically identical DVHs as those generated by using manual air contours.Significance.The DIFF method is robust and accurate and can be implemented to automatically consider the inter- and intra- fractional air volume variations during MRgOART for abdominal tumors. The use of DIFF method improves dosimetric accuracy as compared to other methods, especially beneficial for the patients with large daily abdominal air volume variations.

Shortening the preparation time of the single prolonged breath-hold for radiotherapy sessions.

OBJECTIVE: Single prolonged breath-holds of >5 min can be obtained in cancer patients. Currently, however, the preparation time in each radiotherapy session is a practical limitation for clinical adoption of this new technique. Here, we show by how much our original preparation time can be shortened without unduly compromising breath-hold duration. METHODS: 44 healthy subjects performed single prolonged breath-holds from 60% O2 and mechanically induced hypocapnia. We tested the effect on breath-hold duration of shortening preparation time (the durations of acclimatization, hyperventilation and hypocapnia) by changing these durations and or ventilator settings. RESULTS: Mean original breath-hold duration was 6.5 ± 0.2 (standard error) min. The total original preparation time (from connecting the facemask to the start of the breath-hold) was 26 ± 1 min. After shortening the hypocapnia duration from 16 to 5 min, mean breath-hold duration was still 6.1 ± 0.2 min (ns vs the original). After abolishing the acclimatization and shortening the hypocapnia to 1 min (a total preparation time now of 9 ± 1 min), a mean breath-hold duration of >5 min was still possible (now significantly shortened to 5.2 ± 0.6 min, p < 0.001). After shorter and more vigorous hyperventilation (lasting 2.7 ± 0.3 min) and shorter hypocapnia (lasting 43 ± 4 s), a mean breath-hold duration of >5 min (5.3 ± 0.2 min, p < 0.05) was still possible. Here, the final total preparation time was 3.5 ± 0.3 min. CONCLUSIONS: These improvements may facilitate adoption of the single prolonged breath-hold for a range of thoracic and abdominal radiotherapies especially involving hypofractionation. ADVANCES IN KNOWLEDGE: Multiple short breath-holds improve radiotherapy for thoracic and abdominal cancers. Further improvement may occur by adopting the single prolonged breath-hold of >5 min. One limitation to clinical adoption is its long preparation time. We show here how to reduce the mean preparation time from 26 to 3.5 min without compromising breath-hold duration.

Respiratory motion management for external radiotherapy treatment.

We present the update of the recommendations of the French society of oncological radiotherapy on respiratory motion management for external radiotherapy treatment. Since twenty years and the report 62 of ICRU, motion management during the course of radiotherapy treatment has become an increasingly significant concern, particularly with the development of hypofractionated treatments under stereotactic conditions, using reduced safety margins. This article related orders of motion amplitudes for different organs as well as the definition of the margins in radiotherapy. An updated review of the various movement management strategies is presented as well as main technological solutions enabling them to be implemented: when acquiring anatomical data, during planning and when carrying out treatment. Finally, the management of these moving targets, such as it can be carried out in radiotherapy departments, will be detailed for a few concrete examples of localizations (abdominal, thoracic and hepatic).

Investigating the use of virtual 4DCT from 4DMRI in gated carbon ion radiation therapy of abdominal tumors.

PURPOSE: To generate virtual 4DCT from 4DMRI with field of view (FOV) extended to the entire involved patient anatomy, in order to evaluate its use in carbon ion radiation therapy (CIRT) of the abdominal site in a clinical scenario. MATERIALS AND METHODS: The virtual 4DCT was generated by deforming a reference CT in order to (1) match the anatomy depicted in the 4DMRI within its FOV, by calculating deformation fields with deformable image registration to describe inter-fractional and breathing motion, and (2) obtain physically plausible deformation outside of the 4DMRI FOV, by propagating and modulating the previously obtained deformation fields. The implemented method was validated on a digital anthropomorphic phantom, for which a ground truth (GT) 4DCT was available. A CIRT treatment plan was optimized at the end-exhale reference CT and the RBE-weighted dose distribution was recalculated on both the virtual and GT 4DCTs. The method estimation error was quantified by comparing the virtual and GT 4DCTs and the corresponding recomputed doses. The method was then evaluated on 8 patients with pancreas or liver tumors treated with CIRT using respiratory gating at end-exhale. The clinical treatment plans adopted at the National Center for Oncological Hadrontherapy (CNAO, Pavia, Italy) were considered and the dose distribution was recomputed on all respiratory phases of the planning and virtual 4DCTs. By comparing the two datasets and the corresponding dose distributions, the geometrical and dosimetric impact of organ motion was assessed. RESULTS: For the phantom, the error outside of the 4DMRI FOV was up to 4.5mm, but it remained sub-millimetric in correspondence to the target within the 4DMRI FOV. Although the impact of motion on the target D95% resulted in variations ranging from 22% to 90% between the planned dose and the doses recomputed on the GT 4DCT phases, the corresponding estimation error was ≤2.2%. In the patient cases, the variation of the baseline tumor position between the planning and the virtual end-exhale CTs presented a median (interquartile range) value of 6.0 (4.9) mm. For baseline variations larger than 5mm, the tumor D95% variation between the plan and the dose recomputed on the end-exhale virtual CT resulted larger than 10%. Median variations higher than 10% in the target D95% and gastro-intestinal OARs D2% were quantified at the end-inhale, whereas close to the end-exhale phase, limited variations of relevant dose metrics were found for both tumor and OARs. CONCLUSIONS: The negligible impact of the geometrical inaccuracy in the estimated anatomy outside of the 4DMRI FOV on the overall dosimetric accuracy suggests the feasibility of virtual 4DCT with extended FOV in CIRT of the abdominal site. In the analyzed patient group, inter-fractional variations such as baseline variation and breathing variability were quantified, demonstrating the method capability to support treatment planning in gated CIRT of the abdominal site.

Pulsed low-dose rate radiotherapy has an improved therapeutic effect on abdominal and pelvic malignancies.

Until now, there has been a lack of standard and effective treatments for patients with recurrent malignant tumors or abdominal and pelvic malignancies with extensive invasion (Morris, 2000). Generally, these patients face problems such as inability to undergo surgery or chemotherapy resistance (Combs et al., 2016). Re-radiotherapy has achieved a prominent place in the treatment of patients who have received radiotherapy previously and developed in-field recurrences (Straube et al., 2018). However, re-radiotherapy is very complicated, requiring comprehensive consideration of appropriate radiation dose, interval from first radiotherapy, boundary of the radiotherapy target area, and damage to surrounding normal tissues (Straube et al., 2019). In other words, it is necessary to focus on the protection of surrounding normal tissues while maximizing the efficacy of re-radiotherapy in such patients.

Patient positioning and immobilization procedures for hybrid MR-Linac systems.

Hybrid magnetic resonance (MR)-guided linear accelerators represent a new horizon in the field of radiation oncology. By harnessing the favorable combination of on-board MR-imaging with the possibility to daily recalculate the treatment plan based on real-time anatomy, the accuracy in target and organs-at-risk identification is expected to be improved, with the aim to provide the best tailored treatment. To date, two main MR-linac hybrid machines are available, Elekta Unity and Viewray MRIdian. Of note, compared to conventional linacs, these devices raise practical issues due to the positioning phase for the need to include the coil in the immobilization procedure and in order to perform the best reproducible positioning, also in light of the potentially longer treatment time. Given the relative novelty of this technology, there are few literature data regarding the procedures and the workflows for patient positioning and immobilization for MR-guided daily adaptive radiotherapy. In the present narrative review, we resume the currently available literature and provide an overview of the positioning and setup procedures for all the anatomical districts for hybrid MR-linac systems.

Proton radiotherapy for recurrent or metastatic sarcoma with palliative quad shot.

Patients with previously treated, recurrent or metastatic sarcomas who have progressed on multiples lines of systemic therapy may have limited options for local control. We evaluated outcomes of palliative proton therapy with the quad shot regimen to unresectable disease for patients with recurrent and/or metastatic sarcoma. From 2014 to 2018, 28 patients with recurrent or metastatic sarcomas were treated to 40 total sites with palliative proton RT with quad shot (14.8 Gy/4 twice daily). Outcomes included toxicity, ability to receive further systemic therapy, and subjective palliative response. Univariate analysis was performed for local progression-free survival (LPFS) and overall survival (OS). Of the 40 total sites, 25 (62.5%) received ≥3 cycles with median follow up of 12 months (IQR 4-19). The most common histologies were GIST (9; 22.5%) and leiomyosarcoma (7; 17.5%). A total of 27 (67.5%) sites were located in the abdomen or pelvis. Seventeen (42.5%) treatments involved concurrent systemic therapy and 13 (32.5%) patients received further systemic therapy following proton therapy. Overall subjective palliative response was 70%. Median LPFS was 11 months and 6-month LPFS was 66.1%. On univariate analysis, receipt of four cycles of quad shot (HR 0.06, p = 0.02) and receipt of systemic therapy after completion of radiation therapy (HR 0.17, p = 0.02) were associated with improved LPFS. Three grade 3 acute toxicities were observed. The proton quad shot regimen serves as a feasible alternative for patients with previously treated, recurrent or metastatic sarcomas where overall treatment options may be limited.

DeepDose: a robust deep learning-based dose engine for abdominal tumours in a 1.5 T MRI radiotherapy system.

We present a robust deep learning-based framework for dose calculations of abdominal tumours in a 1.5 T MRI radiotherapy system. For a set of patient plans, a convolutional neural network is trained on the dose of individual multi-leaf-collimator segments following the DeepDose framework. It can then be used to predict the dose distribution per segment for a set of patient anatomies. The network was trained using data from three anatomical sites of the abdomen: prostate, rectal and oligometastatic tumours. A total of 216 patient fractions were used, previously treated in our clinic with fixed-beam IMRT using the Elekta MR-linac. For the purpose of training, 176 fractions were used with random gantry angles assigned to each segment, while 20 fractions were used for the validation of the network. The ground truth data were calculated with a Monte Carlo dose engine at 1% statistical uncertainty per segment. For a total of 20 independent abdominal test fractions with the clinical angles, the network was able to accurately predict the dose distributions, achieving 99.4% ± 0.6% for the whole plan prediction at the 3%/3 mm gamma test. The average dose difference and standard deviation per segment was 0.3% ± 0.7%. Additional dose prediction on one cervical and one pancreatic case yielded high dose agreement of 99.9% and 99.8% respectively for the 3%/3 mm criterion. Overall, we show that our deep learning-based dose engine calculates highly accurate dose distributions for a variety of abdominal tumour sites treated on the MR-linac, in terms of performance and generality.

Technical Note: Using virtual noncontrast images from dual-energy CT to eliminate the need of precontrast CT for x-ray radiation treatment planning of abdominal tumors†.

PURPOSE: Radiation therapy (RT) planning frequently utilizes contrast-enhanced CT. However, dose calculations should not be performed on a contrast-enhanced CT because the patient will not receive bolus during treatment. It is typical to acquire CT twice during RT simulation: once before injection of bolus and once after. The registration between these datasets introduces errors. In this work, we investigate the use of virtual noncontrast images (VNC) derived from dual-energy CT (DECT) to eliminate the precontrast CT and the registration error. METHODS: CT datasets, including conventional 120 kVp pre- and postcontrast CTs and postcontrast DECT, acquired for ten pancreatic cancer patients were evaluated. The DECTs were acquired simultaneously using a dual source (DS) CT simulator. VNC and virtual mono-energetic images (VMI) were derived from DECTs. Gross tumor volumes (GTV), planning target volumes (PTV), and organs at risks (OAR) were delineated on the postcontrast CT and then populated to the precontrast CT and the VNC. An IMRT plan (50.4 Gy in 28 fractions) was then optimized on the precontrast CT. Dose distributions were recalculated on the VNC images. Contours from the pre- and postcontrast CTs and the dose distributions based on both were compared. RESULTS: On average, the distance of centroids of the populated duodenum contours on precontrast CT differed by 6.0 ± 4.0 mm from those on postcontrast CTs. The dose distributions on the precontrast CT and VNC were almost identical. The PTV mean and maximum doses differed by 0.1% and 0.2% between the two plans, respectively. CONCLUSION: The VNC derived from DECT can be used to replace the conventional precontrast CT scan for RT planning, eliminating the need for an additional precontrast CT scan and eliminating the registration errors. Thus, VNC can become an important asset to the future of RT.

Deep learning prediction of proton and photon dose distributions for paediatric abdominal tumours.

OBJECTIVE: Dose prediction using deep learning networks prior to radiotherapy might lead tomore efficient modality selections. The study goal was to predict proton and photon dose distributions based on the patient-specific anatomy and to assess their clinical usage for paediatric abdominal tumours. MATERIAL AND METHODS: Data from 80 patients with neuroblastoma or Wilms' tumour was included. Pencil beam scanning (PBS) (5 mm/ 3%) and volumetric-modulated arc therapy (VMAT) plans (5 mm) were robustly optimized on the internal target volume (ITV). Separate 3-dimensional patch-based U-net networks were trained to predict PBS and VMAT dose distributions. Doses, planning-computed tomography images and relevant optimization masks (ITV, vertebra and organs-at-risk) of 60 patients were used for training with a 5-fold cross validation. The networks' performance was evaluated by computing the relative error between planned and predicted dose-volume histogram (DVH) parameters for 20 inference patients. In addition, the organs-at-risk mean dose difference between modalities was calculated using planned and predicted dose distributions (ΔDmean = DVMAT-DPBS). Two radiation oncologists performed a blind PBS/VMAT modality selection based on either planned or predicted ΔDmean. RESULTS: Average DVH differences between planned and predicted dose distributions were ≤ |6%| for both modalities. The networks classified the organs-at-risk Dmean difference as a gain (ΔDmean > 0) with 98% precision. An identical modality selection based on planned compared to predicted ΔDmean was made for 18/20 patients. CONCLUSION: Deep learning networks for accurate prediction of proton and photon dose distributions for abdominal paediatric tumours were established. These networks allowing fast dose visualisation might aid in identifying the optimal radiotherapy technique when experience and/or resources are unavailable.

Feasibility of using post-contrast dual-energy CT for pediatric radiation treatment planning and dose calculation.

OBJECTIVES: When iodinated contrast is administered during CT simulation, standard practice requires a separate non-contrast CT for dose calculation. The objective of this study is to validate our hypothesis that since iodine affects Hounsfield units (HUs) more than electron density (ED), the information from post-contrast dual-layer CT (DLCT) would be sufficient for accurate dose calculation for both photon and proton therapy. METHODS AND MATERIALS: 10 pediatric patients with abdominal tumors underwent DLCT scans before and after iodinated contrast administration for radiotherapy planning. Dose distributions with these DLCT-based methods were compared to those with conventional calibration-curve methods that map HU images to ED and stopping-power ratio (SPR) images. RESULTS: For photon plans, conventional and DLCT approaches based on post-contrast scans underestimated the PTV D99 by 0.87 ± 0.70% (p = 0.18) and 0.36 ± 0.31% (p = 0.34), respectively, comparing to their non-contrast optimization plans. Renal iodine concentration was weakly associated with D99 deviation for both conventional (R2 = 0.10) and DLCT (R2 = 0.02) approaches. For proton plans, the clinical target volume D99 errors were 3.67 ± 2.43% (p = 0.0001) and 0.30 ± 0.25% (p = 0.40) for conventional and DLCT approaches, respectively. The proton beam range changed noticeably with the conventional approach. Renal iodine concentration was highly associated with D99 deviation for the conventional approach (R2 = 0.83) but not for DLCT (R2 = 0.007). CONCLUSION: Conventional CT with iodine contrast resulted in a large dosimetric error for proton therapy, compared to true non-contrast plans, but the error was less for photon therapy. These errors can be greatly reduced in the case of the proton plans if DLCT is used, raising the possibility of using only a single post-contrast CT for radiotherapy dose calculation, thus reducing the time and imaging dose required. ADVANCES IN KNOWLEDGE: This study is the first to compare directly the differences in the calculated dose distributions between pre- and post-contrast CT images generated by single-energy CT and dual-energy CT methods for photon and proton therapy.

Protocol of a study investigating breath-hold techniques for upper-abdominal radiation therapy (BURDIE): addressing the challenge of a moving target.

BACKGROUND: Radiation therapy to upper abdominal sites is technically challenging due to motion of tumors and surrounding organs resulting from normal respiration. Breath-hold, using an Active Breathing Coordinator is one strategy used to reduce motion in these tumor sites. Though widely used, no studies have prospectively compared the different breath-hold techniques (inspiration, deep-inspiration and expiration) using ABC in the same patient cohort. METHODS: Patients planned for radiation therapy to upper abdominal tumors are invited to participate in this prospective study. Participants attempt three breath hold techniques: inspiration, deep-inspiration and expiration breath-hold, in random order. kV fluoroscopy images of the dome of diaphragm are taken of five consecutive breath-holds in each technique. Reproducibility and stability of tumour position are measured, and used to select the technique with which to proceed to planning and treatment. Reproducibility at planning and each treatment fraction is measured, along with breath hold time, treatment efficiency and patient experience. DISCUSSION: The screening method was validated after the first three participants. This screening process may be able to select the best breath-hold technique for an individual, which may lead to improved reproducibility. The screening process is being piloted as a prospective clinical trial. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry (ANZCTR): 12618001691235. Registered 12th October 2018. https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=376109&isReview=true .