Search

This study quantified the performance of Intra-fraction Motion Review (IMR) during prostate Stereotactic Body Radiotherapy (SBRT) treatments. IMR was evaluated using prostate motion data from patients treated in an SBRT clinical trial (PROMETHEUS, NCT00587990).IMR measured prostate displacements were compared to those of two 3D motion management methods: Kilovoltage Intra-fraction Motion management (KIM) and MV/kV triangulation. A planning study assessing the impact of a defined prostate motion (2-5 mm) on the PTV coverage with and without IMR was performed. A clinically relevant IMR search region for prostate cancer SBRT treatments was determined using a customised anthropomorphic pelvis phantom with implanted gold seeds and a motion platform. IMR showed submillimeter agreement with corresponding 2D projections from both KIM and MV/kV triangulation. However, IMR detected actual displacements consistently in considerably fewer frames than KIM (3D), with the actual numbers depending on the settings. The Default Search Region (DSR) method employing a circular search region proved superior to user-contoured structures in detecting clinically relevant prostate motion. Reducing the DSR search region radius can reduce the impact of the 2D nature of IMR and improve the detectability of actual motion (by 10% per 0.5 mm reduction) but must be balanced against increased beam interruptions from minor, clinically irrelevant motion. The use of IMR for SBRT prostate treatments has the potential to improve target dose coverage (minimum dose to 98% of the PTV, D98%) by 20% compared to treatment without IMR. Calculated D98% of IMR monitored treatments with motion was within 1.5% of plans without motion.

Background: During prostate stereotactic body radiation therapy (SBRT), prostate tumor translational motion may deteriorate the planned dose distribution. Most of the major advances in motion management to date have focused on correcting this one aspect of the tumor motion, translation. However, large prostate rotation up to 30° has been measured. As the technological innovation evolves toward delivering increasingly precise radiotherapy, it is important to quantify the clinical benefit of translational and rotational motion correction over translational motion correction alone. Purpose: The purpose of this work was to quantify the dosimetric impact of intrafractional dynamic rotation of the prostate measured with a six degrees-of-freedom tumor motion monitoring technology. Methods: The delivered dose was reconstructed including (a) translational and rotational motion and (b) only translational motion of the tumor for 32 prostate cancer patients recruited on a 5-fraction prostate SBRT clinical trial. Patients on the trial received 7.25 Gy in a treatment fraction. A 5 mm clinical target volume (CTV) to planning target volume (PTV) margin was applied in all directions except the posterior direction where a 3 mm expansion was used. Prostate intrafractional translational motion was managed using a gating strategy, and any translation above the gating threshold was corrected by applying an equivalent couch shift. The residual translational motion is denoted as (Formula presented.). Prostate intrafractional rotational motion (Formula presented.) was recorded but not corrected. The dose differences from the planned dose due to (Formula presented.) + (Formula presented.), ΔD((Formula presented.) + (Formula presented.)) and due to (Formula presented.) alone, ΔD((Formula presented.)), were then determined for CTV D98, PTV D95, bladder V6Gy, and rectum V6Gy. The residual dose error due to uncorrected rotation, (Formula presented.) was then quantified: (Formula presented.) = ΔD((Formula presented.) + (Formula presented.)) - ΔD((Formula presented.)). Results: Fractional data analysis shows that the dose differences from the plan (both ΔD((Formula presented.) + (Formula presented.)) and ΔD((Formula presented.))) for CTV D98 was less than 5% in all treatment fractions. ΔD((Formula presented.) + (Formula presented.)) was larger than 5% in one fraction for PTV D95, in one fraction for bladder V6Gy, and in five fractions for rectum V6Gy. Uncorrected rotation, (Formula presented.) induced residual dose error, (Formula presented.), resulted in less dose to CTV and PTV in 43% and 59% treatment fractions, respectively, and more dose to bladder and rectum in 51% and 53% treatment fractions, respectively. The cumulative dose over five fractions, ∑D((Formula presented.) + (Formula presented.)) and ∑D((Formula presented.)), was always within 5% of the planned dose for all four structures for every patient. Conclusions: The dosimetric impact of tumor rotation on a large prostate cancer patient cohort was quantified in this study. These results suggest that the standard 3–5 mm CTV-PTV margin was sufficient to account for the intrafraction prostate rotation observed for this cohort of patients, provided an appropriate gating threshold was applied to correct for translational motion. Residual dose errors due to uncorrected prostate rotation were small in magnitude, which may be corrected using different treatment adaptation strategies to further improve the dosimetric accuracy.

The quality of radiotherapy delivery has been shown to significantly impact clinical outcomes including patient survival. To identify errors, institutions perform Patient Specific Quality Assurance (PSQA) assessing each individual radiotherapy plan prior to starting patient treatments. Externally administered Dosimetry Audits have found problems despite institutions passing their own PSQA. Hence a new audit concept which assesses the institution's ability to detect errors with their routine PSQA is needed.Purposefully introduced edits which simulated treatment delivery errors were embedded into radiation treatment plans of participating institutions. These were designed to produce clinically significant changes yet were mostly within treatment delivery specifications. Actual impact was centrally assessed for each plan. Institutions performed PSQA on each plan, without knowing which contained errors.Seventeen institutions using six radiation treatment planning systems and two delivery systems performed PSQA on twelve plans each. Seventeen erroneous plans (across seven institutions) passed PSQA despite causing5% increase in spinal cord dose relative to the original plans. Six plans (from four institutions) passed despite a10% increase.This novel audit concept evolves beyond testing an institution's ability to deliver a single test case, to increasing the number of errors caught by institutions themselves, thus increasing quality of radiation therapy and impacting every patient treated. Administered remotely this audit also provides advantages in cost, environmental impact, and logistics.

Background and purpose Magnetic resonance imaging (MRI)-only treatment planning is gaining in popularity in radiation oncology, with various methods available to generate a synthetic computed tomography (sCT) for this purpose. The aim of this study was to validate a sCT generation software for MRI-only radiotherapy planning of male and female pelvic cancers. The secondary aim of this study was to improve dose agreement by applying a derived relative electron and mass density (RED) curve to the sCT. Method and materials Computed tomography (CT) and MRI scans of forty patients with pelvic neoplasms were used in the study. Treatment plans were copied from the CT scan to the sCT scan for dose comparison. Dose difference at reference point, 3D gamma comparison and dose volume histogram analysis was used to validate the dose impact of the sCT. The RED values were optimised to improve dose agreement by using a linear plot. Results The average percentage dose difference at isocentre was 1.2% and the mean 3D gamma comparison with a criteria of 1%/1 mm was 84.0% ± 9.7%. The results indicate an inherent systematic difference in the dosimetry of the sCT plans, deriving from the tissue densities. With the adapted REDmod table, the average percentage dose difference was reduced to −0.1% and the mean 3D gamma analysis improved to 92.9% ± 5.7% at 1%/1 mm. Conclusions CT generation software is a viable solution for MRI-only radiotherapy planning. The option makes it relatively easy for departments to implement a MRI-only planning workflow for cancers of male and female pelvic anatomy.

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

Radiotherapy planning for lung cancer typically requires both 3D and 4D Computed Tomography (CT) to account for respiratory related movement. 4D Magnetic Resonance Imaging (MRI) with self-navigation offers a potential alternative with greater reliability in patients with irregular breathing patterns and improved soft tissue contrast. In this study 4D-CT and a 4D-MRI Radial Volumetric Interpolated Breath-hold Examination (VIBE) sequence was evaluated with a 4D phantom and 13 patient respiratory patterns, simulating tumour motion. Quantification of motion related tumour displacement in 4D-MRI and 4D-CT found no statistically significant difference in mean motion range. The results demonstrated the potential viability of 4D-MRI for lung cancer treatment planning.

Purpose Reducing margins during treatment planning to decrease dose to healthy organs surrounding the prostate can risk inadequate treatment of subclinical disease. This study aimed to investigate whether lack of dose to subclinical disease is associated with increased disease progression by using high-quality prostate radiation therapy clinical trial data to identify anatomically localized regions where dose variation is associated with prostate-specific antigen progression (PSAP). Methods and Materials Planned dose distributions for 683 patients of the Trans-Tasman Radiation Oncology Group 03.04 Randomized Androgen Deprivation and Radiotherapy (RADAR) trial were deformably registered onto a single exemplar computed tomography data set. These were divided into high-risk and intermediate-risk subgroups for analysis. Three independent voxel-based statistical tests, using permutation testing, Cox regression modeling, and least absolute shrinkage selection operator feature selection, were applied to identify regions where dose variation was associated with PSAP. Results from the intermediate-risk RADAR subgroup were externally validated by registering dose distributions from the RT01 (n = 388) and Conventional or Hypofractionated High Dose Intensity Modulated Radiotherapy for Prostate Cancer Trial (CHHiP) (n = 253) trials onto the same exemplar and repeating the tests on each of these data sets. Results Voxel-based Cox regression revealed regions where reduced dose was correlated with increased prostate-specific androgen progression. Reduced dose in regions associated with coverage at the posterior prostate, in the immediate periphery of the posterior prostate, and in regions corresponding to the posterior oblique beams or posterior lateral beam boundary, was associated with increased PSAP for RADAR and RT01 patients, but not for CHHiP patients. Reduced dose to the seminal vesicle region was also associated with increased PSAP for RADAR intermediate-risk patients. Conclusions Ensuring adequate dose coverage at the posterior prostate and immediately surrounding posterior region (including the seminal vesicles), where aggressive cancer spread may be occurring, may improve tumor control. It is recommended that particular care be taken when defining margins at the prostate posterior, acknowledging the trade-off between quality of life due to rectal dose and the preferences of clinicians and patients.

PurposeStereotactic Ablative Radiotherapy (SABR) has recently emerged as a favourable treatment option for prostate cancer patients. With higher doses delivered over fewer fractions, motion adaptation is a requirement for accurate delivery of SABR. This study compared the efficacy of multileaf collimator (MLC) tracking vs. gating as a real-time motion adaptation strategy for prostate SABR patients enrolled in a clinical trial.MethodsForty-four prostate cancer patients treated over five fractions in the TROG 15.01 SPARK trial were analysed in this study. Forty-nine fractions were treated using MLC tracking and 166 fractions were treated using beam gating and couch shifts. A time-resolved motion-encoded dose reconstruction method was used to evaluate the dose delivered using each motion adaptation strategy and compared to an estimation of what would have been delivered with no motion adaptation strategy implemented.ResultsMLC tracking and gating both delivered doses closer to the plan compared to when no motion adaptation strategy was used. Differences between MLC tracking and gating were small with differences in the mean discrepancy from the plan of -0.3% (CTV D98%), 1.4% (CTV D2%), 0.4% (PTV D95%), 0.2% (rectum V30Gy) and 0.0% (bladder V30Gy). On average, 0.5 couch shifts were required per gated fractions with a mean interruption duration of 1.8 ± 2.6 min per fraction treated using gating.ConclusionBoth MLC tracking and gating were effective strategies at improving the accuracy of the dose delivered to the target and organs at risk. While dosimetric performance was comparable, gating resulted in interruptions to treatment.Clinical trial registration numberNCT02397317.

Purpose The aim of this study was to develop and assess the performance of supervised machine learning technique to classify magnetic resonance imaging (MRI) voxels as cancerous or noncancerous using noncontrast multiparametric MRI (mp‐MRI), comprised of T2‐weighted imaging (T2WI), diffusion‐weighted imaging (DWI), and advanced diffusion tensor imaging (DTI) parameters. Materials and methods In this work, 191 radiomic features were extracted from mp‐MRI from prostate cancer patients. A comprehensive set of support vector machine (SVM) models for T2WI and mp‐MRI (T2WI + DWI, T2WI + DTI, and T2WI + DWI + DTI) were developed based on novel Bayesian parameters optimization method and validated using leave‐one‐patient‐out approach to eliminate any possible overfitting. The diagnostic performance of each model was evaluated using the area under the receiver operating characteristic curve (AUROC). The average sensitivity, specificity, and accuracy of the models were evaluated using the test data set and the corresponding binary maps generated. Finally, the SVM plus sigmoid function of the models with the highest performance were used to produce cancer probability maps. Results The T2WI + DWI + DTI models using the optimal feature subset achieved the best performance in prostate cancer detection, with the average AUROC , sensitivity, specificity, and accuracy of 0.93 ± 0.03, 0.85 ± 0.05, 0.82 ± 0.07, and 0.83 ± 0.04, respectively. The average diagnostic performance of T2WI + DTI models was slightly higher than T2WI + DWI models (+3.52%) using the optimal radiomic features. Conclusions Combination of noncontrast mp‐MRI (T2WI, DWI, and DTI) features with the framework of a supervised classification technique and Bayesian optimization method are able to differentiate cancer from noncancer voxels with high accuracy and without administration of contrast agent. The addition of cancer probability maps provides additional functionality for image interpretation, lesion heterogeneity evaluation, and treatment management.

External beam radiotherapy with photon beams is a highly accurate treatment modality, but requires extensive quality assurance programs to confirm that radiation therapy will be or was administered appropriately. In vivo dosimetry (IVD) is an essential element of modern radiation therapy because it provides the ability to catch treatment delivery errors, assist in treatment adaptation, and record the actual dose delivered to the patient. However, for various reasons, its clinical implementation has been slow and limited. The purpose of this report is to stimulate the wider use of IVD for external beam radiotherapy, and in particular of systems using electronic portal imaging devices (EPIDs). After documenting the current IVD methods, this report provides detailed software, hardware and system requirements for in vivo EPID dosimetry systems in order to help in bridging the current vendor-user gap. The report also outlines directions for further development and research. In vivo EPID dosimetry vendors, in collaboration with users across multiple institutions, are requested to improve the understanding and reduce the uncertainties of the system and to help in the determination of optimal action limits for error detection. Finally, the report recommends that automation of all aspects of IVD is needed to help facilitate clinical adoption, including automation of image acquisition, analysis, result interpretation, and reporting/documentation. With the guidance of this report, it is hoped that widespread clinical use of IVD will be significantly accelerated.

The purpose of this study was to describe the use of the VIPER software for patient-specific quality assurance (PSQA) of single-isocenter multitarget (SIMT) stereotactic radiosurgery (SRS) plans.Twenty clinical of intensity-modulated (IMRT) SIMT SRS plans were reviewed. A total of 88 brain metastases were included. Number of lesions per plan and their individual volumes ranged from 2 to 35 and from 0.03 to 32.8 cmThe averages (± 1 SD) of the 3D GPRs over the 20 SRS plans were: 99.9 ± 0.2%, 99.7 ± 0.3%, 99.6 ± 0.5%, 99.3 ± 0.9%,99.1 ± 1.6%, 99.0 ± 1.6%, and 98.5 ± 3.3%, for dose thresholds of 10%, 20%, 30%, 50%, 70%, 80% and 90% respectively.This work shows the feasibility of the VIPER software for PSQA of SIMT SRS plans, being a reliable alternative to commercially available 2D detector arrays.

The deep inspiration breath‐hold (DIBH) technique assists in sparing the heart, lungs, and liver during breast radiotherapy (RT). The quality of DIBH is currently assessed via surrogates which correlate to varying degrees with the patient's internal anatomy. Since modern linacs are equipped with an electronic portal imaging device (EPID), images of the irradiated anatomy streamed from EPIDs and analyzed in real time could significantly improve assessment of the quality of DIBH. A system has been developed to quantify the quality of DIBH during tangential breast RT by analyzing the “beam's eye view” images of the treatment fields. The system measures the lung depth (LD) and the distance from the breast surface to the posterior tangential radiation field edge (skin distance, SD) at three user‐defined locations. LD and SD measured in real time in EPID images of two RT phantoms showing different geometrical characteristics of their chest wall regions (computed tomography dose index [CTDI] and “END‐TO‐END” stereotactic body radiation therapy [E2E SBRT]) were compared with ground truth displacements provided by a precision motion platform. Performance of the new system was evaluated via static and dynamic (sine wave motion) measurements of LD and SD, covering clinical situations with stable and unstable breath‐hold. The accuracy and precision of the system were calculated as the mean and standard deviation of the differences between the ground truth and measured values. The accuracy of the static measurements of LD and SD for the CTDI phantom was 0.31 (1.09) mm [mean (standard deviation)] and –0.10 (0.14) mm, respectively. The accuracy of the static measurements for E2E SBRT phantom was 0.01 (0.18) mm and 0.05 (0.08) mm. The accuracy of the dynamic LD and SD measurements for the CTDI phantom was –0.50 (1.18) mm and 0.01 (0.12) mm, respectively. The accuracy of the dynamic measurements for E2E SBRT phantom was –0.03 (0.19) mm and 0.01 (0.11) mm.

Purpose Deep learning methods (DLMs) have recently been proposed to generate pseudo-CT (pCT) for magnetic resonance imaging (MRI) based dose planning. This study aims to evaluate and compare DLMs (U-Net and generative adversarial network [GAN]) using various loss functions (L2, single-scale perceptual loss [PL], multiscale PL, weighted multiscale PL) and a patch-based method (PBM). Methods and Materials Thirty-nine patients received a volumetric modulated arc therapy for prostate cancer (78 Gy). T2-weighted MRIs were acquired in addition to planning CTs. The pCTs were generated from the MRIs using 7 configurations: 4 GANs (L2, single-scale PL, multiscale PL, weighted multiscale PL), 2 U-Net (L2 and single-scale PL), and the PBM. The imaging endpoints were mean absolute error and mean error, in Hounsfield units, between the reference CT (CTref) and the pCT. Dose uncertainties were quantified as mean absolute differences between the dose volume histograms (DVHs) calculated from the CTref and pCT obtained by each method. Three-dimensional gamma indexes were analyzed. Results Considering the image uncertainties in the whole pelvis, GAN L2 and U-Net L2 showed the lowest mean absolute error (≤34.4 Hounsfield units). The mean errors were not different than 0 (P ≤ .05). The PBM provided the highest uncertainties. Very few DVH points differed when comparing GAN L2 or U-Net L2 DVHs and CTref DVHs (P ≤ .05). Their dose uncertainties were ≤0.6% for the prostate planning target Volume V95%, ≤0.5% for the rectum V70Gy, and ≤0.1% for the bladder V50Gy. The PBM, U-Net PL, and GAN PL presented the highest systematic dose uncertainties. The gamma pass rates were >99% for all DLMs. The mean calculation time to generate 1 pCT was 15 s for the DLMs and 62 min for the PBM. Conclusions Generating pCT for MRI dose planning with DLMs and PBM provided low-dose uncertainties. In particular, the GAN L2 and U-Net L2 provided the lowest dose uncertainties together with a low computation time.

Intrafraction motion review (IMR), a real-time 2D, motion management feature of the Varian Truebeam™ incorporates triggered imaging, automatic fiducial marker detection and automatic beam hold. With the increasing adoption of high dose per fraction stereotactic body radiotherapy (SBRT) this system provides a potential means to ensure treatment accuracy. The goal of this study was therefore to investigate and quantify key performance characteristics of IMR for prostate treatment guidance. Phantom experiments were performed with a custom Computerized Imaging Reference Systems, Inc (CIRS) pelvis phantom with implanted gold seeds and the Hexamotion™ 5D motion platform. The system accuracy was assessed statically and under typical prostate motion trajectories. The IMR functionality and marker detectability was tested under different anatomical conditions and with different imaging acquisition modes. Imaging dose for triggered imaging modes was determined using an ionisation chamber based on IPEMB dose calibration protocol for kV energies. For zero displacement, the IMR demonstrated submillimeter agreement with the known position. Similarly, dynamic motion differences between the IMR reported position and 2D trajectory displacement were within 1 mm. Static displacement in the anterior direction was reported by IMR as sinusoidal motion on the x-axis (kV angle). The 2D nature of IMR limits the ability to detect motion out of the plane of the kV image detector. Using typical clinical imaging settings, imaging dose determined at the patient surface was 2.58 mGy/frame and the corresponding IMR displayed dose was 2.63 mGy/frame. The methodology used was able to quantify the accuracy of the IMR system. The IMR was able to accurately and consistently report fiducial positions within the limitations inherent of a 2D system. IMR is fully integrated with the Truebeam system with an easy to use and efficient workflow and is clinically beneficial especially within the context of SBRT.

Purpose/Objective(s): The additional personnel and imaging procedures required for Adaptive Radiation Therapy (ART) pose a challenge for a broad implementation. We hypothesize that a change in transit fluence during the treatment course is correlated with the change of quality of life and thus can be used as a replanning trigger. Materials/Methods: Twenty-one head and neck cancer (HNC) patients filled out an MD Anderson Dysphagia Inventory (MDADI) questionnaire, before-and-after the radiotherapy treatment course. The transit fluence was measured by the Watchdog (WD) in-vivo portal dosimetry system. The patients were monitored with daily WD and weekly CBCTs. The region of interest (ROI) of each patient was defined as the outer contour of the patient between approximate spine levels C1 to C4, essentially the neck and mandible inside the beam’s eye view. The nth day integrated transit fluence change, Δϕn, and the volume change, ΔVROI, of the ROI of each patient was calculated from the corresponding WD and CBCT measurements. The correlation between MDADI scores and age, gender, planning mean dose to salivary glands sg>, weight change ΔW, ΔVROI, and Δϕn, were analyzed using the ranked-Pearson correlation. Results: No statistically significant correlation was found for age, gender and ΔW. sg> was found to have clinically important correlation with functional MDADI (ρ = −0.39, P = 0.081). ΔVROI was found to have statistically significant correlation of 0.44, 0.47 and 0.44 with global, physical and functional MDADI ( P-value < 0.05). Δϕn was found to have statistically significant ranked-correlation (−0.46, −0.46 and −0.45) with physical, functional and total MDADI ( P-value < 0.05). Conclusion: A transit fluence based decision support metric (DSM) is statistically correlated with the dysphagia risk. It can not only be used as an early signal in assisting clinicians in the ART patient selection for replanning, but also lowers the resource barrier of ART implementation.

Introduction et but de l’etude La generation de pseudo-scanographie ou tomodensitometrie synthetique a partir d’IRM est necessaire pour le calcul de la dose dans le cadre d’une radiotherapie basee sur l’IRM. De nombreuses methodes d’apprentissage profond ont ete developpees a cet effet. L’objectif de cette etude est de generer des tomodensitometries synthetiques precises avec une methode d’apprentissage profond (Pix2Pix) pour une radiotherapie de la prostate. Materiel et methodes Trente-neuf patients ayant eu une radiotherapie conformationnelle avec modulation d’intensite (RCMI ; delivrant 78 Gy) pour un cancer de la prostate ont eu une scanographie de planification et une IRM en position de traitement. Des tomodensitometries synthetiques ont ete generees a partir de l’IRM par la methode Pix2Pix (conditional generative adversarial network), perceptual loss. Les hyper parametres du modele (momentum, learning rate) ont ete optimises afin d’obtenir la meilleure qualite de tomodensitometrie synthetique. L’evaluation a porte sur la comparaison entre la scanographie de reference et la tomodensitometrie synthetique, sur des criteres d’image et de dose. Les criteres d’image etaient la moyenne des ecarts absolus et la moyenne des ecarts en unites Hounsfield pour le contour externe, les os, la prostate, la vessie et le rectum. Les criteres dosimetriques etaient les moyennes des ecarts absolus des histogrammes dose–volume (sur tomodensitometries synthetiques contre scanographie de planification), pour le volume cible previsionnel, la vessie et le rectum. Des analyses gamma ont ete realisees (locales, 1 %/1 mm et 2 %/2 mm) ainsi que des tests de Wilcoxon. Resultats et analyse statistique Le Tableau 1 presente les resultats des metriques d’images pour le contour externe, les os, la prostate, la vessie et le rectum. En ce qui concerne les criteres dosimetriques, les differences moyennes d’histogrammes dose–volume etaient de 0,5 % pour 95 % du volume cible previsionnel, 0,4 % pour le volume recevant 70 Gy (V70 Gy) du rectum et 0,1 % pour le V50 Gy de la vessie. Les taux de passe gamma etaient de 99,4 % pour le critere 1 %/1 mm et de 100 %, pour le critere 2 %/2 mm. Les gamma moyens etaient respectivement de 0,31 et 0,17. Les doses moyennes entre la scanographie de reference et la tomodensitometrie synthetique n’etaient pas significativement differentes. L’analyse statistique a montre la complexite de l’evaluation dans le rectum due a la mobilite des gaz. En effet, le cas ayant la plus grande difference de position du gaz entre la scanographie de reference et l’IRM, a montre le gamma le plus bas et la moyenne des ecarts absolus la plus elevee et inversement. Conclusion Afin de generer une tomodensitometrie synthetique a partir de l’IRM de la prostate pour le calcul de la dose, l’architecture Pix2Pix fournit une moyenne des ecarts absolus de 29,5 HU et une difference de dose inferieure a 0,3 %. Ces resultats sont parmi les meilleurs de la litterature pour une radiotherapie de la prostate. Les faibles incertitudes de dose ouvrent la voie a une utilisation clinique de la tomodensitometrie synthetique pour la planification dosimetrique, a condition qu’un controle de qualite systematique, s’affranchissant de la scanographie de reference, puisse etre mis en place.