Prostate volume contouring: a 3D analysis of segmentation using 3DTRUS, CT, and MR

Manual prostate MRI segmentation by readers with different experience: a study of the learning progress

OBJECTIVE

To evaluate the learning progress of less experienced readers in prostate MRI segmentation.

MATERIALS AND METHODS

One hundred bi-parametric prostate MRI scans were retrospectively selected from the Göteborg Prostate Cancer Screening 2 Trial (single center). Nine readers with varying degrees of segmentation experience were involved: one expert radiologist, two experienced radiology residents, two inexperienced radiology residents, and four novices. The task was to segment the whole prostate gland. The expert's segmentations were used as reference. For all other readers except three novices, the 100 MRI scans were divided into five rounds (cases 1-10, 11-25, 26-50, 51-76, 76-100). Three novices segmented only 50 cases (three rounds). After each round, a one-on-one feedback session between the expert and the reader was held, with feedback on systematic errors and potential improvements for the next round. Dice similarity coefficient (DSC) > 0.8 was considered accurate.

RESULTS

Using DSC > 0.8 as the threshold, the novices had a total of 194 accurate segmentations out of 250 (77.6%). The residents had a total of 397/400 (99.2%) accurate segmentations. In round 1, the novices had 19/40 (47.5%) accurate segmentations, in round 2 41/60 (68.3%), and in round 3 84/100 (84.0%) indicating learning progress.

CONCLUSIONS

Radiology residents, regardless of prior experience, showed high segmentation accuracy. Novices showed larger interindividual variation and lower segmentation accuracy than radiology residents. To prepare datasets for artificial intelligence (AI) development, employing radiology residents seems safe and provides a good balance between cost-effectiveness and segmentation accuracy. Employing novices should only be considered on an individual basis.

CLINICAL RELEVANCE STATEMENT

Employing radiology residents for prostate MRI segmentation seems safe and can potentially reduce the workload of expert radiologists. Employing novices should only be considered on an individual basis.

KEY POINTS

• Using less experienced readers for prostate MRI segmentation is cost-effective but may reduce quality. • Radiology residents provided high accuracy segmentations while novices showed large inter-reader variability. • To prepare datasets for AI development, employing radiology residents seems safe and might provide a good balance between cost-effectiveness and segmentation accuracy while novices should only be employed on an individual basis.

Inter-observer effects in needle reconstruction for temporary prostate brachytherapy: Dosimetric implications and adaptive CBCT-TRUS registration solutions

PURPOSE

To investigate geometric and dosimetric inter-observer variability in needle reconstruction for temporary prostate brachytherapy. To assess the potential of registrations between transrectal ultrasound (TRUS) and cone-beam computed tomography (CBCT) to support implant reconstructions.

METHODS AND MATERIALS

The needles implanted in 28 patients were reconstructed on TRUS by three physicists. Corresponding geometric deviations and associated dosimetric variations to prostate and organs at risk (urethra, bladder, rectum) were analyzed. To account for the found inter-observer variability, various approaches (template-based, probe-based, marker-based) for registrations of CBCT to TRUS were investigated regarding the respective needle transfer accuracy in a phantom study. Three patient cases were examined to assess registration accuracy in-vivo.

RESULTS

Geometric inter-observer deviations >1 mm and >3 mm were found for 34.9% and 3.5% of all needles, respectively. Prostate dose coverage (changes up to 7.2%) and urethra dose (partly exceeding given dose constraints) were most affected by associated dosimetric changes. Marker-based and probe-based registrations resulted in the phantom study in high mean needle transfer accuracies of 0.73 mm and 0.12 mm, respectively. In the patient cases, the marker-based approach was the superior technique for CBCT-TRUS fusions.

CONCLUSION

Inter-observer variability in needle reconstruction can substantially affect dosimetry for individual patients. Especially marker-based CBCT-TRUS registrations can help to ensure accurate reconstructions for improved treatment planning.

Impact of Relative Volume Difference Between Magnetic Resonance Imaging and Three-dimensional Transrectal Ultrasound Segmentation on Clinically Significant Prostate Cancer Detection in Fusion Magnetic Resonance Imaging-targeted Biopsy

BACKGROUND

Segmentation of three-dimensional (3D) transrectal ultrasound (TRUS) images is known to be challenging, and the clinician often lacks a reliable and easy-to-use indicator to assess its accuracy during the fusion magnetic resonance imaging (MRI)-targeted prostate biopsy procedure.

OBJECTIVE

To assess the effect of the relative volume difference between 3D-TRUS and MRI segmentation on the outcome of a targeted biopsy.

DESIGN, SETTING, AND PARTICIPANTS

All adult males who underwent an MRI-targeted prostate biopsy for clinically suspected prostate cancer between February 2012 and July 2021 were consecutively included.

INTERVENTION

All patients underwent a fusion MRI-targeted prostate biopsy with a Koelis device.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Three-dimensional TRUS and MRI prostate volumes were calculated using 3D prostate models issued from the segmentations. The primary outcome was the relative segmentation volume difference (SVD) between transrectal ultrasound and MRI divided by the MRI volume (SVD = MRI volume - TRUS volume/MRI volume) and its correlation with clinically significant prostate cancer (eg, International Society of Urological Pathology [ISUP] ≥2) positiveness on targeted biopsy cores.

RESULTS AND LIMITATIONS

Overall, 1721 patients underwent a targeted biopsy resulting in a total of 5593 targeted cores. The median relative SVD was significantly lower in patients diagnosed with clinically significant prostate cancer than in those with ISUP 0-1: (6.7% [interquartile range {IQR} -2.7, 13.6] vs 8.0% [IQR 3.3, 16.4], p < 0.01). A multivariate regression analysis showed that a relative SVD of >10% of the MRI volume was associated with a lower detection rate of clinically significant prostate cancer (odds ratio = 0.74 [95% confidence interval: 0.55-0.98]; p = 0.038).

CONCLUSIONS

A relative SVD of >10% of the MRI segmented volume was associated with a lower detection rate of clinically significant prostate cancer on targeted biopsy cores. The relative SVD can be used as a per-procedure quality indicator of 3D-TRUS segmentation.

PATIENT SUMMARY

A discrepancy of ≥10% between segmented magnetic resonance imaging and transrectal ultrasound volume is associated with a reduced ability to detect significant prostate cancer on targeted biopsy cores.

Prostate volume variation during 1.5T MR-guided adaptive stereotactic body radiotherapy (SBRT) and correlation with treatment toxicity

INTRODUCTION

To evaluate prostate volume change during daily-adaptive prostate SBRT on 1.5 T MR-linac and to correlate it with treatment toxicity.

METHODS

a series of patients affected by low-to-intermediate risk prostate cancer was treated by 5-fraction SBRT within a prospective study (Prot. n° 23748). Total dose was 35 Gy and 36.25 Gy delivered every day or on alternate days. Treatment toxicity was recorded with the following patient reported outcomes (PROMs): IPSS, ICIQ-SF, and EPIC-26.

RESULTS

254 patients were included in the analysis. Baseline median CTV volume was 55 cc (range 15.3-163.3). Mean prostate volume were 58.9 cc, and 62.7 cc at first and last fraction respectively (mean volume increase 6.4 %; p = <0.0001). We observed prostate swelling (mean 15.4 % increase) in 50 % of cases, stable volume (≤5% volume change) in 39 % of patients, and prostate shrinkage in 11 % of cases (mean 12.2 % reduction). Baseline CTV > 55 cc showed a trend towards higher CTV shrinkage (-10.5 % versus -14.5 %; p = 0.052). We found no correlation between CTV change and PROMs. Prostate swelling was generally compensated by the planned PTV expansion, even though the mean setup volume dropped from 47.4 cc to 38.9 cc at last fraction, with few cases not covered by initial setup margins.

CONCLUSION

The present study reported a significant prostate volume change during prostate SBRT on 1.5T MR-linac. We observed both prostate swelling in half of cases and few cases of prostate shrinkage. No correlations were found with PROMs in this population treatment with daily-adaptive strategy.

Uncertainty in magnetic resonance imaging-based prostate postimplant dosimetry: Results of a 10-person human observer study, and comparisons with automatic postimplant dosimetry

PURPOSE

Uncertainties in postimplant quality assessment (QA) for low-dose-rate prostate brachytherapy (LDRPBT) are introduced at two steps: seed localization and contouring. We quantified how interobserver variability (IoV) introduced in both steps impacts dose-volume-histogram (DVH) parameters for MRI-based LDRPBT, and compared it with automatically derived DVH parameters.

METHODS AND MATERIALS

Twenty-five patients received MRI-based LDRPBT. Seven clinical observers contoured the prostate and four organs at risk, and 4 dosimetrists performed seed localization, on each MRI. Twenty-eight unique manual postimplant QAs were created for each patient from unique observer pairs. Reference QA and automatic QA were also performed for each patient. IoV of prostate, rectum, and external urinary sphincter (EUS) DVH parameters owing to seed localization and contouring was quantified with coefficients of variation. Automatically derived DVH parameters were compared with those of the reference plans.

RESULTS

Coefficients of variation (CoVs) owing to contouring variability (CoVcontours) were significantly higher than those due to seed localization variability (CoVseeds) (median CoVcontours vs. median CoVseeds: prostate D90-15.12% vs. 0.65%, p < 0.001; prostate V100-5.36% vs. 0.37%, p < 0.001; rectum V100-79.23% vs. 8.69%, p < 0.001; EUS V200-107.74% vs. 21.18%, p < 0.001). CoVcontours were lower when the contouring observers were restricted to the 3 radiation oncologists, but were still markedly higher than CoVseeds. Median differences in prostate D90, prostate V100, rectum V100, and EUS V200 between automatically computed and reference dosimetry parameters were 3.16%, 1.63%, -0.00 mL, and -0.00 mL, respectively.

CONCLUSIONS

Seed localization introduces substantially less variability in postimplant QA than does contouring for MRI-based LDRPBT. While automatic seed localization may potentially help improve workflow efficiency, it has limited potential for improving the consistency and quality of postimplant dosimetry.

Dosimetric and workflow impact of synthetic-MRI use in prostate high-dose-rate brachytherapy

PURPOSE

Target and organ delineation during prostate high-dose-rate (HDR) brachytherapy treatment planning can be improved by acquiring both a postimplant CT and MRI. However, this leads to a longer treatment delivery workflow and may introduce uncertainties due to anatomical motion between scans. We investigated the dosimetric and workflow impact of MRI synthesized from CT for prostate HDR brachytherapy.

METHODS AND MATERIALS

Seventy-eight CT and T2-weighted MRI datasets from patients treated with prostate HDR brachytherapy at our institution were retrospectively collected to train and validate our deep-learning-based image-synthesis method. Synthetic MRI was assessed against real MRI using the dice similarity coefficient (DSC) between prostate contours drawn using both image sets. The DSC between the same observer's synthetic and real MRI prostate contours was compared with the DSC between two different observers' real MRI prostate contours. New treatment plans were generated targeting the synthetic MRI-defined prostate and compared with the clinically delivered plans using target coverage and dose to critical organs.

RESULTS

Variability between the same observer's prostate contours from synthetic and real MRI was not significantly different from the variability between different observer's prostate contours on real MRI. Synthetic MRI-planned target coverage was not significantly different from that of the clinically delivered plans. There were no increases above organ institutional dose constraints in the synthetic MRI plans.

CONCLUSIONS

We developed and validated a method for synthesizing MRI from CT for prostate HDR brachytherapy treatment planning. Synthetic MRI use may lead to a workflow advantage and removal of CT-to-MRI registration uncertainty without loss of information needed for target delineation and treatment planning.

Stability of Multi-Parametric Prostate MRI Radiomic Features to Variations in Segmentation

Stability analysis remains a fundamental step in developing a successful imaging biomarker to personalize oncological strategies. This study proposes an in silico contour generation method for simulating segmentation variations to identify stable radiomic features. Ground-truth annotation provided for the whole prostate gland on the multi-parametric MRI sequences (T2w, ADC, and SUB-DCE) were perturbed to mimic segmentation differences observed among human annotators. In total, we generated 15 synthetic contours for a given image-segmentation pair. One thousand two hundred twenty-four unfiltered/filtered radiomic features were extracted applying Pyradiomics, followed by stability assessment using ICC(1,1). Stable features identified in the internal population were then compared with an external population to discover and report robust features. Finally, we also investigated the impact of a wide range of filtering strategies on the stability of features. The percentage of unfiltered (filtered) features that remained robust subjected to segmentation variations were T2w-36% (81%), ADC-36% (94%), and SUB-43% (93%). Our findings suggest that segmentation variations can significantly impact radiomic feature stability but can be mitigated by including pre-filtering strategies as part of the feature extraction pipeline.

Comparison of automated segmentation techniques for magnetic resonance images of the prostate

BACKGROUND

Contouring of anatomical regions is a crucial step in the medical workflow and is both time-consuming and prone to intra- and inter-observer variability. This study compares different strategies for automatic segmentation of the prostate in T2-weighted MRIs.

METHODS

This study included 100 patients diagnosed with prostate adenocarcinoma who had undergone multi-parametric MRI and prostatectomy. From the T2-weighted MR images, ground truth segmentation masks were established by consensus from two expert radiologists. The prostate was then automatically contoured with six different methods: (1) a multi-atlas algorithm, (2) a proprietary algorithm in the Syngo.Via medical imaging software, and four deep learning models: (3) a V-net trained from scratch, (4) a pre-trained 2D U-net, (5) a GAN extension of the 2D U-net, and (6) a segmentation-adapted EfficientDet architecture. The resulting segmentations were compared and scored against the ground truth masks with one 70/30 and one 50/50 train/test data split. We also analyzed the association between segmentation performance and clinical variables.

RESULTS

The best performing method was the adapted EfficientDet (model 6), achieving a mean Dice coefficient of 0.914, a mean absolute volume difference of 5.9%, a mean surface distance (MSD) of 1.93 pixels, and a mean 95th percentile Hausdorff distance of 3.77 pixels. The deep learning models were less prone to serious errors (0.854 minimum Dice and 4.02 maximum MSD), and no significant relationship was found between segmentation performance and clinical variables.

CONCLUSIONS

Deep learning-based segmentation techniques can consistently achieve Dice coefficients of 0.9 or above with as few as 50 training patients, regardless of architectural archetype. The atlas-based and Syngo.via methods found in commercial clinical software performed significantly worse (0.855[Formula: see text]0.887 Dice).

AAPM Task Group Report 303 endorsed by the ABS: MRI Implementation in HDR Brachytherapy-Considerations from Simulation to Treatment

The Task Group (TG) on Magnetic Resonance Imaging (MRI) Implementation in High Dose Rate (HDR) Brachytherapy - Considerations from Simulation to Treatment, TG 303, was constituted by the American Association of Physicists in Medicine's (AAPM's) Science Council under the direction of the Therapy Physics Committee, the Brachytherapy Subcommittee, and the Working Group on Brachytherapy Clinical Applications. The TG was charged with developing recommendations for commissioning, clinical implementation, and on-going quality assurance (QA). Additionally, the TG was charged with describing HDR brachytherapy (BT) workflows and evaluating practical consideration that arise when implementing MR imaging. For brevity, the report is focused on the treatment of gynecologic and prostate cancer. The TG report provides an introduction and rationale for MRI implementation in BT, a review of previous publications on topics including available applicators, clinical trials, previously published BT related TG reports, and new image guided recommendations beyond CT based practices. The report describes MRI protocols and methodologies, including recommendations for the clinical implementation and logical considerations for MR imaging for HDR BT. Given the evolution from prescriptive to risk-based QA,¹ an example of a risk-based analysis using MRI-based, prostate HDR BT is presented. In summary, the TG report is intended to provide clear and comprehensive guidelines and recommendations for commissioning, clinical implementation, and QA for MRI-based HDR BT that may be utilized by the medical physics community to streamline this process. This report is endorsed by the American Brachytherapy Society (ABS). This article is protected by copyright. All rights reserved.

Autonomous Prostate Segmentation in 2D B-Mode Ultrasound Images

Prostate brachytherapy is a treatment for prostate cancer; during the planning of the procedure, ultrasound images of the prostate are taken. The prostate must be segmented out in each of the ultrasound images, and to assist with the procedure, an autonomous prostate segmentation algorithm is proposed. The prostate contouring system presented here is based on a novel superpixel algorithm, whereby pixels in the ultrasound image are grouped into superpixel regions that are optimized based on statistical similarity measures, so that the various structures within the ultrasound image can be differentiated. An active shape prostate contour model is developed and then used to delineate the prostate within the image based on the superpixel regions. Before segmentation, this contour model was fit to a series of point-based clinician-segmented prostate contours exported from conventional prostate brachytherapy planning software to develop a statistical model of the shape of the prostate. The algorithm was evaluated on nine sets of in vivo prostate ultrasound images and compared with manually segmented contours from a clinician, where the algorithm had an average volume difference of 4.49 mL or 10.89%.

Technical note: The effect of image annotation with minimal manual interaction for semiautomatic prostate segmentation in CT images using fully convolutional neural networks

PURPOSE

The goal is to study the performance improvement of a deep learning algorithm in three-dimensional (3D) image segmentation through incorporating minimal user interaction into a fully convolutional neural network (CNN).

METHODS

A U-Net CNN was trained and tested for 3D prostate segmentation in computed tomography (CT) images. To improve the segmentation accuracy, the CNN's input images were annotated with a set of border landmarks to supervise the network for segmenting the prostate. The network was trained and tested again with annotated images after 5, 10, 15, 20, or 30 landmark points were used.

RESULTS

Compared to fully automatic segmentation, the Dice similarity coefficient increased up to 9% when 5-30 sparse landmark points were involved, with the segmentation accuracy improving as more border landmarks were used.

CONCLUSIONS

When a limited number of sparse border landmarks are used on the input image, the CNN performance approaches the interexpert observer difference observed in manual segmentation.

CT measurement of prostate volume using OsiriX® viewer is reliable, repeatable, and not dependent on observer, CT protocol, or contrast enhancement in dogs

Computed tomography (CT) is an established method for evaluating dogs with suspected prostatic disease; however, publications assessing the effects of varying factors on prostate volume measurements are lacking. The objectives of this two-part, observer agreement, methods comparison study were to assess observer agreement and the effects of varying CT technical parameters for volume measurements of canine prostate glands on CT images using OsiriX^® DICOM viewer software. In the first retrospective study, two observers measured prostate volumes of 13 client-owned dogs thrice on noncontrast and contrast CT images. In the second prospective study, two observers measured the prostate volume of 10 cadavers using five different CT protocols and eight cadavers using three slice thicknesses. Observer agreement analyses were performed, and prostatic CT volume measurements were compared with water displacement volume measurements. Intra- and interobserver variability and the effect of contrast enhancement were found to be minimal when a one-way analysis of variance model and intraclass correlation coefficients were used. No significant differences emerged between different protocols and slice thicknesses using a linear mixed effects model. When the prostate CT volume was compared using a Bland-Altman plot with the reference volume acquired by the water displacement method, agreement without consistent bias between the methods was shown, and over 90% of measurements were located within the 95% limits of agreement. The findings supported using OsiriX^® software for CT prostatic volume measurements in dogs.

The one hundred most cited publications in prostate brachytherapy

PURPOSE

The aim of this study is to identify the leaders in research on prostate brachytherapy through a bibliometric analysis of the top 100 most cited publications in the field.

METHODS AND MATERIALS

A broad search was performed with the term "prostate brachytherapy" using the Web of Science database to generate wide-ranging results that were reviewed by reading the abstracts and, if necessary, the articles to select the top 100 most cited publications.

RESULTS

The median of the total citation count was 187 (range 132-1464). The median citation per year index (citations/year since publication) was 13.5 (range 6.3-379.0). In all publications, the first author was also the corresponding author. The top publishing countries of the first author included the United States (n = 78), Canada (n = 6), the UK (n = 5), and Germany (n = 4). The journal with the most publications was the International Journal of Radiation Oncology Biology Physics (n = 38). There were 27 more publications on low-dose-rate (LDR) than on high-dose-rate (HDR) (43 vs 16) among the top 100. HDR publications had only one first author that had three articles in comparison to LDR publications, which had four first authors, each with three articles on LDR. The United States was the leading country in 43.8% of HDR publications (n = 7) and 88.4% of LDR publications (n = 38).

CONCLUSIONS

Our bibliometric analysis of the top 100 most cited publications clearly demonstrates the North American dominance in the publications of prostate brachytherapy, especially in LDR. However, European first authors were more frequent in HDR publications.

Absence of prostate oedema obviates the need for delay between fiducial marker insertion and radiotherapy simulation

INTRODUCTION

Fiducial markers (FMs) are commonly inserted into the prostate for image guided radiation therapy. This study aimed to quantify prostate oedema immediately following FM insertion compared to prostate volumes measured a week later, at the time of simulation for radiation therapy.

METHODS

Thirty patients underwent a verification computed tomography (VCT) scan in treatment position immediately after the fiducial insertion and their planning computed tomography scan (PCT) one week after. Patient data sets were retrospectively evaluated, comparing prostate volumes and planning target volumes (PTV). Volumes were delineated by a single radiation oncologist, blinded to whether the scan was VCT or PCT. Distances between the FMs were measured on both scans. Descriptive statistics described the data, DICE similarity co-efficient (DSC) calculated, and paired t-tests were used to compare paired data.

RESULTS

The median prostate volume was 35.09 cc and 36.31 cc for VCT and PCT data sets, respectively, and median PTV was 118.56 cc and 127.04 cc for VCT and PCT, respectively. There was no significant difference in prostate volumes (P = 0.3037) or PTV (P = 0.1279), with a DSC of 0.87 (range 0.76-0.91) and 0.91 (range 0.85 to 0.95), respectively. Similarly, there was no significant difference in distance between fiducial markers (P > 0.05).

CONCLUSION

This study demonstrates no statistically significant difference in prostate or PTV volumes (P > 0.05) between the CT acquired at fiducial marker insertion compared with the CT acquired a week later. Therefore, oedema is not significant enough to justify a delay between FM insertion and simulation.

Tumor Control Probability Modeling and Systematic Review of the Literature of Stereotactic Body Radiation Therapy for Prostate Cancer

PURPOSE

Dose escalation improves localized prostate cancer disease control, and moderately hypofractionated external beam radiation is noninferior to conventional fractionation. The evolving treatment approach of ultrahypofractionation with stereotactic body radiation therapy (SBRT) allows possible further biological dose escalation (biologically equivalent dose [BED]) and shortened treatment time.

METHODS AND MATERIALS

The American Association of Physicists in Medicine Working Group on Biological Effects of Hypofractionated Radiation Therapy/SBRT included a subgroup to study the prostate tumor control probability (TCP) with SBRT. We performed a systematic review of the available literature and created a dose-response TCP model for the endpoint of freedom from biochemical relapse. Results were stratified by prostate cancer risk group.

RESULTS

Twenty-five published cohorts were identified for inclusion, with a total of 4821 patients (2235 with low-risk, 1894 with intermediate-risk, and 446 with high-risk disease, when reported) treated with a variety of dose/fractionation schemes, permitting dose-response modeling. Five studies had a median follow-up of more than 5 years. Dosing regimens ranged from 32 to 50 Gy in 4 to 5 fractions, with total BED (α/β = 1.5 Gy) between 183.1 and 383.3 Gy. At 5 years, we found that in patients with low-intermediate risk disease, an equivalent doses of 2 Gy per fraction (EQD2) of 71 Gy (31.7 Gy in 5 fractions) achieved a TCP of 90% and an EQD2 of 90 Gy (36.1 Gy in 5 fractions) achieved a TCP of 95%. In patients with high-risk disease, an EQD2 of 97 Gy (37.6 Gy in 5 fractions) can achieve a TCP of 90% and an EQD2 of 102 Gy (38.7 Gy in 5 fractions) can achieve a TCP of 95%.

CONCLUSIONS

We found significant variation in the published literature on target delineation, margins used, dose/fractionation, and treatment schedule. Despite this variation, TCP was excellent. Most prescription doses range from 35 to 40 Gy, delivered in 4 to 5 fractions. The literature did not provide detailed dose-volume data, and our dosimetric analysis was constrained to prescription doses. There are many areas in need of continued research as SBRT continues to evolve as a treatment modality for prostate cancer, including the durability of local control with longer follow-up across risk groups, the efficacy and safety of SBRT as a boost to intensity modulated radiation therapy (IMRT), and the impact of incorporating novel imaging techniques into treatment planning.

Dosimetric evaluation of MRI-to-ultrasound automated image registration algorithms for prostate brachytherapy

PURPOSE

Identifying dominant intraprostatic lesions (DILs) on transrectal ultrasound (TRUS) images during prostate high-dose-rate brachytherapy treatment planning remains a significant challenge. Multiparametric MRI (mpMRI) is the tool of choice for DIL identification; however, the geometry of the prostate on mpMRI and on the TRUS may differ significantly, requiring image registration. This study assesses the dosimetric impact attributed to differences in DIL contours generated using commonly available MRI to TRUS automated registration: rigid, semi-rigid, and deformable image registration, respectively.

METHODS AND MATERIALS

Ten patients, each with mpMRI and TRUS data sets, were included in this study. Five radiation oncologists with expertise in TRUS-based high-dose-rate brachytherapy were asked cognitively to transfer the DIL from the mpMRI images of each patient to the TRUS image. The contours were analyzed for concordance using simultaneous truth and performance level estimation (STAPLE) algorithm. The impact of DIL contour differences due to registration variability was evaluated by comparing the STAPLE-DIL dosimetry from the reference (STAPLE) plan with that from the evaluation plans (manual and automated registration) for each patient. The dosimetric impact of the automatic registration approach was also validated using a margin expansion that normalizes the volume of the autoregistered DILs to the volumes of the STAPLE-DILs. Dose metrics including D₉₀, D_mean, V₁₅₀, and V₂₀₀ to the prostate and DIL were reported. For urethra and rectum, D₁₀ and V₈₀ were reported.

RESULTS

Significant differences in DIL coverage between reference and evaluation plans were found regardless of the algorithm methodology. No statistical difference was reported in STAPLE-DIL dosimetry when manual registration was used. A margin of 1.5 ± 0.8 mm, 1.1 ± 0.8 mm, and 2.5 ± 1.6 mm was required to be added for rigid, semi-rigid, and deformable registration, respectively, to mitigate the difference in STAPLE-DIL coverage between the evaluation and reference plans.

CONCLUSION

The dosimetric impact of integrating an MRI-delineated DIL into a TRUS-based brachytherapy workflow has been validated in this study. The results show that rigid, semi-rigid, and deformable registration algorithms lead to a significant undercoverage of the DIL D₉₀ and D_mean. A margin of at least 1.5 ± 0.8 mm, 1.1 ± 0.8 mm, and 2.5 ± 1.6 mm is required to be added to the rigid, semi-rigid, and deformable DIL registration to be suitable for DIL-boosting during prostate brachytherapy.

Comparison of CTVHR and organs at risk contours between TRUS and MR images in IB cervical cancers: a proof of concept study

Purpose

To compare CTV_HR and OAR dimensions and inter-rater agreement between magnetic resonance (MR) and trans-rectal ultrasound (TRUS) images in IB cervical cancer patients.

Methods

IB cervical cancer patients treated with (chemo)radiotherapy plus MR-guided brachytherapy (BT) were prospectively enrolled in this study. Radiation oncologists contoured CTV_HR and OARs in pre-BT MR images (MRI) and intra-operative TRUS images. These contours were subsequently compared in regard to volume and dimension. Contour inter-rater agreement analysis was also investigated using kappa index (KI). Stata 15.0 was used for statistical analysis and a p-value < 0.05 was considered statistically significant.

Results

TRUS CTV_HR volumes were statistically smaller than the respective MRI contoured volumes. TRUS CTV_HR thickness was found to be consistently smaller than MRI contours in all patients. No statistical difference was seen in width and height between the two different imaging modalities. MRI contours had a median KI of 0.66 (range: 0.56–0.77) while TRUS-based contours had a median KI of 0.64 (range: 0.47–0.77). Bladder and rectum had very satisfactory KI in both imaging modalities. Vaginal contours had moderate agreement in MR (0.52) and in TRUS images (0.58).

Conclusion

TRUS images allow good visualization of CTV_HR and OARs in IB cervical cancer patients. Inter-rater contour variability was comparable between TRUS and MR images. TRUS is a promising modality on its own for image-guided BT.

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.

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.

Prostate Benign Diseases

Magnetic resonance imaging (MRI) has been increasingly used in the detection, localization, and staging of prostate cancer. Because of its excellent soft tissue contrast and multiplane imaging, it can be also very useful in the evaluation of benign prostate diseases. Prostatic benign disorders have a high prevalence, vastly represented by benign prostatic hyperplasia and prostatitis. On the contrary, benign prostatic neoplasms are extremely rare, represented by multilocular cystadenoma, leiomyomas, hemangioma, and granular cell tumor, although these uncommon tumors have been most encountered due to widespread use of MRI. Congenital prostatic anomalies are associated with defects in the development of the prostate embryology, including hypoplasia, ectopia, and vascular malformations, abnormalities rarely seen on cross-sectional imaging. Prostatic cysts are the most common development abnormalities and occasionally are related to clinical symptoms, mainly due to infection and hemorrhage. As with prostate cancer, multiparametric MRI is a reliable tool for the diagnosis and management of benign prostatic diseases as well, providing additional information such morphological changes of the prostate, more accurate prostatic measurements, and functional characteristics of nonmalignant prostatic lesions. In this review, we discuss MRI findings of these benign prostatic diseases.

CT prostate segmentation based on synthetic MRI-aided deep attention fully convolution network

PURPOSE

Accurate segmentation of the prostate on computed tomography (CT) for treatment planning is challenging due to CT's poor soft tissue contrast. Magnetic resonance imaging (MRI) has been used to aid prostate delineation, but its final accuracy is limited by MRI-CT registration errors. We developed a deep attention-based segmentation strategy on CT-based synthetic MRI (sMRI) to deal with the CT prostate delineation challenge without MRI acquisition.

METHODS AND MATERIALS

We developed a prostate segmentation strategy which employs an sMRI-aided deep attention network to accurately segment the prostate on CT. Our method consists of three major steps. First, a cycle generative adversarial network was used to estimate an sMRI from CT images. Second, a deep attention fully convolution network was trained based on sMRI and the prostate contours deformed from MRIs. Attention models were introduced to pay more attention to prostate boundary. The prostate contour for a query patient was obtained by feeding the patient's CT images into the trained sMRI generation model and segmentation model.

RESULTS

The segmentation technique was validated with a clinical study of 49 patients by leave-one-out experiments and validated with an additional 50 patients by hold-out test. The Dice similarity coefficient, Hausdorff distance, and mean surface distance indices between our segmented and deformed MRI-defined prostate manual contours were 0.92 ± 0.09, 4.38 ± 4.66, and 0.62 ± 0.89 mm, respectively, with leave-one-out experiments, and were 0.91 ± 0.07, 4.57 ± 3.03, and 0.62 ± 0.65 mm, respectively, with hold-out test.

CONCLUSIONS

We have proposed a novel CT-only prostate segmentation strategy using CT-based sMRI, and validated its accuracy against the prostate contours that were manually drawn on MRI images and deformed to CT images. This technique could provide accurate prostate volume for treatment planning without requiring MRI acquisition, greatly facilitating the routine clinical workflow.

MRI-based IMPT planning for prostate cancer

PURPOSE

Treatment planning for proton therapy requires the relative proton stopping power ratio (RSP) information of the patient for accurate dose calculations. RSP are conventionally obtained after mapping of the Hounsfield units (HU) from a calibrated patient computed tomography (CT). One or multiple CT are needed for a given treatment which represents additional, undesired dose to the patient. For prostate cancer, magnetic resonance imaging (MRI) scans are the gold standard for segmentation while offering dose-less imaging. We here quantify the clinical applicability of converted MR images as a substitute for intensity modulated proton therapy (IMPT) treatment of the prostate.

METHODS

MRCAT (Magnetic Resonance for Calculating ATtenuation) is a Philips-developed technology which produces a synthetic CT image consisting of five HU from a specific set of MRI acquisitions. MRCAT and original planning CT data sets were obtained for ten patients. An IMPT plan was generated on the MRCAT for each patient. Plans were produced such that they fulfill the prostate protocol in use at Massachusetts General Hospital (MGH). The plans were then recomputed onto the nominal planning CT for each patient. Robustness analyses (±5 mm setup shifts and ±3.5 % range uncertainties) were also performed.

RESULTS

Comparison of MRCAT plans and their recomputation onto the planning CT plan showed excellent agreement. Likewise, dose perturbations due to setup shifts and range uncertainties were well within clinical acceptance demonstrating the clinical viability of the approach.

CONCLUSIONS

This work demonstrate the clinical acceptability of substituting MR converted RSP images instead of CT for IMPT planning of prostate cancer. This further translates into higher contouring accuracy along with lesser imaging dose.

Synthetic MRI-aided multi-organ segmentation on male pelvic CT using cycle consistent deep attention network

BACKGROUND AND PURPOSE

Manual contouring is labor intensive, and subject to variations in operator knowledge, experience and technique. This work aims to develop an automated computed tomography (CT) multi-organ segmentation method for prostate cancer treatment planning.

METHODS AND MATERIALS

The proposed method exploits the superior soft-tissue information provided by synthetic MRI (sMRI) to aid the multi-organ segmentation on pelvic CT images. A cycle generative adversarial network (CycleGAN) was used to estimate sMRIs from CT images. A deep attention U-Net (DAUnet) was trained on sMRI and corresponding multi-organ contours for auto-segmentation. The deep attention strategy was introduced to identify the most relevant features to differentiate different organs. Deep supervision was incorporated into the DAUnet to enhance the features' discriminative ability. Segmented contours of a patient were obtained by feeding CT image into the trained CycleGAN to generate sMRI, which was then fed to the trained DAUnet to generate organ contours. We trained and evaluated our model with 140 datasets from prostate patients.

RESULTS

The Dice similarity coefficient and mean surface distance between our segmented and bladder, prostate, and rectum manual contours were 0.95 ± 0.03, 0.52 ± 0.22 mm; 0.87 ± 0.04, 0.93 ± 0.51 mm; and 0.89 ± 0.04, 0.92 ± 1.03 mm, respectively.

CONCLUSION

We proposed a sMRI-aided multi-organ automatic segmentation method on pelvic CT images. By integrating deep attention and deep supervision strategy, the proposed network provides accurate and consistent prostate, bladder and rectum segmentation, and has the potential to facilitate routine prostate-cancer radiotherapy treatment planning.

Planning feasibility of extremely hypofractionated prostate radiotherapy on a 1.5 T magnetic resonance imaging guided linear accelerator

BACKGROUND AND PURPOSE

Recently, intermediate and high-risk prostate cancer patients have been treated in a multicenter phase II trial with extremely hypofractionated prostate radiotherapy (hypo-FLAME trial). The purpose of the current study was to investigate whether a 1.5 T magnetic resonance imaging guided linear accelerator (MRI-linac) could achieve complex dose distributions of a quality similar to conventional linac state-of-the-art prostate treatments.

MATERIALS AND METHODS

The clinically delivered treatment plans of 20 hypo-FLAME patients (volumetric modulated arc therapy, 10 MV, 5 mm leaf width) were included. Prescribed dose to the prostate was 5 × 7 Gy, with a focal tumor boost up to 5 × 10 Gy. MRI-linac treatment plans (intensity modulated radiotherapy, 7 MV, 7 mm leaf width, fixed collimator angle and 1.5 T magnetic field) were calculated. Dose distributions were compared.

RESULTS

In both conventional and MRI-linac treatment plans, the V35Gy to the whole prostate was >99% in all patients. Mean dose to the gross tumor volume was 45 Gy for conventional and 44 Gy for MRI-linac plans, respectively. Organ at risk doses were met in the majority of plans, except for a rectal V35Gy constraint, which was exceeded in one patient, by 1 cc, for both modalities. The bladder V32Gy and V28Gy constraints were exceeded in two and one patient respectively, for both modalities.

CONCLUSION

Planning of stereotactic radiotherapy with focal ablative boosting in prostate cancer on a high field MRI-linac is feasible with the current MRI-linac properties, without deterioration of plan quality compared to conventional treatments.

Deep learning-based three-dimensional segmentation of the prostate on computed tomography images

Segmentation of the prostate in computed tomography (CT) is used for planning and guidance of prostate treatment procedures. However, due to the low soft-tissue contrast of the images, manual delineation of the prostate on CT is a time-consuming task with high interobserver variability. We developed an automatic, three-dimensional (3-D) prostate segmentation algorithm based on a customized U-Net architecture. Our dataset contained 92 3-D abdominal CT scans from 92 patients, of which 69 images were used for training and validation and the remaining for testing the convolutional neural network model. Compared to manual segmentation by an expert radiologist, our method achieved 83 % ± 6 % for Dice similarity coefficient (DSC), 2.3 ± 0.6    mm for mean absolute distance (MAD), and 1.9 ± 4.0    cm 3 for signed volume difference ( Δ V ). The average recorded interexpert difference measured on the same test dataset was 92% (DSC), 1.1 mm (MAD), and 2.1    cm 3 ( Δ V ). The proposed algorithm is fast, accurate, and robust for 3-D segmentation of the prostate on CT images.

Definition of fields margins for the optimized 2D radiotherapy of prostate carcinoma

Prostate cancer (PCa) is one of the most common malignancies in men both in western and developing countries. Radiotherapy (RT) is an important therapeutic option. New technologies (including 3D, intensity modulated RT, image-guided RT and, volumetric modulated arc therapy) have been introduced in the last few decades with progressive improvement of clinical outcomes. However, in many developing countries, the only treatment option is the traditional two-dimensional (2D) technique based on standard simulation. The guidelines for 2D field definition are still based on expert's opinions. The aim of the present study was to propose new practical guidelines for 2D fields definition based on 3D simulation in PCa. A total of 20 patients were enrolled. Computed tomography-simulation and pelvic magnetic resonance images were merged to define the prostate volumes. Clinical Target Volume (CTV) was defined using the European Organisation for Research and Treatment of Cancer guidelines in consideration of the four risk categories: Low, intermediate, and high risk with or without seminal vesicles involvement, respectively. Planning Target Volume (PTV) was defined by adding 10 mm to the CTV. For each category, two treatment plans were calculated using a cobalt source or 10 MV photons. Progressive optimization was achieved by evaluating 3D dose distribution. Finally, the optimal distances between field margins and radiological landmarks (bones and rectum with contrast medium) were defined. The results were reported in tabular form. Both field margins (PTV D_98% >95%) needed to adequately irradiate all patients and to achieve a similar result in 95% of the enrolled patients are reported. Using a group of patients with PCa and based on a 3D planning analysis, we propose new practical guidelines for PCa 2D-RT based on current criteria for risk category and CTV, and PTV definition.

Comparison of multiparametric MRI-based and transrectal ultrasound-based preplans with intraoperative ultrasound-based planning for low dose rate interstitial prostate seed implantation

PURPOSE

Transrectal ultrasound images are routinely acquired for low dose rate (LDR) prostate brachytherapy dosimetric preplanning (pTRUS), although diagnostic multiparametric magnetic resonance imaging (mpMRI) may serve this purpose as well. We compared the predictive abilities of TRUS vs MRI relative to intraoperative TRUS (iTRUS) to assess the role of mpMRI in brachytherapy preplanning.

MATERIALS AND METHODS

Retrospective analysis was performed on 32 patients who underwent iTRUS-guided prostate LDR brachytherapy as either mono- or combination therapy. 56.3% had pTRUS-only volume studies and 43.7% had both 3T-mpMRI and pTRUS preplanning. MRI was used for preplanning and its image fusion with iTRUS was also used for intraoperative guidance of seed placement. Differences in gland volume, seed number, and activity and procedure time were examined, as well as the identification of lesions suspicious for tumor foci. Pearson correlation coefficient and Fisher's Z test were used to estimate associations between continuous measures.

RESULTS

There was good correlation of planning volumes between iTRUS and either pTRUS or MRI (r = 0.89, r = 0.77), not impacted by the addition of hormonal therapy (P = 0.65, P = 0.33). Both consistently predicted intraoperative seed number (r = 0.87, r = 0.86). MRI/TRUS fusion did not significantly increase surgical or anesthesia time (P = 0.10, P = 0.46). mpMRI revealed suspicious focal lesions in 11 of 14 cases not visible on pTRUS, that when correlated with histopathology, were incorporated into the plan.

CONCLUSIONS

Relative to pTRUS, MRI yielded reliable preplanning measures, supporting the role of MRI-only LDR treatment planning. mpMRI carries numerous diagnostic, staging and preplanning advantages that facilitate better patient selection and delivery of novel dose escalation and targeted therapy, with no additional surgical or anesthesia time. Prospective studies assessing its impact on treatment planning and delivery can serve to establish mpMRI as the standard of care in LDR prostate brachytherapy planning.

Multisite evaluation of radiomic feature reproducibility and discriminability for identifying peripheral zone prostate tumors on MRI

Recent advances in the field of radiomics have enabled the development of a number of prognostic and predictive imaging-based tools for a variety of diseases. However, wider clinical adoption of these tools is contingent on their generalizability across multiple sites and scanners. This may be particularly relevant in the context of radiomic features derived from T1- or T2-weighted magnetic resonance images (MRIs), where signal intensity values are known to lack tissue-specific meaning and vary based on differing acquisition protocols between institutions. We present the first empirical study of benchmarking five different radiomic feature families in terms of both reproducibility and discriminability in a multisite setting, specifically, for identifying prostate tumors in the peripheral zone on MRI. Our cohort comprised 147 patient T2-weighted MRI datasets from four different sites, all of which are first preprocessed to correct for acquisition-related artifacts such as bias field, differing voxel resolutions, and intensity drift (nonstandardness). About 406 three-dimensional voxel-wise radiomic features from five different families (gray, Haralick, gradient, Laws, and Gabor) were evaluated in a cross-site setting to determine (a) how reproducible they are within a relatively homogeneous nontumor tissue region and (b) how well they could discriminate tumor regions from nontumor regions. Our results demonstrate that a majority of the popular Haralick features are reproducible in over 99% of all cross-site comparisons, as well as achieve excellent cross-site discriminability (classification accuracy of ≈ 0.8 ). By contrast, a majority of Laws features are highly variable across sites (reproducible in < 75 % of all cross-site comparisons) as well as resulting in low cross-site classifier accuracies ( < 0.6 ), likely due to a large number of noisy filter responses that can be extracted. These trends suggest that only a subset of radiomic features and associated parameters may be both reproducible and discriminable enough for use within machine learning classifier schemes.

Target definition in radiotherapy of prostate cancer using magnetic resonance imaging only workflow

In magnetic resonance (MR) only radiotherapy, the target delineation needs to be performed without computed tomography (CT). We investigated in thirteen patients with prostate cancer, how the clinical target volume (CTV) was affected, when the target delineation procedure was changed from using both CT and MR images to using MR images only. The mean volume of the CTV_CT/MR was 61.0 cm³ as compared to 49.9 cm³ from MR-only based target delineation, corresponding to an average decrease of 18%. Our results show that CTV_MR-only was consistently smaller than CTV_CT/MR, which has to be taken into consideration before clinical commissioning of MR-only radiotherapy.

Automatic Segmentation of the Prostate on CT Images Using Deep Neural Networks (DNN)

PURPOSE

Recent advances in deep neural networks (DNNs) have unlocked opportunities for their application for automatic image segmentation. We have evaluated a DNN-based algorithm for automatic segmentation of the prostate gland on a large cohort of patient images.

METHODS AND MATERIALS

Planning-CT data sets for 1114 patients with prostate cancer were retrospectively selected and divided into 2 groups. Group A contained 1104 data sets, with 1 physician-generated prostate gland contour for each data set. Among these image sets, 771 were used for training, 193 for validation, and 140 for testing. Group B contained 10 data sets, each including prostate contours delineated by 5 independent physicians and a consensus contour generated using the STAPLE method in the CERR software package. All images were resampled to a spatial resolution of 1 × 1 × 1.5 mm. A region (128 × 128 × 64 voxels) containing the prostate was selected to train a DNN. The best-performing model on the validation data sets was used to segment the prostate on all testing images. Results were compared between DNN and physician-generated contours using the Dice similarity coefficient, Hausdorff distances, regional contour distances, and center-of-mass distances.

RESULTS

The mean Dice similarity coefficients between DNN-based prostate segmentation and physician-generated contours for test data in Group A, Group B, and Group B-consensus were 0.85 ± 0.06 (range, 0.65-0.93), 0.85 ± 0.04 (range, 0.80-0.91), and 0.88 ± 0.03 (range, 0.82-0.92), respectively. The Hausdorff distance was 7.0 ± 3.5 mm, 7.3 ± 2.0 mm, and 6.3 ± 2.0 mm for Group A, Group B, and Group B-consensus, respectively. The mean center-of-mass distances for all 3 data set groups were within 5 mm.

CONCLUSIONS

A DNN-based algorithm was used to automatically segment the prostate for a large cohort of patients with prostate cancer. DNN-based prostate segmentations were compared to the consensus contour for a smaller group of patients; the agreement between DNN segmentations and consensus contour was similar to the agreement reported in a previous study. Clinical use of DNNs is promising, but further investigation is warranted.

A semiautomatic approach for prostate segmentation in MR images using local texture classification and statistical shape modeling

Segmentation of the prostate in magnetic resonance (MR) images has many applications in image-guided treatment planning and procedures such as biopsy and focal therapy. However, manual delineation of the prostate boundary is a time-consuming task with high inter-observer variation. In this study, we proposed a semiautomated, three-dimensional (3D) prostate segmentation technique for T2-weighted MR images based on shape and texture analysis. The prostate gland shape is usually globular with a smoothly curved surface that could be accurately modeled and reconstructed if the locations of a limited number of well-distributed surface points are known. For a training image set, we used an inter-subject correspondence between the prostate surface points to model the prostate shape variation based on a statistical point distribution modeling. We also studied the local texture difference between prostate and non-prostate tissues close to the prostate surface. To segment a new image, we used the learned prostate shape and texture characteristics to search for the prostate border close to an initially estimated prostate surface. We used 23 MR images for training, and 14 images for testing the algorithm performance. We compared the results to two sets of experts' manual reference segmentations. The measured mean ± standard deviation of error values for the whole gland were 1.4 ± 0.4 mm, 8.5 ± 2.0 mm, and 86 ± 3% in terms of mean absolute distance (MAD), Hausdorff distance (HDist), and Dice similarity coefficient (DSC). The average measured differences between the two experts on the same datasets were 1.5 mm (MAD), 9.0 mm (HDist), and 83% (DSC). The proposed algorithm illustrated a fast, accurate, and robust performance for 3D prostate segmentation. The accuracy of the algorithm is within the inter-expert variability observed in manual segmentation and comparable to the best performance results reported in the literature.

Determination of Prostate Volume: A Comparison of Contemporary Methods

RATIONALE AND OBJECTIVES

Prostate volume (PV) determination provides important clinical information. We compared PVs determined by digital rectal examination (DRE), transrectal ultrasound (TRUS), magnetic resonance imaging (MRI) with or without three-dimensional (3D) segmentation software, and surgical prostatectomy weight (SPW) and volume (SPV).

MATERIALS AND METHODS

This retrospective review from 2010 to 2016 included patients who underwent radical prostatectomy ≤1 year after multiparametric prostate MRI. PVs from DRE and TRUS were obtained from urology clinic notes. MRI-based PVs were calculated using bullet and ellipsoid formulas, automated 3D segmentation software (MRI-A3D), manual segmentation by a radiologist (MRI-R3D), and a third-year medical student (MRI-S3D). SPW and SPV were derived from pathology reports. Intraclass correlation coefficients compared the relative accuracy of each volume measurement.

RESULTS

Ninety-nine patients were analyzed. Median PVs were DRE 35 mL, TRUS 35 mL, MRI-bullet 49 mL, MRI-ellipsoid 39 mL, MRI-A3D 37 mL, MRI-R3D 36 mL, MRI-S3D 36 mL, SPW 54 mL, SPV-bullet 47 mL, and SPV-ellipsoid 37 mL. SPW and bullet formulas had consistently large PV, and formula-based PV had a wider spread than PV based on segmentation. Compared to MRI-R3D, the intraclass correlation coefficient was 0.91 for MRI-S3D, 0.90 for MRI-ellipsoid, 0.73 for SPV-ellipsoid, 0.72 for MRI-bullet, 0.71 for TRUS, 0.70 for SPW, 0.66 for SPV-bullet, 0.38 for MRI-A3D, and 0.33 for DRE.

CONCLUSIONS

With MRI-R3D measurement as the reference, the most reliable methods for PV estimation were MRI-S3D and MRI-ellipsoid formula. Automated segmentations must be individually assessed for accuracy, as they are not always truly representative of the prostate anatomy. Manual segmentation of the prostate does not require expert training.

A semiautomatic algorithm for three-dimensional segmentation of the prostate on CT images using shape and local texture characteristics

Prostate segmentation in computed tomography (CT) images is useful for planning and guidance of the diagnostic and therapeutic procedures. However, the low soft-tissue contrast of CT images makes the manual prostate segmentation a time-consuming task with high inter-observer variation. We developed a semi-automatic, three-dimensional (3D) prostate segmentation algorithm using shape and texture analysis and have evaluated the method against manual reference segmentations. In a training data set we defined an inter-subject correspondence between surface points in the spherical coordinate system. We applied this correspondence to model the globular and smoothly curved shape of the prostate with 86, well-distributed surface points using a point distribution model that captures prostate shape variation. We also studied the local texture difference between prostate and non-prostate tissues close to the prostate surface. For segmentation, we used the learned shape and texture characteristics of the prostate in CT images and we used a set of user inputs for prostate localization. We trained our algorithm using 23 CT images and tested it on 10 images. We evaluated the results compared with those of two experts' manual reference segmentations using different error metrics. The average measured Dice similarity coefficient (DSC) and mean absolute distance (MAD) were 88 ± 2% and 1.9 ± 0.5 mm, respectively. The averaged inter-expert difference measured on the same dataset was 91 ± 4% (DSC) and 1.3 ± 0.6 mm (MAD). With no prior intra-patient information, the proposed algorithm showed a fast, robust and accurate performance for 3D CT segmentation.

Magnetic Resonance Imaging only Workflow for Radiotherapy Simulation and Planning in Prostate Cancer

Magnetic resonance imaging (MRI) is often combined with computed tomography (CT) in prostate radiotherapy to optimise delineation of the target and organs-at-risk (OAR) while maintaining accurate dose calculation. Such a dual-modality workflow requires two separate imaging sessions, and it has some fundamental and logistical drawbacks. Due to the availability of new MRI hardware and software solutions, CT examinations can be omitted for prostate radiotherapy simulations. All information for treatment planning, including electron density maps and bony anatomy, can nowadays be obtained with MRI. Such an MRI-only simulation workflow reduces delineation ambiguities, eases planning logistics, and improves patient comfort; however, careful validation of the complete MRI-only workflow is warranted. The first institutes are now adopting this MRI-only workflow for prostate radiotherapy. In this article, we will review technology and workflow requirements for an MRI-only prostate simulation workflow.

Pre-implant magnetic resonance and transrectal ultrasound imaging in high-dose-rate prostate brachytherapy: comparison of prostate volumes, craniocaudal extents, and contours

PURPOSE

The purpose of this study was to compare the prostate contours drawn by two radiation oncologists and one radiologist on magnetic resonance (MR) and transrectal ultrasound (TRUS) images. TRUS intra- and inter-fraction variability as well as TRUS vs. MR inter-modality and inter-operator variability were studied.

MATERIAL AND METHODS

Thirty patients affected by localized prostate cancer and treated with interstitial high-dose-rate (HDR) prostate brachytherapy at the National Cancer Institute in Milan were included in this study. Twenty-five patients received an exclusive two-fraction (14 Gy/fraction) treatment, while the other 5 received a single 14 Gy fraction as a boost after external beam radiotherapy. The prostate was contoured on TRUS images acquired before (virtual US) and after (real US) needle implant by two radiation oncologists, whereas on MR prostate was independently contoured by the same radiation oncologists (MR1, MR2) and by a dedicated radiologist (MR3). Absolute differences of prostate volumes (│ΔV│) and craniocaudal extents (│Δdz│) were evaluated. The Dice's coefficient (DC) was calculated to quantify spatial overlap between MR contours.

RESULTS

Significant difference was found between Vvirtual and Vlive (p < 0.001) for the first treatment fractions and between VMR1 and VMR2 (p = 0.043). Significant difference between cranio-caudal extents was found between dzvirtual and dzlive (p < 0.033) for the first treatment fractions, between dzvirtual of the first treatment fractions and dzMR1 (p < 0.001) and between dzMR1 and dzMR3 (p < 0.01). Oedema might be responsible for some of the changes in US volumes. Average DC values resulting from the comparison MR1 vs. MR2, MR1 vs. MR3 and MR2 vs. MR3 were 0.95 ± 0.04 (range, 0.82-0.99), 0.87 ± 0.04 (range, 0.73-0.91) and 0.87 ± 0.04 (range, 0.72-0.91), respectively.

CONCLUSIONS

Our results demonstrate the importance of a multiprofessional approach to TRUS-guided HDR prostate brachytherapy. Specific training in MR and US prostate imaging is recommended for centers that are unfamiliar with HDR prostate brachytherapy.

Accuracy Validation of an Automated Method for Prostate Segmentation in Magnetic Resonance Imaging

Three dimensional (3D) manual segmentation of the prostate on magnetic resonance imaging (MRI) is a laborious and time-consuming task that is subject to inter-observer variability. In this study, we developed a fully automatic segmentation algorithm for T2-weighted endorectal prostate MRI and evaluated its accuracy within different regions of interest using a set of complementary error metrics. Our dataset contained 42 T2-weighted endorectal MRI from prostate cancer patients. The prostate was manually segmented by one observer on all of the images and by two other observers on a subset of 10 images. The algorithm first coarsely localizes the prostate in the image using a template matching technique. Then, it defines the prostate surface using learned shape and appearance information from a set of training images. To evaluate the algorithm, we assessed the error metric values in the context of measured inter-observer variability and compared performance to that of our previously published semi-automatic approach. The automatic algorithm needed an average execution time of ∼60 s to segment the prostate in 3D. When compared to a single-observer reference standard, the automatic algorithm has an average mean absolute distance of 2.8 mm, Dice similarity coefficient of 82%, recall of 82%, precision of 84%, and volume difference of 0.5 cm³ in the mid-gland. Concordant with other studies, accuracy was highest in the mid-gland and lower in the apex and base. Loss of accuracy with respect to the semi-automatic algorithm was less than the measured inter-observer variability in manual segmentation for the same task.

A semiautomatic segmentation method for prostate in CT images using local texture classification and statistical shape modeling

PURPOSE

Prostate segmentation in computed tomography (CT) images is useful for treatment planning and procedure guidance such as external beam radiotherapy and brachytherapy. However, because of the low, soft tissue contrast of CT images, manual segmentation of the prostate is a time-consuming task with high interobserver variation. In this study, we proposed a semiautomated, three-dimensional (3D) segmentation for prostate CT images using shape and texture analysis and we evaluated the method against manual reference segmentations.

METHODS

The prostate gland usually has a globular shape with a smoothly curved surface, and its shape could be accurately modeled or reconstructed having a limited number of well-distributed surface points. In a training dataset, using the prostate gland centroid point as the origin of a coordination system, we defined an intersubject correspondence between the prostate surface points based on the spherical coordinates. We applied this correspondence to generate a point distribution model for prostate shape using principal component analysis and to study the local texture difference between prostate and nonprostate tissue close to the different prostate surface subregions. We used the learned shape and texture characteristics of the prostate in CT images and then combined them with user inputs to segment a new image. We trained our segmentation algorithm using 23 CT images and tested the algorithm on two sets of 10 nonbrachytherapy and 37 postlow dose rate brachytherapy CT images. We used a set of error metrics to evaluate the segmentation results using two experts' manual reference segmentations.

RESULTS

For both nonbrachytherapy and post-brachytherapy image sets, the average measured Dice similarity coefficient (DSC) was 88% and the average mean absolute distance (MAD) was 1.9 mm. The average measured differences between the two experts on both datasets were 92% (DSC) and 1.1 mm (MAD).

CONCLUSIONS

The proposed, semiautomatic segmentation algorithm showed a fast, robust, and accurate performance for 3D prostate segmentation of CT images, specifically when no previous, intrapatient information, that is, previously segmented images, was available. The accuracy of the algorithm is comparable to the best performance results reported in the literature and approaches the interexpert variability observed in manual segmentation.

Breast lesion shape and margin evaluation: BI-RADS based metrics understate radiologists' actual levels of agreement

BACKGROUND

While there is much literature describing the radiologic detection of breast cancer, there are limited data available on the agreement between experts when delineating and classifying breast lesions. The aim of this work is to measure the level of agreement between expert radiologists when delineating and classifying breast lesions as demonstrated through Breast Imaging Reporting and Data System (BI-RADS) and quantitative shape metrics.

METHODS

Forty mammographic images, each containing a single lesion, were presented to nine expert breast radiologists using a high specification interactive digital drawing tablet with stylus. Each reader was asked to manually delineate the breast masses using the tablet and stylus and then visually classify the lesion according to the American College of Radiology (ACR) BI-RADS lexicon. The delineated lesion compactness and elongation were computed using Matlab software. Intraclass Correlation Coefficient (ICC) and Cohen's kappa were used to assess inter-observer agreement for delineation and classification outcomes, respectively.

RESULTS

Inter-observer agreement was fair for BI-RADS shape (kappa = 0.37) and moderate for margin (kappa = 0.58) assessments. Agreement for quantitative shape metrics was good for lesion elongation (ICC = 0.82) and excellent for compactness (ICC = 0.93).

CONCLUSIONS

Fair to moderate levels of agreement was shown by radiologists for shape and margin classifications of cancers using the BI-RADS lexicon. When quantitative shape metrics were used to evaluate radiologists' delineation of lesions, good to excellent inter-observer agreement was found. The results suggest that qualitative descriptors such as BI-RADS lesion shape and margin understate the actual level of expert radiologist agreement.

Online Robust Projective Dictionary Learning: Shape Modeling for MR-TRUS Registration

Robust and effective shape prior modeling from a set of training data remains a challenging task, since the shape variation is complicated, and shape models should preserve local details as well as handle shape noises. To address these challenges, a novel robust projective dictionary learning (RPDL) scheme is proposed in this paper. Specifically, the RPDL method integrates the dimension reduction and dictionary learning into a unified framework for shape prior modeling, which can not only learn a robust and representative dictionary with the energy preservation of the training data, but also reduce the dimensionality and computational cost via the subspace learning. In addition, the proposed RPDL algorithm is regularized by using the norm to handle the outliers and noises, and is embedded in an online framework so that of memory and time efficiency. The proposed method is employed to model prostate shape prior for the application of magnetic resonance transrectal ultrasound registration. The experimental results demonstrate that our method provides more accurate and robust shape modeling than the state-of-the-art methods do. The proposed RPDL method is applicable for modeling other organs, and hence, a general solution for the problem of shape prior modeling.

Fusion of Intraoperative Transrectal Ultrasound Images with Post-implant Computed Tomography and Magnetic Resonance Imaging

Purpose

To compare the impact of the fusion of intraoperative transrectal ultrasound (TRUS) images with day 30 computed tomography (CT) and magnetic resonance imaging (MRI) on prostate volume and dosimetry.

Methods and materials

Seventy-five consecutive patients with CT and MRI obtained on day 30 with a Fast Spin Echo T2-weighted magnetic resonance (MR) sequence were analyzed. A rigid manual registration was performed between the intraoperative TRUS and day-30 CT based on the prostate volume. A second manual rigid registration was performed between the intraoperative TRUS and the day-30 MRI. The prostate contours were manually modified on CT and MRI. The difference in prostate volume and dosimetry between CT and MRI were compared.

Results

Prostate volume was on average 8% (standard deviation (SD) ± 16%) larger on intraoperative TRUS than on CT and 6% (18%) larger than on MRI. In 48% of the cases, the difference in volume on CT was > 10% compared to MRI. The difference in prostate volume between CT and MRI was inversely correlated to the difference in D90 (minimum dose that covers 90% of the prostate volume) between CT and MRI (r = -0.58, P < .001). A D90 < 90% was found in 5% (n = 4) on MRI and in 10% (n = 7) on CT (Fisher exact test one-sided P = .59), but in no patient was the D90 < 90% on both MRI and CT.

Conclusions

When fusing TRUS images with CT and MRI, the differences in prostate volume between those modalities remain clinically important in nearly half of the patients, and this has a direct influence on how implant quality is evaluated.

Role of Prostate MR Imaging in Radiation Oncology

The use of prostate MR imaging in radiotherapy continues to evolve. This article describes its current application in the selection of treatment regimens, integration in treatment planning or simulation, and assessment of response. An expert consensus statement from the annual MR in RT symposium is presented, as a list of 21 key quality indicators for the practice of MR imaging simulation in prostate cancer. Although imaging requirements generally follow PIRADSv2 guidelines, additional requirements specific to radiotherapy planning are described. MR imaging-only workflows and MR imaging-guided treatment systems are expected to replace conventional computed tomography-based practice, further adding specific requirements for MR imaging in radiotherapy.

Does intensity-modulated radiation therapy (IMRT) alter prostate size? Magnetic resonance imaging evaluation of patients undergoing IMRT alone

AIM

To assess the changes in prostate size in patients with prostate cancer undergoing intensity-modulated radiation therapy (IMRT).

BACKGROUND

The effect of size change produced by IMRT is not well known.

MATERIALS AND METHODS

We enrolled 72 patients who received IMRT alone without androgen-deprivation therapy and underwent magnetic resonance imaging (MRI) examination before and after IMRT. The diameter of the entire prostate in the anterior-posterior (P-AP) and left-right (P-LR) directions was measured. The transitional zone diameter in the anterior-posterior (T-AP) and left-right (T-LR) directions was also measured.

RESULTS

The average relative P-AP values at 3, 6, 12, 24, and 36 months after IMRT compared to the pre-IMRT value were 0.94, 0.90, 0.89, 0.89, and 0.90, respectively; the average relative P-LR values were 0.93, 0.92, 0.91, 0.91, and 0.90, respectively. The average P-AP and P-LR decreased by approximately 10% during the 12 months post-IMRT, and remained unchanged thereafter. The average relative T-AP values at 3, 6, 12, 24, and 36 months after IMRT compared to the pre-IMRT value were 0.93, 0.88, 0.91, 0.87, and 0.89, respectively; the average relative T-LR values were 0.96, 0.90, 0.91, 0.87, and 0.88, respectively. The average T-AP and T-LR also decreased by approximately 10% during the 12 months post-IMRT, and remained unchanged thereafter. At 12 months after IMRT, the average relative T-AP was significantly lower in patients with recurrence than in those without recurrence.

CONCLUSIONS

The average prostate diameter decreased by approximately 10% during the 12 months after IMRT; thereafter remained unchanged.

A method for mapping and quantifying whole organ diffusion-weighted image distortion in MR imaging of the prostate

A computational algorithm was designed to produce a measure of DW image distortion across the prostate. This algorithm was tested and validated on virtual phantoms incorporating known degrees and distributions of distortion. A study was then carried out on DW image volumes from three sets of 10 patients who had been imaged previously. These volumes had been radiologically assessed to have, respectively, 'no distortion' or 'significant distortion' or the potential for 'significant distortion' due to susceptibility effects from hip prostheses. Prostate outlines were drawn on a T2-weighted (T2W) image 'gold-standard' volume and on an ADC image volume derived from DW images acquired over the same region. The algorithm was then applied to these outlines to quantify and map image distortion. The proposed method correctly reproduced known distortion values and distributions in virtual phantoms. It also successfully distinguished between the three groups of patients: mean distortion in 'non-distorted' image volumes, 1.942 ± 0.582 mm; 'distorted', 4.402 ± 1.098 mm; and 'hip patients' 8.083 ± 4.653 mm; P < 0.001. This work has demonstrated and validated a means of quantifying and mapping image distortion in clinical prostate MRI cases.

Classification and evaluation strategies of auto-segmentation approaches for PET: Report of AAPM task group No. 211

PURPOSE

The purpose of this educational report is to provide an overview of the present state-of-the-art PET auto-segmentation (PET-AS) algorithms and their respective validation, with an emphasis on providing the user with help in understanding the challenges and pitfalls associated with selecting and implementing a PET-AS algorithm for a particular application.

APPROACH

A brief description of the different types of PET-AS algorithms is provided using a classification based on method complexity and type. The advantages and the limitations of the current PET-AS algorithms are highlighted based on current publications and existing comparison studies. A review of the available image datasets and contour evaluation metrics in terms of their applicability for establishing a standardized evaluation of PET-AS algorithms is provided. The performance requirements for the algorithms and their dependence on the application, the radiotracer used and the evaluation criteria are described and discussed. Finally, a procedure for algorithm acceptance and implementation, as well as the complementary role of manual and auto-segmentation are addressed.

FINDINGS

A large number of PET-AS algorithms have been developed within the last 20 years. Many of the proposed algorithms are based on either fixed or adaptively selected thresholds. More recently, numerous papers have proposed the use of more advanced image analysis paradigms to perform semi-automated delineation of the PET images. However, the level of algorithm validation is variable and for most published algorithms is either insufficient or inconsistent which prevents recommending a single algorithm. This is compounded by the fact that realistic image configurations with low signal-to-noise ratios (SNR) and heterogeneous tracer distributions have rarely been used. Large variations in the evaluation methods used in the literature point to the need for a standardized evaluation protocol.

CONCLUSIONS

Available comparison studies suggest that PET-AS algorithms relying on advanced image analysis paradigms provide generally more accurate segmentation than approaches based on PET activity thresholds, particularly for realistic configurations. However, this may not be the case for simple shape lesions in situations with a narrower range of parameters, where simpler methods may also perform well. Recent algorithms which employ some type of consensus or automatic selection between several PET-AS methods have potential to overcome the limitations of the individual methods when appropriately trained. In either case, accuracy evaluation is required for each different PET scanner and scanning and image reconstruction protocol. For the simpler, less robust approaches, adaptation to scanning conditions, tumor type, and tumor location by optimization of parameters is necessary. The results from the method evaluation stage can be used to estimate the contouring uncertainty. All PET-AS contours should be critically verified by a physician. A standard test, i.e., a benchmark dedicated to evaluating both existing and future PET-AS algorithms needs to be designed, to aid clinicians in evaluating and selecting PET-AS algorithms and to establish performance limits for their acceptance for clinical use. The initial steps toward designing and building such a standard are undertaken by the task group members.

Permanent prostate brachytherapy postimplant magnetic resonance imaging dosimetry using positive contrast magnetic resonance imaging markers

PURPOSE

Permanent prostate brachytherapy dosimetry using computed tomography-magnetic resonance imaging (CT-MRI) fusion combines the anatomic detail of MRI with seed localization on CT but requires multimodality imaging acquisition and fusion. The purpose of this study was to compare the utility of MRI only postimplant dosimetry to standard CT-MRI fusion-based dosimetry.

METHODS AND MATERIALS

Twenty-three patients undergoing permanent prostate brachytherapy with use of positive contrast MRI markers were included in this study. Dose calculation to the whole prostate, apex, mid-gland, and base was performed via standard CT-MRI fusion and MRI only dosimetry with prostate delineated on the same T2 MRI sequence. The 3-dimensional (3D) distances between seed positions of these two methods were also evaluated. Wilcoxon-matched-pair signed-rank test compared the D90 and V100 of the prostate and its sectors between methods.

RESULTS

The day 0 D90 and V100 for the prostate were 98% versus 94% and 88% versus 86% for CT-MRI fusion and MRI only dosimetry. There were no differences in the D90 or V100 of the whole prostate, mid-gland, or base between dosimetric methods (p > 0.19), but prostate apex D90 was high by 13% with MRI dosimetry (p = 0.034). The average distance between seeds on CT-MRI fusion and MRI alone was 5.5 mm. After additional automated rigid registration of 3D seed positions, the average distance between seeds was 0.3 mm, and the previously observed differences in apex dose between methods was eliminated (p > 0.11).

CONCLUSIONS

Permanent prostate brachytherapy dosimetry based only on MRI using positive contrast MRI markers is feasible, accurate, and reduces the uncertainties arising from CT-MRI fusion abating the need for postimplant multimodality imaging.