Clinical workflow for MR-only simulation and planning in prostate

Development of Magnetic Resonance-Compatible Head Immobilization Device and Initial Experience of Magnetic Resonance-Guided Radiation Therapy for Central Nervous System Tumors

PURPOSE

We aimed to develop and investigate positional reproducibility using a fixation device (Unity Brain tumor Immobilization Device [UBID]) in patients with brain tumor undergoing magnetic resonance (MR)-guided radiation therapy (RT) with a 1.5 Tesla (T) MR-linear accelerator (MR-LINAC) to evaluate its feasibility in clinical practice and report representative cases of patients with central nervous system (CNS) tumor.

MATERIALS AND METHODS

Quantitative analysis was performed by comparing images obtained by placing only the MR phantom on the couch with those obtained by placing UBID next to the MR phantom. Twenty patients who underwent RT for CNS tumors using 1.5T MR-LINAC between June and October 2022 were retrospectively analyzed. Among them, 5 did not use UBID, whereas 15 used UBID. The positional reproducibility of UBID was evaluated using the median interfractional and intrafractional errors in the first 10 fractions.

RESULTS

Each MR quality factor of the MR phantom with UBID satisfied the criteria presented by Elekta. Median values of median shifts in the mediolateral, anteroposterior, and craniocaudal axes for interfractional errors were 2.98, 2.35, and 1.40 mm, respectively. For intrafractional errors, the median values were 0.05, 0.03, and 0.06 mm, respectively. The median values of the median rotations in pitch, roll, and yaw for both interfractional and intrafractional rotations were 0.00°. One patient diagnosed with an optic nerve sheath meningioma received RT with motion monitoring during irradiation. In 2 patients, changes in the tumor cavity and residual lesions were observed in the MRI obtained using 1.5T MR-LINAC on the day of the first treatment and immediately before the 21st fraction, respectively; therefore, offline/online adaptation was performed.

CONCLUSIONS

The reproducible and immobile UBID is clinically feasible in patients with CNS tumors receiving RT with 1.5T MR-LINAC. Based on our initial experience, we developed a workflow for 1.5T MR-LINAC treatment of CNS tumors.

Region of interest focused MRI to synthetic CT translation using regression and segmentation multi-task network

Objective. In MR-only clinical workflow, replacing CT with MR image is of advantage for workflow efficiency and reduces radiation to the patient. An important step required to eliminate CT scan from the workflow is to generate the information provided by CT via an MR image. In this work, we aim to demonstrate a method to generate accurate synthetic CT (sCT) from an MR image to suit the radiation therapy (RT) treatment planning workflow. We show the feasibility of the method and make way for a broader clinical evaluation.Approach. We present a machine learning method for sCT generation from zero-echo-time (ZTE) MRI aimed at structural and quantitative accuracies of the image, with a particular focus on the accurate bone density value prediction. The misestimation of bone density in the radiation path could lead to unintended dose delivery to the target volume and results in suboptimal treatment outcome. We propose a loss function that favors a spatially sparse bone region in the image. We harness the ability of the multi-task network to produce correlated outputs as a framework to enable localization of region of interest (RoI) via segmentation, emphasize regression of values within RoI and still retain the overall accuracy via global regression. The network is optimized by a composite loss function that combines a dedicated loss from each task.Main results. We have included 54 brain patient images in this study and tested the sCT images against reference CT on a subset of 20 cases. A pilot dose evaluation was performed on 9 of the 20 test cases to demonstrate the viability of the generated sCT in RT planning. The average quantitative metrics produced by the proposed method over the test set were-(a) mean absolute error (MAE) of 70 ± 8.6 HU; (b) peak signal-to-noise ratio (PSNR) of 29.4 ± 2.8 dB; structural similarity metric (SSIM) of 0.95 ± 0.02; and (d) Dice coefficient of the body region of 0.984 ± 0.Significance. We demonstrate that the proposed method generates sCT images that resemble visual characteristics of a real CT image and has a quantitative accuracy that suits RT dose planning application. We compare the dose calculation from the proposed sCT and the real CT in a radiation therapy treatment planning setup and show that sCT based planning falls within 0.5% target dose error. The method presented here with an initial dose evaluation makes an encouraging precursor to a broader clinical evaluation of sCT based RT planning on different anatomical regions.

Clinical Experience and Feasibility of Using 2D-kVimage Online Intervention in the Ultrafractionated Stereotactic Radiation Treatment of Prostate Cancer

PURPOSE

This study reports clinical experience and feasibility of using a 2-dimensional (2D)-kV image system with online intervention in the ultrafractionated stereotactic body radiation treatment (UF-SBRT) of prostate cancer.

METHODS AND MATERIALS

Fifteen patients with prostate cancer who had a low- to intermediate-risk marker implanted received UF-SBRT with online 2D-kV image tracking and a manual beam interruption strategy with a 2-mm motion threshold. A total of 180 kV paired setup images and 1272 intrabeam 2D-kV images were analyzed to evaluate the setup deviation and intratreatment target deviation. Correlation of expected treatment interruptions with a set of parameters (eg, image and treatment time; direction of deviation) was performed (Spearman test). A subset of the data from 22 fractions was re-evaluated to check the differences in analysis results between using the planning position and using the pretreatment setup position as a reference. Margins based on the derived system and random errors were calculated to evaluate the feasibility of the workflow in ensuring prostate coverage during treatment.

RESULTS

Mean target motion in 3D propagated from 1.0 mm (setup at 0 minutes) to 2.0 mm (beam on at 7 minutes) to 2.4 mm (end at 13.5 minutes). Out of 75 fractions, 50 were found to require beam interruption. Interruption had a strong correlation with prostate motion along the longitudinal direction and had moderate correlation with prostate motion along the vertical direction and the prostate's treatment starting position along vertical and longitudinal directions. Using the pretreatment position as a reference for intrabeam monitoring, the magnitude of motion deviation from the reference position was reduced by 0.3 mm at a vertical direction and 0.4 mm at lateral and longitudinal directions. The calculated 3D margin to ensure target coverage was 3.7 mm, 4.6 mm, and 5.0 mm in lateral, vertical, and longitudinal directions, respectively.

CONCLUSIONS

Prostate motion propagated over time. It is feasible to use a 2D-kV online intrabeam monitoring system with a proper intervention scheme to perform UF-SBRT for prostate cancer.

Clinical implementation of magnetic resonance imaging simulation for radiation oncology planning: 5 year experience

PURPOSE

Integrating magnetic resonance (MR) into radiotherapy planning has several advantages. This report details the clinical implementation of an MR simulation (MR-planning) program for external beam radiotherapy (EBRT) in one of North America's largest radiotherapy programs.

METHODS AND MATERIALS

An MR radiotherapy planning program was developed and implemented at Sunnybrook Health Sciences Center in 2016 with two dedicated wide-bore MR platforms (1.5 and 3.0 Tesla). Planning MR was sequentially implemented every 3 months for separate treatment sites, including the central nervous system (CNS), gynecologic (GYN), head and neck (HN), genitourinary (GU), gastrointestinal (GI), breast, and brachial plexus. Essential protocols and processes were detailed in this report, including clinical workflow, optimized MR-image acquisition protocols, MR-adapted patient setup, strategies to overcome risks and challenges, and an MR-planning quality assurance program. This study retrospectively reviewed simulation site data for all MR-planning sessions performed for EBRT over the past 5 years.

RESULTS

From July 2016 to December 2021, 8798 MR-planning sessions were carried out, which corresponds to 25% of all computer tomography (CT) simulations (CT-planning) performed during the same period at our institution. There was a progressive rise from 80 MR-planning sessions in 2016 to 1126 in 2017, 1492 in 2018, 1824 in 2019, 2040 in 2020, and 2236 in 2021. As a result, the relative number of planning MR/CT increased from 3% of all planning sessions in 2016 to 36% in 2021. The most common site of MR-planning was CNS (49%), HN (13%), GYN (12%), GU (12%), and others (8%).

CONCLUSION

Detailed clinical processes and protocols of our MR-planning program were presented, which have been improved over more than 5 years of robust experience. Strategies to overcome risks and challenges in the implementation process are highlighted. Our work provides details that can be used by institutions interested in implementing an MR-planning program.

The future of MRI in radiation therapy: Challenges and opportunities for the MR community

Radiation therapy is a major component of cancer treatment pathways worldwide. The main aim of this treatment is to achieve tumor control through the delivery of ionizing radiation while preserving healthy tissues for minimal radiation toxicity. Because radiation therapy relies on accurate localization of the target and surrounding tissues, imaging plays a crucial role throughout the treatment chain. In the treatment planning phase, radiological images are essential for defining target volumes and organs-at-risk, as well as providing elemental composition (e.g., electron density) information for radiation dose calculations. At treatment, onboard imaging informs patient setup and could be used to guide radiation dose placement for sites affected by motion. Imaging is also an important tool for treatment response assessment and treatment plan adaptation. MRI, with its excellent soft tissue contrast and capacity to probe functional tissue properties, holds great untapped potential for transforming treatment paradigms in radiation therapy. The MR in Radiation Therapy ISMRM Study Group was established to provide a forum within the MR community to discuss the unmet needs and fuel opportunities for further advancement of MRI for radiation therapy applications. During the summer of 2021, the study group organized its first virtual workshop, attended by a diverse international group of clinicians, scientists, and clinical physicists, to explore our predictions for the future of MRI in radiation therapy for the next 25 years. This article reviews the main findings from the event and considers the opportunities and challenges of reaching our vision for the future in this expanding field.

A deep learning approach to generate synthetic CT in low field MR-guided radiotherapy for lung cases

INTRODUCTION

This study aims to apply a conditional Generative Adversarial Network (cGAN) to generate synthetic Computed Tomography (sCT) from 0.35 Tesla Magnetic Resonance (MR) images of the thorax.

METHODS

Sixty patients treated for lung lesions were enrolled and divided into training (32), validation (8), internal (10,T_A) and external (10,T_B) test set. Image accuracy of generated sCT was evaluated computing the mean absolute (MAE) and mean error (ME) with respect the original CT. Three treatment plans were calculated for each patient considering MRI as reference image: original CT, sCT (pure sCT) and sCT with GTV density override (hybrid sCT) were used as Electron Density (ED) map. Dose accuracy was evaluated comparing treatment plans in terms of gamma analysis and Dose Volume Histogram (DVH) parameters.

RESULTS

No significant difference was observed between the test sets for image and dose accuracy parameters. Considering the whole test cohort, a MAE of 54.9 ± 10.5 HU and a ME of 4.4 ± 7.4 HU was obtained. Mean gamma passing rates for 2%/2mm, and 3%/3mm tolerance criteria were 95.5 ± 5.9% and 98.2 ± 4.1% for pure sCT, 96.1 ± 5.1% and 98.5 ± 3.9% for hybrid sCT: the difference between the two approaches was significant (p = 0.01). As regards DVH analysis, differences in target parameters estimation were found to be within 5% using hybrid approach and 20% using pure sCT.

CONCLUSION

The DL algorithm here presented can generate sCT images in the thorax with good image and dose accuracy, especially when the hybrid approach is used. The algorithm does not suffer from inter-scanner variability, making feasible the implementation of MR-only workflows for palliative treatments.

Radiation-induced prostate swelling during SBRT of the prostate

BACKGROUND

Reduced planning target volume (PTV) margins are commonly used in stereotactic body radiotherapy (SBRT) of the prostate. In addition, MR-only treatment planning is becoming more common in prostate radiotherapy and compared to CT-MRI-based contouring results in notable smaller clinical target volume (CTV). Tight PTV margins coupled with MR-only planning raise a concern whether the margins are adequate enough to cover possible volumetric changes of the prostate. The aim of this study was to evaluate the volumetric change of the prostate and its effect on PTV margin during 5x7.25 Gy SBRT of the prostate.

MATERIAL AND METHODS

Twenty patients were included in the study. Three MRI scans, first prior to treatment (baseline), second after third fraction (mid-treatment) and third after fifth fraction (end-treatment) were acquired for each patient. Prostate contours were delineated on each MRI scan and used to assess the prostate volume and maximum prostate diameter on left-right (LR), anterior-posterior (AP) and superior-inferior (SI) directions at baseline, mid- and end-treatment.

RESULTS

Median (IQR) change in the prostate volume relative to the baseline was 12.0% (3.1, 17.7) and 9.2% (2.0, 18.9) at the mid- and end-treatment, respectively, and the change was statistically significant (p = 0.004 and p = 0.020, respectively). Compared to the baseline, median increase in the maximum LR, SI and AP prostate diameters were 0.8, 2.3 and 1.5 mm at mid-treatment, and 0.5, 2.5 and 2.3 mm at end-treatment, respectively.

CONCLUSION

If prostate contouring is based solely on MRI (e.g., in MR-only protocol), additional margin of 1-2 mm should be considered to account for prostate swelling. The study is part of clinical trial NCT02319239.

A narrative review of MRI acquisition for MR-guided-radiotherapy in prostate cancer

Magnetic resonance guided radiotherapy (MRgRT), enabled by the clinical introduction of the integrated MRI and linear accelerator (MR-LINAC), is a novel technique for prostate cancer (PCa) treatment, promising to further improve clinical outcome and reduce toxicity. The role of prostate MRI has been greatly expanded from the traditional PCa diagnosis to also PCa screening, treatment and surveillance. Diagnostic prostate MRI has been relatively familiar in the community, particularly with the development of Prostate Imaging - Reporting and Data System (PI-RADS). But, on the other hand, the use of MRI in the emerging clinical practice of PCa MRgRT, which is substantially different from that in PCa diagnosis, has been so far sparsely presented in the medical literature. This review attempts to give a comprehensive overview of MRI acquisition techniques currently used in the clinical workflows of PCa MRgRT, from treatment planning to online treatment guidance, in order to promote MRI practice and research for PCa MRgRT. In particular, the major differences in the MRI acquisition of PCa MRgRT from that of diagnostic prostate MRI are demonstrated and explained. Limitations in the current MRI acquisition for PCa MRgRT are analyzed. The future developments of MRI in the PCa MRgRT are also discussed.

Artificial Intelligence in Radiation Therapy

Artificial intelligence (AI) has great potential to transform the clinical workflow of radiotherapy. Since the introduction of deep neural networks, many AI-based methods have been proposed to address challenges in different aspects of radiotherapy. Commercial vendors have started to release AI-based tools that can be readily integrated to the established clinical workflow. To show the recent progress in AI-aided radiotherapy, we have reviewed AI-based studies in five major aspects of radiotherapy including image reconstruction, image registration, image segmentation, image synthesis, and automatic treatment planning. In each section, we summarized and categorized the recently published methods, followed by a discussion of the challenges, concerns, and future development. Given the rapid development of AI-aided radiotherapy, the efficiency and effectiveness of radiotherapy in the future could be substantially improved through intelligent automation of various aspects of radiotherapy.

Prospective Clinical Feasibility Study for MRI-Only Brain Radiotherapy

OBJECTIVES

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

MATERIAL AND METHODS

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

RESULTS

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

CONCLUSION

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

Out-of-field dose and its constituent components for a 1.5 T MR-Linac

This study aims to quantify the relative contributions of phantom scatter, collimator scatter and head leakage to the out-of-field doses (OFDs) of both static fields and clinical intensity-modulated radiation therapy (IMRT) treatments in a 1.5 T MR-Linac. The OFDs of static fields were measured at increasing distances from the field edge in an MR-conditional water phantom. Inline scans at depths of dmax (14 mm), 50 and 100 mm were performed for static fields of 5 × 5, 10 × 10 and 15 × 15 cm²under three different conditions: full scatter, with phantom scatter prevented, and head leakage only. Crossline scans at isocenter and offset positions were performed in full scatter condition. EBT3 radiochromic films were placed at 100 mm depth of solid water phantom to measure the OFD of clinical IMRT plans. All water tank data were normalized to Dmax of a 10 × 10 cm²field and the film results were presented as a fraction of the target mean dose.The OFD in the inline direction varied from 3.5% (15 × 15 cm², 100 mm depth, 50 mm distance) to 0.014% (5 × 5 cm², dmax, 400 mm distance). For all static fields, the collimator scatter was higher than the phantom scatter and head leakage at a distance of 100-400 mm. Head leakage remained the smallest among the three components, except at long distances (>375 mm) with small field size. Compared to the inline scans, the crossline scans at the isocenter showed higher doses at distances longer than 80 mm. All crossline profiles at longitudinal offset positions showed a cone shape with laterally shifted maxima. The OFD of IMRT deliveries varied with different target size. For prostate stereotactic body radiation therapy (SBRT) treatment, the OFD decreased from 2% to 0.03% at a distance of 50-500 mm. The OFDs have been measured for a 1.5 T MR-Linac. The presented dosimetric data are valuable for radiation safety assessments on patients treated with the MR-Linac, such as evaluating carcinogenic risk and radiation exposure to cardiac implantable electronic devices.

Combined Compressed Sensing and SENSE to Enhance Radiation Therapy Magnetic Resonance Imaging Simulation

Purpose

To assess the effect of a combination of compressed sensing and SENSitivity Encoding (SENSE) acceleration techniques on radiation therapy magnetic resonance imaging (MRI) simulation workflows.

Methods and Materials

Thirty-seven acquisitions were performed with both SENSE-only (SENSE) and combined compressed sensing and SENSE (CS) techniques in 24 patients receiving radiation therapy MRI simulation for a wide range of disease sites. The anatomic field of view prescription and image resolution were identical for both SENSE and CS acquisitions to ensure fair comparison. The acquisition time of all images was recorded to assess time savings. For each image pair, image quality, and ability to contour were assessed by 2 radiation oncologists. Aside from direct image pair comparisons, the feasibility of using CS to improve MRI simulation protocols by increasing image resolution, field of view, and reducing motion artifacts was also evaluated.

Results

CS resulted in an average reduction of 27% in scan time with negligible changes in image quality and the ability to contour structures for RT treatment planning compared with SENSE. Physician scoring of image quality and ability to contour shows that while SENSE still has slightly better image quality compared with CS, this observed difference in image quality did not affect the ability to contour. In addition, the higher acceleration capability of CS enabled use of superior-inferior direction phase encoding in a sagittal 3-dimensional T2-weighted scan for substantially improved visibility of the prostatic urethra, which eliminated the need for a Foley catheter in most patients.

Conclusions

The combination of compressed sensing and parallel imaging resulted in marked improvements in the MRI Simulation workflow. The scan time was reduced without significantly affecting image quality in the context of ability to contour. The acceleration capabilities allowed for increased image resolution under similar scanning times as well as significantly improved urethra visualization in prostate simulations.

Delineation of prostatic calcification using quantitative susceptibility mapping: Spatial accuracy for magnetic resonance-only radiotherapy planning

To investigate the spatial accuracy of delineating prostatic calcifications by quantitative susceptibility mapping (QSM) in comparison with computed tomography (CT), we conducted phantom and human studies. Five differently‐sized spherical hydroxyapatites mimicking prostatic calcification (pseudo‐calcification) were arranged in the order of their sizes at the center of a plastic container filled with gelatin. This calcification phantom underwent magnetic resonance (MR) imaging, including the multiple spoiled gradient‐echo sequences (SPGR) for the QSM and CT as a reference. The volume of each pseudo‐calcification and center‐to‐center distance between the pseudo‐calcifications delineated by QSM and CT were measured. In the human study, eight patients with prostate cancer who underwent radiation therapy and had some prostatic calcifications were included. The patients underwent CT and SPGR and modified DIXON sequence for MR‐only simulation. The hybrid QSM processing combined with the complex signals in the SPGR and water and fat fraction maps estimated from the modified DIXON sequence were used to reconstruct the pelvic susceptibility map in humans. The threshold of CT numbers was set at 130 HU, while the QSM images were manually segmented in the calcification phantom and human studies. In the phantom study, there was an excellent agreement in the pseudo‐calcification volumes between QSM and CT (y = 1.02x – 7.38, R² = 0.99). The signal profiles had similar trends in CT and QSM. The center‐to‐center distances between the pseudo‐calcifications in the phantom were also identical in QSM and CT. The calcification volumes were almost identical between the QSM and CT in the human study (y = 0.95x – 9.32, R² = 1.00). QSM can offer geometric and volumetric accuracies to delineate prostatic calcifications, similar to CT. The prostatic calcification delineated by QSM may facilitate image‐guided radiotherapy in the MR‐only simulation workflow.

MR SIGnature MAtching (MRSIGMA) with retrospective self-evaluation for real-time volumetric motion imaging

Objective. MR SIGnature MAtching (MRSIGMA) is a real-time volumetric MRI technique to image tumor and organs at risk motion in real-time for radiotherapy applications, where a dictionary of high-resolution 3D motion states and associated motion signatures are computed first during offline training and real-time 3D imaging is performed afterwards using fast signature-only acquisition and signature matching. However, the lack of a reference image with similar spatial resolution and temporal resolution introduces significant challenges forin vivovalidation.Approach. This work proposes a retrospective self-validation for MRSIGMA, where the same data used for real-time imaging are used to create a non-real-time reference for comparison. MRSIGMA with self-validation is tested in patients with liver tumors using quantitative metrics defined on the tumor and nearby organs-at-risk structures. The dice coefficient between contours defined on the real-time MRSIGMA and non-real-time reference was used to assess motion imaging performance.Main Results. Total latency (including signature acquisition and signature matching) was between 250 and 314 ms, which is sufficient for organs affected by respiratory motion. Mean ± standard deviation dice coefficient over time was 0.74 ± 0.03 for patients imaged without contrast agent and 0.87 ± 0.03 for patients imaged with contrast agent, which demonstrated high-performance real-time motion imaging.Signficance. MRSIGMA with self-evaluation provides a means to perform real-time volumetric MRI for organ motion tracking with quantitative performance measures.

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.

Clinical experience and cost evaluation of magnetic resonance imaging -only workflow in radiation therapy planning of prostate cancer

•

Using MRI-only for prostate cancer radiation therapy planning (RTP) can reduce costs.

•

An MRI-only workflow is particularly suitable for medium-sized and large departments.

•

Omitting CT in the RTP workflow saves scanner, staff, and patient time.

Background and purpose

In radiation therapy (RT), significant improvements have been made recently particularly in the practices of planning imaging. This study aimed to conduct a cost evaluation between magnetic resonance imaging (MRI) -only and combined computed tomography (CT) and MRI workflows.

Materials and methods

The time-driven activity-based costing (TDABC) model was used to conduct a cost evaluation between the two workflows in those steps, where cost differences were expected. Costs were divided into capital costs and operational costs. The former consisted of fixed, one-time expenses, e.g. the purchase of a scanner, whereas the latter were partially based on the amount of activity consumed i.e. time required for image acquisition, image registration and structure contouring.

Results

In a review over a period of 10 years for 300 annual prostate cancer patients, the total cost of the workflow steps included in the study for an individual patient applying the MRI-only workflow was 903 € (100%), comprised of 537 € (59%) capital costs and 366 € (41%) operational costs. The corresponding total cost for an individual patient applying the CT + MRI workflow was 922 € (100%), comprised of 197 € (21%) capital costs and 726 € (79%) operational costs. In 10 years for 3000 patients, a total saving of 58,544 € (2%) was achieved with the MRI-only workflow compared with the dual imaging workflow.

Conclusions

MRI-only workflow is a feasible and economic way to perform clinical RT for localized prostate cancer, in particular for medium- and large-sized departments treating a sufficient number of patients.

Geometrical imaging accuracy and imaging and plan quality for prostate cancer on a 1.5T MRLinac in patients with a unilateral hip implant

PURPOSE

To assess the feasibility of prostate cancer radiotherapy for patients with a hip implant on an 1.5T MRI-Linac (MRL) in terms of geometrical image accuracy, image quality, and plan quality.

METHODS

Pretreatment MRI images on a 1.5T MRL and 3T MRI consisting of a T2-weighted 3D delineation scan and main magnetic field homogeneity (B0) scan were performed in 6 patients with a unilateral hip implant. System specific geometrical errors due to gradient non-linearity were determined for the MRL. Within the prostate and skin contour, B0 inhomogeneity, gradient non-linearity error and the total geometrical error (vector summation of the prior two) was determined. Image quality was determined by visually scoring the extent of implant-born image artifacts. A treatment planning study was performed on 5 patients to quantify the impact of the implant on plan quality, in which conventional MRL IMRT plans were created, as well as plans which avoid radiation through the left or right femur.

RESULTS

The total maximum geometrical error in the prostate was < 1 mm and the skin contour < 1.7 mm; in all cases the machine-specific gradient error was most dominant. The B0 error for the MRlinac MRI could partly be predicted based on the pre-treatment 3T scan. Image quality for all patients was sufficient at 1.5T MRL. Plan comparison showed that, even with avoidance of the hips, in all cases sufficient target coverage could be obtained with similar D1cc and D5cc to rectum and bladder, while V28Gy was slightly poorer in only the rectum for femur avoidance.

CONCLUSION

We showed that geometrical accuracy, image quality and plan quality for six prostate patients with a hip implant or hip fixation treated on a 1.5T MRL did not show relevant deterioration for the used image settings, which allowed safe treatment.

Patient position verification in magnetic-resonance imaging only radiotherapy of anal and rectal cancers

BACKGROUND AND PURPOSE

Magnetic resonance (MR)-only treatment pathways require either the MR-simulation or synthetic-computed tomography (sCT) as an alternative reference image for cone beam computed tomography (CBCT) patient position verification. This study assessed whether using T2 MR or sCT as CBCT reference images introduces systematic registration errors as compared to CT for anal and rectal cancers.

MATERIALS AND METHODS

A total of 32 patients (18 rectum,14 anus) received pre-treatment CT- and T2 MR- simulation. Routine treatment CBCTs were acquired. sCTs were generated using a validated research model. The local clinical registration protocol, using a grey-scale registration algorithm, was performed for 216 CBCTs using CT, MR and sCT as the reference image. Linear mixed effects modelling identified systematic differences between modalities.

RESULTS

Systematic translation and rotation differences to CT for MR were -0.3 to + 0.3 mm and -0.1 to 0.4° for anal cancers and -0.4 to 0.0 mm and 0.0 to 0.1° for rectal cancers, and for sCT were -0.4 to + 0.8 mm, -0.1 to 0.2° for anal cancers and -0.6 to + 0.2 mm, -0.1 to + 0.1° for rectal cancers.

CONCLUSIONS

T2 MR or sCT can successfully be used as reference images for anal and rectal cancer CBCT position verification with systematic differences to CT <±1 mm and <±0.5°. Clinical enabling of alternative modalities as reference images by vendors is required to reduce challenges associated with their use.

Initial clinical experience of patient-specific QA of treatment delivery in online adaptive radiotherapy using a 1.5 T MR-Linac

Purpose. This study aims to evaluate the performance of a commercial 1.5 T MR-Linac by analyzing its patient-specific quality assurance (QA) data collected during one full year of clinical operation.Methods and Materials. The patient-specific QA system consisted of offline delivery QA (DQA) and online calculation-based QA. Offline DQA was based on ArcCHECK-MR combined with an ionization chamber. Online QA was performed using RadCalc that calculated and compared the point dose calculation with the treatment planning system (TPS). A total of 24 patients with 189 treatment fractions were enrolled in this study. Gamma analysis was performed and the threshold that encompassed 95% of QA results (T95) was reported. The plan complexity metric was calculated for each plan and compared with the dose measurements to determine whether any correlation existed.Results. All point dose measurements were within 5% deviation. The mean gamma passing rates of the group data were found to be 96.8 ± 4.0% and 99.6 ± 0.7% with criteria of 2%/2mm and 3%/3mm, respectively. T95 of 87.4% and 98.2% was reported for the overall group with the two passing criteria, respectively. No statistically significant difference was found between adaptive treatments with adapt-to-position (ATP) and adapt-to-shape (ATS), whilst the category of pelvis data showed a better passing rate than other sites. Online QA gave a mean deviation of 0.2 ± 2.2%. The plan complexity metric was positively correlated with the mean dose difference whilst the complexity of the ATS cohort had larger variations than the ATP cohort.Conclusions. A patient-specific QA system based on ArcCHECK-MR, solid phantom and ionization chamber has been well established and implemented for validation of treatment delivery of a 1.5 T MR-Linac. Our QA data obtained over one year confirms that good agreement between TPS calculation and treatment delivery was achieved.

Technical Note: Validation of an automatic ACR phantom quality assurance tool for an MR-guided radiotherapy system

PURPOSE

To modify and evaluate an automatic American College of Radiology (ACR) phantom analysis toolbox for ACR quality assurance (QA) on a low-field MR-guided radiotherapy system (ViewRay).

METHODS

An open-source toolbox was modified for ACR QA of a 0.35T MRI system (ViewRay MRIdian). A total of 17 ACR datasets were evaluated, including 10 datasets acquired from different systems across the world, and seven datasets acquired at our center between 2014 and 2020. All required ACR tests, geometric accuracy (GA), high-contrast spatial resolution (HCSR), slice thickness accuracy (ST), slice position accuracy (SP), percent integral uniformity (PIU), percentage signal ghosting (PSG), and low-contrast object detectability (LCOD), were assessed manually and using the toolbox automatically. Measurements between manual and automatic analysis were compared. Precision, recall, and accuracy were calculated, where the manual results were used as the ground truth.

RESULTS

The software took less than 2 min to complete all seven tests, which usually requires 40 min or more if analyzed manually. Overall, the automatic measurement was consistent with the manual result. The absolute differences between the two measurements were 0.72 ± 0.66 (mm), 0.01 ± 0.03, 0.50 ± 0.60 (mm), 0.39 ± 0.41 (mm), 1.01 ± 1.00 (%), 0.0016 ± 0.0019, and 2.79 ± 2.29 for the seven tests. The precision of the automatic toolbox was 100% for all tests, indicating that a test would 100% pass a manual analysis if it had passed the automatic analysis. Recall and accuracy were ≥ 96% for GA, HCSR, SP, PIU, PSG, and LCOD tests, and 91% for the ST test.

CONCLUSION

An automatic ACR QA tool was adopted and evaluated for the low-field MR-guided radiotherapy (MRgRT) system. Overall, the toolbox provided comparable results as manual analysis, and reduced the processing time from over 40 min to <2 min. This toolbox holds the potential to be widely adopted either as a second check tool or partially replace human measurement for MRgRT programs using the same system.

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.

Predictors for post-treatment biopsy outcomes after prostate stereotactic body radiotherapy

PURPOSE

To investigate predictors associated with post-treatment biopsy outcomes after stereotactic body radiotherapy (SBRT) for localized prostate cancer.

MATERIALS AND METHODS

257 patients treated with prostate SBRT to dose levels of 32.5 Gy to >40 Gy in 5-6 fractions underwent a post-treatment biopsy performed approximately two years after treatment to evaluate local control status. 73 had% intermediate-risk disease (n = 187) and the remaining 17% (n = 43) and 10% (n = 27) had low-risk and high-risk disease, respectively.

RESULTS

The incidence of positive, negative, and treatment-effect post-treatment biopsies were 15.6%, 57.6%, and 26.8%, respectively. The incidence of a positive biopsy according to dose was 37.5% (n = 9/24), 21.4% (n = 6/28), 19.4% (n = 6/31), and 10.9% (n = 19/174) for 32.5 Gy, 35 Gy, 37.5 Gy, and >40 Gy, respectively. In a multivariable model, patients treated with SBRT doses of <40 Gy and those with unfavorable-intermediate-risk or high-risk disease had higher likelihood of a positive post-treatment biopsy. A positive post-SBRT biopsy was associated with a significantly higher likelihood of subsequent PSA relapse at five years (Positive biopsy: 57%, 95% CI: 29-77% compared to negative biopsy: 7%, 95% CI: 3-14%; p < 0.001).

CONCLUSION

Based on two-year post-SBRT biopsies, excellent tumor control was achieved when dose levels of 40 Gy or higher were used. Standard SBRT dose levels of 35-37.5 Gy were associated with a higher likelihood of a positive post-treatment biopsy. Two-year positive post-treatment biopsies pre-dated the development of PSA failure in the majority of patients.

An MR-only acquisition and artificial intelligence based image-processing protocol for photon and proton therapy using a low field MR

OBJECTIVE

Recent developments on synthetically generated CTs (sCT), hybrid MRI linacs and MR-only simulations underlined the clinical feasibility and acceptance of MR guided radiation therapy. However, considering clinical application of open and low field MR with a limited field of view can result in truncation of the patient's anatomy which further affects the MR to sCT conversion. In this study an acquisition protocol and subsequent MR image stitching is proposed to overcome the limited field of view restriction of open MR scanners, for MR-only photon and proton therapy.

MATERIAL AND METHODS

12 prostate cancer patients scanned with an open 0.35T scanner were included. To obtain the full body contour an enhanced imaging protocol including two repeated scans after bilateral table movement was introduced. All required structures (patient contour, target and organ at risk) were delineated on a post-processed combined transversal image set (stitched MRI). The postprocessed MR was converted into a sCT by a pretrained neural network generator. Inversely planned photon and proton plans (VMAT and SFUD) were designed using the sCT and recalculated for rigidly and deformably registered CT images and compared based on D2%, D50%, V70Gy for organs at risk and based on D2%, D50%, D98% for the CTV and PTV. The stitched MRI and the untruncated MRI were compared to the CT, and the maximum surface distance was calculated. The sCT was evaluated with respect to delineation accuracy by comparing on stitched MRI and sCT using the DICE coefficient for femoral bones and the whole body.

RESULTS

Maximum surface distance analysis revealed uncertainties in lateral direction of 1-3mm on average. DICE coefficient analysis confirms good performance of the sCT conversion, i.e. 92%, 93%, and 100% were obtained for femoral bone left and right and whole body. Dose comparison resulted in uncertainties below 1% between deformed CT and sCT and below 2% between rigidly registered CT and sCT in the CTV for photon and proton treatment plans.

DISCUSSION

A newly developed acquisition protocol for open MR scanners and subsequent Sct generation revealed good acceptance for photon and proton therapy. Moreover, this protocol tackles the restriction of the limited FOVs and expands the capacities towards MR guided proton therapy with horizontal beam lines.

MRI-guided Radiation Therapy: An Emerging Paradigm in Adaptive Radiation Oncology

Radiation therapy (RT) continues to be one of the mainstays of cancer treatment. Considerable efforts have been recently devoted to integrating MRI into clinical RT planning and monitoring. This integration, known as MRI-guided RT, has been motivated by the superior soft-tissue contrast, organ motion visualization, and ability to monitor tumor and tissue physiologic changes provided by MRI compared with CT. Offline MRI is already used for treatment planning at many institutions. Furthermore, MRI-guided linear accelerator systems, allowing use of MRI during treatment, enable improved adaptation to anatomic changes between RT fractions compared with CT guidance. Efforts are underway to develop real-time MRI-guided intrafraction adaptive RT of tumors affected by motion and MRI-derived biomarkers to monitor treatment response and potentially adapt treatment to physiologic changes. These developments in MRI guidance provide the basis for a paradigm change in treatment planning, monitoring, and adaptation. Key challenges to advancing MRI-guided RT include real-time volumetric anatomic imaging, addressing image distortion because of magnetic field inhomogeneities, reproducible quantitative imaging across different MRI systems, and biologic validation of quantitative imaging. This review describes emerging innovations in offline and online MRI-guided RT, exciting opportunities they offer for advancing research and clinical care, hurdles to be overcome, and the need for multidisciplinary collaboration.

MR-Guided Radiotherapy for Prostate Cancer

External beam radiotherapy remains the primary treatment modality for localized prostate cancer. The radiobiology of prostate carcinoma lends itself to hypofractionation, with recent studies showing good outcomes with shorter treatment schedules. However, the ability to accurately deliver hypofractionated treatment is limited by current image-guided techniques. Magnetic resonance imaging is the main diagnostic tool for localized prostate cancer and its use in the therapeutic setting offers anatomical information to improve organ delineation. MR-guided radiotherapy, with daily re-planning, has shown early promise in the accurate delivery of radiotherapy. In this article, we discuss the shortcomings of current image-guidance strategies and the potential benefits and limitations of MR-guided treatment for prostate cancer. We also recount present experiences of MR-linac workflow and the opportunities afforded by this technology.

Current Status of Anatomical Magnetic Resonance Imaging in Brachytherapy and External Beam Radiotherapy Planning and Delivery

Radiotherapy planning and delivery have dramatically improved in recent times. Imaging is key to a successful three-dimensional and increasingly four-dimensional based pathway with computed tomography embedded as the backbone modality. Computed tomography has significant limitations for many tumour sites where soft-tissue discrimination is suboptimal, and where magnetic resonance imaging (MRI) has largely superseded in the diagnostic arena. MRI is increasingly used together with computed tomography in the radiotherapy planning pathway and is now established as a prerequisite for several tumours. With the advent of combined MRI and linear accelerator (MR-linac) systems, a transition to MRI-based radiotherapy planning is becoming reality, with increasing experience and research involving these new platforms. In this overview, we aim to highlight how magnetic resonance-guided imaging has improved radiotherapy, using gynaecological malignancies to illustrate, in both external beam radiotherapy and image-guided brachytherapy, and will assess the early evidence for magnetic resonance-guided radiotherapy using combined MR-linac systems.

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 Impact of the Positional Imaging Frequency for Hypofractionated Prostate Radiotherapy - A Voxel-by-Voxel Analysis

Background

To investigate deviations between planned and applied treatment doses for hypofractionated prostate radiotherapy and to quantify dosimetric accuracy in dependence of the image guidance frequency.

Methods

Daily diagnostic in-room CTs were carried out in 10 patients in treatment position as image guidance for hypofractionated prostate radiotherapy. Fraction doses were mapped to the planning CTs and recalculated, and applied doses were accumulated voxel-wise using deformable registration. Non-daily imaging schedules were simulated by deriving position correction vectors from individual scans and used to rigidly register the following scans until the next repositioning before dose recalculation and accumulation. Planned and applied doses were compared regarding dose-volume indices and TCP and NTCP values in dependence of the imaging and repositioning frequency.

Results

Daily image-guided repositioning was associated with only negligible deviations of analyzed dose-volume parameters and conformity/homogeneity indices for the prostate, bladder and rectum. Average CTV T did not significantly deviate from the plan values, and rectum NTCPs were highly comparable, while bladder NTCPs were reduced. For non-daily image-guided repositioning, there were significant deviations in the high-dose range from the planned values. Similarly, CTV dose conformity and homogeneity were reduced. While TCPs and rectal NTCPs did not significantly deteriorate for non-daily repositioning, bladder NTCPs appeared falsely diminished in dependence of the imaging frequency.

Conclusion

Using voxel-by-voxel dose accumulation, we showed for the first time that daily image-guided repositioning resulted in only negligible dosimetric deviations for hypofractionated prostate radiotherapy. Regarding dosimetric aberrations for non-daily imaging, daily imaging is required to adequately deliver treatment.

Technical Note: Extended field-of-view (FOV) MRI distortion determination through multi-positional phantom imaging

Comprehensive characterization of geometric distortions for MRI simulators and MRI‐guided treatment delivery systems is typically performed with large phantoms that are costly and unwieldy to handle. Here we propose an easily implementable methodology for MR distortion determination of the entire imaging space of the scanner through the use of a compact commercially available distortion phantom. The MagphanRT phantom was scanned at several locations within a MR scanner. From each scan, an approximate location of the phantom was determined from a subset of the fiducial spheres. The fiducial displacements were determined, and a displacement field was fitted to the displacement data using the entire multi‐scan data set. An orthogonal polynomial expansion fitting function was used that had been augmented to include independent rigid‐body transformations for each scan. The rigid‐body portions of the displacement field were thereafter discarded, and the resultant fit then represented the distortion field. Multi‐positional scans of the phantom were used successfully to determine the distortion field with extended coverage. A single scan of the phantom covered 20 cm in its smallest dimension. By stitching together overlapping scans we extended the distortion measurements to 30 cm. No information about the absolute location or orientation of each scan was required. The method, termed the Multi‐Scan Expansion (MSE) method, can be easily applied for larger field‐of‐views (FOVs) by using a combination of larger phantom displacements and more scans. The implementation of the MSE method allows for distortion determination beyond the physical limitations of the phantom. The method is scalable to the user’s needs and does not require any specialized equipment. This approach could open up for easier determination of the distortion magnitude at distances further from the scanner’s isocenter. This is especially important in the newly proposed methodologies of MR‐only simulation in RT and in adaptive replanning in MR linac systems.

Clinical experience and workflow challenges with magnetic resonance-only radiation therapy simulation and planning for prostate cancer

BACKGROUND AND PURPOSE

Magnetic Resonance (MR)-only planning has been implemented clinically for radiotherapy of prostate cancer. However, fewer studies exist regarding the overall success rate of MR-only workflows. We report on successes and challenges of implementing MR-only workflows for prostate.

MATERIALS AND METHODS

A total of 585 patients with prostate cancer underwent an MR-only simulation and planning between 06/2016-06/2018. MR simulation included images for contouring, synthetic-CT generation and fiducial identification. Workflow interruptions occurred that required a backup CT, a re-simulation or an update to our current quality assurance (QA) process. The challenges were prospectively evaluated and classified into syn-CT generation, motion/artifacts in the MRs, fiducial QA and bowel preparation guidelines.

RESULTS

MR-only simulation was successful in 544 (93.2 %) patients. . In seventeen patients (2.9%), reconstruction of synthetic-CT failed due to patient size, femur angulation, or failure to determine the body contour. Twenty-four patients (4.1%) underwent a repeat/backup CT scan because of artifacts on the MR such as image blur due to patient motion or biopsy/surgical artifacts that hampered identification of the implanted fiducial markers. In patients requiring large coverage due to nodal involvement, inhomogeneity artifacts were resolved by using a two-stack acquisition and adaptive inhomogeneity correction. Bowel preparation guidelines were modified to address frequent rectum/gas issues due to longer MR scan time.

CONCLUSIONS

MR-only simulation has been successfully implemented for a majority of patients in the clinic. However, MR-CT or CT-only pathway may still be needed for patients where MR-only solution fails or patients with MR contraindications.

Therapeutic Radiographers at the Helm: Moving Towards Radiographer-Led MR-Guided Radiotherapy

INTRODUCTION

Magnetic resonance-guided adaptive radiotherapy (MRgART) has the potential to improve treatment processes and outcomes for a variety of tumour sites; however, it requires significant clinical resources. Magnetic resonance linear accelerator (MR-linac) treatments require a daily multidisciplinary presence for delivery. To facilitate sustainable MRgART models, agreed protocols facilitating therapeutic radiographer (RTT)-led delivery must be developed to establish a service similar to conventional image-guided radiotherapy (IGRT). This work provides a clinical perspective on the implementation of a protocol-driven 'clinician-lite' MRgART workflow at one institution.

METHODS

To identify knowledge, skills, and competence required at each step in the MRgART workflow, an interdisciplinary informal survey and needs assessment were undertaken to identify additional or enhanced skills required for MRgART, over and above those required for conventional cone-beam computed tomography-based IGRT. The MRgART pathway was critically evaluated by relevant professionals to encourage multidisciplinary input and discussion, allowing an iterative development of the RTT-led workflow. Starting with the simplest online adaptation strategy, consisting of a virtual couch shift and online replanning, clear guidelines were established for the delivery of radical prostate radiotherapy with a reduction in staff numbers present.

RESULTS

The MRgART-specific skills identified included MRI safety and screening, MR image acquisition, MRI-based anatomy, multimodality image interpretation and registration, and treatment plan evaluation. These skills were developed in RTTs via tutorials, workshops, focussed self-directed reading, teaching of colleagues, and end-to-end workflow testing. After initial treatments and discussions, roles and responsibilities of the three professional groups (clinicians, RTTs, and physicists) have evolved to achieve a 'clinician-lite' workflow for simple radical prostate treatments.

DISCUSSION

Through applying a definitive framework and establishing agreed threshold and action levels for action within anticipated treatment scenarios similar to those in cone-beam computed tomography-based IGRT, we have implemented a 'clinician-lite' workflow for simple adaptive treatments on the MR-linac. The responsibility for online plan evaluation and approval now rests with physicists and RTTs to streamline MRgART. Early evaluation of the framework after treatment of 10 patients has required minimal online clinician input (1.5% of 200 fractions delivered).

CONCLUSION

A 'clinician-lite' prostate treatment workflow has been successfully introduced on the MR-linac at our institution and will serve as a model for other tumour sites, using more complex adaptive strategies. Early indications are that this framework has the potential to improve patient throughput and efficiency. Further identification and validation of roles and responsibilities such as online contouring, and more interactive online planning, will facilitate RTTs to fully lead in the online workflow as adaptive radiotherapy becomes ever more complex.

B0 field homogeneity recommendations, specifications, and measurement units for MRI in radiation therapy

PURPOSE

The purpose is: (a) Relate magnetic resonance imaging (MRI) quality recommendations for radiation therapy (RT) to B₀ field homogeneity; (b) Evaluate manufacturer specifications of B₀ homogeneity for 34 commercial whole-body MRI systems based on the MRI quality recommendations and RT application; (c) Measure field homogeneity in five commercial MRI systems and one commercial MRI-Linac used in RT and compare the results with their B₀ homogeneity specifications.

METHODS

Magnetic resonance imaging quality recommendations for spatial integrity, image blurring, fat saturation, and null banding in RT were developed based on the literature. Guaranteed (maximum) and typical B₀ field homogeneity specifications for various diameter spherical volumes (DSVs) were provided by GE, Philips, Siemens, and Canon. For each system, the DSV that conforms to each MRI quality recommendation and anatomical RT application was estimated based on the manufacturer specifications. B₀ field homogeneity was measured on six MRI systems including Philips (1.5 T), Siemens (1.5 and 3 T), and ViewRay MRI (0.35 T) systems using 24 and 35 cm DSV spherical phantoms. Two measurement techniques were used: (a) MRI using phase contrast field mapping to measure peak-to-peak (pk-pk), volume root mean square (VRMS), and standard deviation (SD); and (b) Magnetic resonance (MR) spectroscopy by acquiring a volumetric free induction decay (FID) to measure full width at half maximum (FWHM). The measurements were used to assess: (a) conformance with the manufacturer specifications; and (b) the relationship between the various field homogeneity measurement units. Measurements were made with and without gradient shimming (gradshim) or second-order active shimming. Multiple comparisons, analysis of variance (ANOVA), and Pearson correlations were performed to assess the dependence of pk-pk, VRMS, SD, and FWHM measurements of field homogeneity on shim volume, level of shim, and MRI system.

RESULTS

For a 40 cm DSV, the B₀ homogeneity specifications ranged from 0.35 to 5 ppm (median = 0.75 ppm) VRMS for 1.5 T systems and 0.2 to 1.4 ppm (median = 0.5 ppm) VRMS for 3 T systems. The usable DSVs ranged from 16 to 49 cm (median = 35 cm) based on the image quality recommendations and the manufacturer specifications. There was general compliance between the six measured field homogeneities and manufacturer specifications although signal dephasing was observed in two systems at < 35 cm DSV. The relationships between pk-pk, VRMS, SD, and FWHM varied based on MRI system, shim volume, and quality of shim. However, VRMS and SD measurements were highly correlated.

CONCLUSIONS

The delineation of the diseased lesion from organs at risk is the main priority for RT. Therefore, field homogeneity performance for RT must minimize image blurring and image artifacts (null bands and signal dephasing) while optimizing spatial integrity and fat saturation. Based on the specifications and recommendations for field homogeneity, some MRI systems are not well suited to meet the strict demands of RT particularly for the large imaging volumes used in body MRI. VRMS and SD measurements of B₀ field homogeneity tend to be more stable and sensitive to field inhomogeneities in RT applications than pk-pk and FWHM.

Quality comparison between three-dimensional T2-weighted SPACE and two-dimensional T2-weighted turbo spin echo magnetic resonance images for the brachytherapy planning evaluation of prostate and periprostatic anatomy

PURPOSE

The purpose of this study was to compare an isotropic three-dimensional (3D) T2-weighted sequence sampling perfection with application-optimized contrasts by using flip angle evolution (SPACE) with an axial two-dimensional T2-weighted turbo spin echo (TSE) sequence with regard to overall image quality and the delineation of normal prostate and periprostatic anatomy for low-dose-rate prostate cancer brachytherapy planning evaluation.

METHODS AND MATERIALS

Patients (n = 69) with prostate cancer who had pelvic magnetic resonance imaging (MRI) for low-dose-rate brachytherapy treatment planning were included. Three radiologists independently assessed the visibility of nine anatomic structures on each sequence by using a 5-point scale and overall image quality by using a 4-point scale. The significance of the differences in diagnostic performance was tested with a Wilcoxon signed rank test.

RESULTS

No significant intersequence differences were found for most (7/9) anatomical structures and overall image quality. The mean scores for visibility of anatomical structures on the 3D SPACE and 2D TSE sequences, respectively, were as follows: the zonal anatomy (3.7; 3.9, p = 0.05), prostate capsule (3.9; 4.0, p = 0.08), neurovascular bundle (2.9; 2.9, p = 0.9), rectoprostatic angle (3.8; 3.8, p = 0.35), rectum (4.2; 4.3, p = 0.26), urethra (3.8; 3.9, p = 0.12), urinary bladder (4.6; 4.6, p = 0.61), and overall image quality (2.9; 2.9, p = 0.33). 3D SPACE was superior for delineation of the genitourinary diaphragm (3.8; 3.6, p = 0.003), whereas 2D TSE was superior for delineation of the seminal vesicles (3.5; 4.0, p < 0.0001).

CONCLUSIONS

Anatomic delineation of the prostatic and periprostatic anatomy provided by the 3D SPACE sequence is as robust in quality as that provided by a conventional 2D TSE sequence with superior delineation of the genitourinary diaphragm. For MRI-based brachytherapy treatment planning, the 3D SPACE sequence with subcentimeter isotropic resolution can replace the 2D TSE sequence and be incorporated into standard MRI protocols.

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.

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.

MRSIGMA: Magnetic Resonance SIGnature MAtching for real-time volumetric imaging

PURPOSE

To propose a real-time 3D MRI technique called MR SIGnature MAtching (MRSIGMA) for high-resolution volumetric imaging and motion tracking with very low imaging latency.

METHODS

MRSIGMA consists of two steps: (1) offline learning of a database of possible 3D motion states and corresponding motion signature ranges and (2) online matching of new motion signatures acquired in real time with prelearned motion states. Specifically, the offline learning step (non-real-time) reconstructs motion-resolved 4D images representing different motion states and assigns a unique motion range to each state. The online matching step (real-time) acquires motion signatures only and selects one of the prelearned 3D motion states for each newly acquired signature, which generates 3D images efficiently in real time. The MRSIGMA technique was evaluated on 15 golden-angle stack-of-stars liver data sets, and the performance of respiratory motion tracking with the online-generated real-time 3D MRI was compared with the corresponding 2D projections acquired in real time.

RESULTS

The total latency of generating each 3D image during online matching was about 300 ms, including acquisition of the motion signature data (~138 ms) and corresponding matching process (~150 ms). Linear correlation assessment suggested excellent correlation (R²  = 0.948) between motion displacement measured from the online-generated real-time 3D images and the 2D real-time projections.

CONCLUSION

This proof-of-concept study demonstrates the feasibility of MRSIGMA for high-resolution real-time volumetric imaging, which shifts the acquisition and reconstruction burden to an offline learning step and leaves fast online matching for online imaging with very low imaging latency. The MRSIGMA technique can potentially be used for real-time motion tracking in MRI-guided radiation therapy.

Accuracy of automatic deformable structure propagation for high-field MRI guided prostate radiotherapy

BACKGROUND

In this study we have evaluated the accuracy of automatic, deformable structure propagation from planning CT and MR scans for daily online plan adaptation for MR linac (MRL) treatment, which is an important element to minimize re-planning time and reduce the risk of misrepresenting the target due to this time pressure.

METHODS

For 12 high-risk prostate cancer patients treated to the prostate and pelvic lymph nodes, target structures and organs at risk were delineated on both planning MR and CT scans and propagated using deformable registration to three T2 weighted MR scans acquired during the treatment course. Generated structures were evaluated against manual delineations on the repeated scans using intra-observer variation obtained on the planning MR as ground truth.

RESULTS

MR-to-MR propagated structures had significant less median surface distance and larger Dice similarity index compared to CT-MR propagation. The MR-MR propagation uncertainty was similar in magnitude to the intra-observer variation. Visual inspection of the deformed structures revealed that small anatomical differences between organs in source and destination image sets were generally well accounted for while large differences were not.

CONCLUSION

Both CT and MR based propagations require manual editing, but the current results show that MR-to-MR propagated structures require fewer corrections for high risk prostate cancer patients treated at a high-field MRL.

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

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

Dosimetric Impact of Interfractional Variations for Post-prostatectomy Radiotherapy to the Prostatic Fossa-Relevance for the Frequency of Position Verification Imaging and Treatment Adaptation

Background and purpose: To analyze divergences between the planned and applied treatment doses for post-prostatectomy radiotherapy to the prostatic fossa on a voxel-by-voxel basis based on interfractional anatomic variations and imaging frequency. Materials and methods: For 10 patients receiving intensity-modulated postoperative radiotherapy to the prostatic fossa, position verification was carried out by daily in-room CT imaging in treatment position (340 fraction CTs). Applied fraction doses were recalculated on daily CT scans, and treatment doses were accumulated on a voxel-by-voxel basis after deformable image registration. To simulate weekly imaging, derived weekly position correction vectors were used to rigidly register all daily scans of the respective treatment week onto the planning CT before dose accumulation. Detailed dose statistics of the prescribed and applied treatment doses were compared in relation to the frequency of position verification imaging. Derived NTCP and P_injury values were calculated for the rectum and bladder. Results: Despite a large variability in the pelvic anatomy, daily CT-based patient repositioning resulted in largely negligible deviations of the analyzed dose-volume, conformity, and uniformity parameters from the planned doses for post-prostatectomy radiotherapy, and only the bladder exhibited significant increases in the accumulated mean and median doses. Derived NTCP for the applied doses to the rectum and bladder and P_injury values did not significantly deviate from the treatment plan. In contrast, weekly CT-based repositioning resulted in significant decreases of the PTV coverage and dose conformity as well as large deviations of the applied doses to the rectum and bladder from the planned doses. Consecutively, NTCP for the rectum and P_injury were found falsely reduced for weekly patient repositioning. Conclusions: Our data indicate for the first time in a voxel-by-voxel analysis that daily imaging is required for reliable adaptive delivery of intensity-modulated radiotherapy to the prostatic fossa. This work will help guiding adaptive treatment strategies for post-prostatectomy radiotherapy.

A Systematic Review of the Clinical Implementation of Pelvic Magnetic Resonance Imaging-Only Planning for External Beam Radiation Therapy

The use of magnetic resonance (MR) imaging scans alone for radiation therapy treatment planning (MR-only planning) has been highlighted as one method of improving patient outcomes. Recent technologic advances have meant that introducing MR-only planning to the clinic is becoming a reality, with several specialist radiation therapy clinics using this technique for treatment. As such, substantial efforts are being made to introduce this technique into wide-spread clinical implementation. A systematic review of publications investigating the clinical implementation of pelvic MR-only radiation therapy treatment planning was undertaken following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The Medline, Embase, Scopus, Science Direct, Cumulative Index to Nursing and Allied Health Literature, and Web of Science databases were searched (timespan: all years to January 2, 2019). Twenty-six articles met the inclusion criteria. The studies were grouped into the following categories: (1) MR acquisition and synthetic computed tomography generation verification, (2) MR distortion quantification and phantom development, (3) clinical validation of patient treatment positioning in an MR-only workflow, and (4) MR-only commissioning processes. Key conclusions from this review are (1) MR-only planning has been implemented clinically for prostate cancer treatments; (2) a substantial amount of work remains to translate MR-only planning into widespread clinical implementation for all pelvic sites; (3) MR scanner distortions are no longer a barrier to MR-only planning, but they must be managed appropriately; (4) MR-only-based patient positioning verification shows promise, but limited evidence is reported in the literature and further investigation is required; and (5) a number of MR-only commissioning processes have been reported, which can aid centers as they undertake local commissioning; however, this needs to be formalized in guidance from national bodies.

Early Tolerance and Tumor Control Outcomes with High-dose Ultrahypofractionated Radiation Therapy for Prostate Cancer

BACKGROUND

Studies using stereotactic body radiotherapy (SBRT) dose escalation in in low- and intermediate-risk prostate cancer patients have indicated favorable outcomes.

OBJECTIVE

To evaluate tolerance and tumor control outcomes in low- and intermediate-risk prostate cancer patients treated with high-dose SBRT following our phase 1 trial.

DESIGN, SETTING, AND PARTICIPANTS

A total of 551 patients with low- or intermediate-risk prostate cancer were treated with SBRT.

INTERVENTION

Treatment with 37.5-40Gy SBRT in five fractions directed to the prostate and seminal vesicles.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Outcome measurements included acute toxicities (<3 mo after radiotherapy [RT]) and late toxicities (>3 mo after RT) and tumor control evaluation (prostate-specific antigen [PSA] levels at 3-6-mo intervals and post-treatment prostate biopsy at 2yr).

RESULTS AND LIMITATIONS

Acute grade 2 gastrointestinal (GI) toxicities occurred in 1.8% of patients, and late grade 2 and 3 GI toxicities were observed in 3.4% and 0.4% of patients, respectively. Acute grade 2 genitourinary (GU) toxicities occurred in 10% of patients, and grade 3 acute GU toxicities were observed in 0.7% of patients. Late grade 2 and 3 GU toxicities were observed in 21.1% and 2.5% of patients, respectively. The use of a hydrogel rectal spacer was significantly associated with reduced late GI toxicity and lower odds of developing late GU toxicity. The median follow-up was 17 mo, and 53% of those with at least 2yr of follow-up (103/193) had a biopsy performed. The 5-yr cumulative incidence of PSA failure was 2.1%, and the incidence of a positive 2-yr treatment biopsy was 12%. Limitations to this report include its retrospective nature and short follow-up time.

CONCLUSIONS

Favorable short-term outcomes were achieved with high-dose SBRT for low- and intermediate-risk disease. Severe late toxicities were observed and favorable tumor control was found.

PATIENT SUMMARY

We utilized stereotactic body radiotherapy, a form of external beam radiotherapy that delivers highly targeted high-dose treatment to the prostate, to treat over 500 localized prostate cancer patients in five sessions over 1.5 wk. Treatments were well tolerated without significant urinary or rectal side effects. Nearly 90% of those who underwent biopsies after treatment did not demonstrate residual active disease.

Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy

BACKGROUND AND PURPOSE

Magnetic resonance (MR) only radiation therapy for prostate treatment provides superior contrast for defining targets and organs-at-risk (OARs). This study aims to develop a deep learning model to leverage this advantage to automate the contouring process.

MATERIALS AND METHODS

Six structures (bladder, rectum, urethra, penile bulb, rectal spacer, prostate and seminal vesicles) were contoured and reviewed by a radiation oncologist on axial T2-weighted MR image sets from 50 patients, which constituted expert delineations. The data was split into a 40/10 training and validation set to train a two-dimensional fully convolutional neural network, DeepLabV3+, using transfer learning. The T2-weighted image sets were pre-processed to 2D false color images to leverage pre-trained (from natural images) convolutional layers' weights. Independent testing was performed on an additional 50 patient's MR scans. Performance comparison was done against a U-Net deep learning method. Algorithms were evaluated using volumetric Dice similarity coefficient (VDSC) and surface Dice similarity coefficient (SDSC).

RESULTS

When comparing VDSC, DeepLabV3+ significantly outperformed U-Net for all structures except urethra (P < 0.001). Average VDSC was 0.93 ± 0.04 (bladder), 0.83 ± 0.06 (prostate and seminal vesicles [CTV]), 0.74 ± 0.13 (penile bulb), 0.82 ± 0.05 (rectum), 0.69 ± 0.10 (urethra), and 0.81 ± 0.1 (rectal spacer). Average SDSC was 0.92 ± 0.1 (bladder), 0.85 ± 0.11 (prostate and seminal vesicles [CTV]), 0.80 ± 0.22 (penile bulb), 0.87 ± 0.07 (rectum), 0.85 ± 0.25 (urethra), and 0.83 ± 0.26 (rectal spacer).

CONCLUSION

A deep learning-based model produced contours that show promise to streamline an MR-only planning workflow in treating prostate cancer.