Uncertainty estimation using a 3D probabilistic U-Net for segmentation with small radiotherapy clinical trial datasets.

BACKGROUND AND OBJECTIVES: Bio-medical image segmentation models typically attempt to predict one segmentation that resembles a ground-truth structure as closely as possible. However, as medical images are not perfect representations of anatomy, obtaining this ground truth is not possible. A surrogate commonly used is to have multiple expert observers define the same structure for a dataset. When multiple observers define the same structure on the same image there can be significant differences depending on the structure, image quality/modality and the region being defined. It is often desirable to estimate this type of aleatoric uncertainty in a segmentation model to help understand the region in which the true structure is likely to be positioned. Furthermore, obtaining these datasets is resource intensive so training such models using limited data may be required. With a small dataset size, differing patient anatomy is likely not well represented causing epistemic uncertainty which should also be estimated so it can be determined for which cases the model is effective or not. METHODS: We use a 3D probabilistic U-Net to train a model from which several segmentations can be sampled to estimate the range of uncertainty seen between multiple observers. To ensure that regions where observers disagree most are emphasised in model training, we expand the Generalised Evidence Lower Bound (ELBO) with a Constrained Optimisation (GECO) loss function with an additional contour loss term to give attention to this region. Ensemble and Monte-Carlo dropout (MCDO) uncertainty quantification methods are used during inference to estimate model confidence on an unseen case. We apply our methodology to two radiotherapy clinical trial datasets, a gastric cancer trial (TOPGEAR, TROG 08.08) and a post-prostatectomy prostate cancer trial (RAVES, TROG 08.03). Each dataset contains only 10 cases each for model development to segment the clinical target volume (CTV) which was defined by multiple observers on each case. An additional 50 cases are available as a hold-out dataset for each trial which had only one observer define the CTV structure on each case. Up to 50 samples were generated using the probabilistic model for each case in the hold-out dataset. To assess performance, each manually defined structure was matched to the closest matching sampled segmentation based on commonly used metrics. RESULTS: The TOPGEAR CTV model achieved a Dice Similarity Coefficient (DSC) and Surface DSC (sDSC) of 0.7 and 0.43 respectively with the RAVES model achieving 0.75 and 0.71 respectively. Segmentation quality across cases in the hold-out datasets was variable however both the ensemble and MCDO uncertainty estimation approaches were able to accurately estimate model confidence with a p-value < 0.001 for both TOPGEAR and RAVES when comparing the DSC using the Pearson correlation coefficient. CONCLUSIONS: We demonstrated that training auto-segmentation models which can estimate aleatoric and epistemic uncertainty using limited datasets is possible. Having the model estimate prediction confidence is important to understand for which unseen cases a model is likely to be useful.

Evaluating the relationship between contouring variability and modelled treatment outcome for prostate bed radiotherapy.

Objectives.Contouring similarity metrics are often used in studies of inter-observer variation and automatic segmentation but do not provide an assessment of clinical impact. This study focused on post-prostatectomy radiotherapy and aimed to (1) identify if there is a relationship between variations in commonly used contouring similarity metrics and resulting dosimetry and (2) identify the variation in clinical target volume (CTV) contouring that significantly impacts dosimetry.Approach.The study retrospectively analysed CT scans of 10 patients from the TROG 08.03 RAVES trial. The CTV, rectum, and bladder were contoured independently by three experienced observers. Using these contours reference simultaneous truth and performance level estimation (STAPLE) volumes were established. Additional CTVs were generated using an atlas algorithm based on a single benchmark case with 42 manual contours. Volumetric-modulated arc therapy (VMAT) treatment plans were generated for the observer, atlas, and reference volumes. The dosimetry was evaluated using radiobiological metrics. Correlations between contouring similarity and dosimetry metrics were calculated using Spearman coefficient (Γ). To access impact of variations in planning target volume (PTV) margin, the STAPLE PTV was uniformly contracted and expanded, with plans created for each PTV volume. STAPLE dose-volume histograms (DVHs) were exported for plans generated based on the contracted/expanded volumes, and dose-volume metrics assessed.Mainresults. The study found no strong correlations between the considered similarity metrics and modelled outcomes. Moderate correlations (0.5 <Γ< 0.7) were observed for Dice similarity coefficient, Jaccard, and mean distance to agreement metrics and rectum toxicities. The observations of this study indicate a tendency for variations in CTV contraction/expansion below 5 mm to result in minor dosimetric impacts.Significance. Contouring similarity metrics must be used with caution when interpreting them as indicators of treatment plan variation. For post-prostatectomy VMAT patients, this work showed variations in contours with an expansion/contraction of less than 5 mm did not lead to notable dosimetric differences, this should be explored in a larger dataset to assess generalisability.

Prostate Virtual High-dose-rate Brachytherapy Boost: 5-Year Results from the PROMETHEUS Prospective Multicentre Trial.

BACKGROUND AND OBJECTIVE: Despite the high efficacy of high-dose-rate brachytherapy boost (HDRB) in the management of prostate cancer (PC), use of this approach is declining. Similar dosimetry can be achieved using stereotactic body radiotherapy or "virtual HDRB" (vHDRB). The aim of the multicentre, single-arm, phase 2 PROMETHEUS trial (ACTRN12615000223538) was to evaluate the safety and efficacy of vHDRB in patients with PC. METHODS: Patients with intermediate-risk PC or selected patients with high-risk PC were eligible for inclusion. vHDRB was given as 19-20 Gy in two fractions, delivered 1 wk apart, followed by conventionally fractionated external beam radiotherapy (EBRT) at 46 Gy in 23 fractions or 36 Gy in 12 fractions. The primary endpoint was the biochemical/clinical relapse-free rate (bcRFR). Toxicity was graded using Common Terminology Criteria for Adverse Events version 4 and quality of life (QoL) data were collected used the Expanded Prostate Cancer Index Composite-26 questionnaire. KEY FINDINGS AND LIMITATIONS: From March 2014 to December 2018, 151 patients (74% intermediate risk, 26% high risk) with a median age of 69 yr were treated across five centres. Median follow-up was 60 mo. The 5-yr bcRFR was 94.1% (95% confidence interval [CI] 90-98%) and the local control rate was 98.7%. Acute grade 2 gastrointestinal (GI) and genitourinary (GU) toxicity occurred in 6.6% and 23.2% of patients, respectively, with no acute grade 3 toxicity. At 60 mo after treatment, the prevalence of late grade ≥2 GI toxicity was 1.7% (95% CI 0.3-6.5%) and the prevalence of late grade ≥2 GU toxicity was 3.3% (95% CI 1.1-8.8%). Between baseline and 60 mo, QoL improved for urinary obstructive and hormonal domains, was stable for the bowel domain, and deteriorated slightly for the sexual and urinary incontinence domains. CONCLUSIONS: Delivery of gantry-based vHDRB followed by conventionally fractionated EBRT is feasible in a multicentre setting, with high 5-yr bcRFR and low toxicity. This approach is being compared with prostate ultrahypofractionated radiotherapy in the TROG 18.01 NINJA randomised trial (ACTRN12618001806257). PATIENT SUMMARY: The PROMETHEUS trial investigated noninvasive high-dose precision radiotherapy combined with conventional radiotherapy in patients with prostate cancer. We found that this new technique was well tolerated and resulted in better cancer control outcomes than historically reported.

Phase 2 Multicenter Study of Gantry-Based Stereotactic Radiotherapy Boost for Intermediate and High Risk Prostate Cancer (PROMETHEUS).

Objectives: To report feasibility, early toxicity, and PSA kinetics following gantry-based, stereotactic radiotherapy (SBRT) boost within a prospective, phase 2, multicenter study (PROMETHEUS: ACTRN12615000223538). Methods: Patients were treated with gantry-based SBRT, 19-20 Gy in two fractions delivered 1 week apart, followed by conventionally fractionated IMRT (46 Gy in 23 fractions). The study mandated MRI fusion for RT planning, rectal displacement, and intrafraction image guidance. Toxicity was prospectively graded using the Common Terminology Criteria for Adverse Events version 4.0 (CTCAE v4). Results: Between March 2014 and July 2018, 135 patients (76% intermediate, 24% high-risk) with a median age of 70 years (range 53-81) were treated across five centers. Short course (≤6 months) androgen deprivation therapy (ADT) was used in 36% and long course in 18%. Rectal displacement method was SpaceOAR in 59% and Rectafix in 41%. Forty-two and ninety-three patients were treated at the 19 Gy and 20 Gy dose levels, respectively. Median follow-up was 24 months. Acute grade 2 gastrointestinal (GI) and urinary toxicity occurred in 4.4 and 26.6% with no acute grade 3 toxicity. At 6, 12, 18, 24, and 36 months post-treatment the prevalence of late grade ≥2 gastrointestinal toxicity was 1.6, 3.7, 2.2, 0, and 0%, respectively, and the prevalence of late grade ≥2 urinary toxicity was 0.8, 11, 12, 7.1, and 6.3%, respectively. Three patients experienced grade 3 late toxicity at 12 to 18 months which subsequently resolved to grade 2 or less. For patients not receiving ADT the median PSA value pre-treatment was 7.6 ug/L (1.1-20) and at 12, 24, and 36 months post-treatment was 0.86, 0.36, and 0.20 ug/L. Conclusions: Delivery of a gantry-based SBRT boost is feasible in a multicenter setting, is well-tolerated with low rates of early toxicity and is associated with promising PSA responses. A second transient peak in urinary toxicity was observed at 18 months which subsequently resolved. Follow-up is ongoing to document late toxicity, long-term patient reported outcomes, and tumor control with this approach.

Reduced motion and improved rectal dosimetry through endorectal immobilization for prostate stereotactic body radiotherapy.

OBJECTIVE: PROMETHEUS (ACTRN12615000223538) is a multicentre clinical trial investigating the feasibility of 19 Gy in 2 fractions of stereotactic body radiotherapy (SBRT) as a boost technique for prostate cancer. The objective of this substudy was to evaluate intrafraction motion using cine MRI and assess the dosimetric impact of using a rectal displacement device (RDD). METHODS: The initial 10 patients recruited underwent planning CT and MRI, with and without a RDD. Cine MRI images were captured using an interleaved T2 HASTE sequence in sagittal and axial planes with a temporal resolution of 5.2 s acquired over 4.3 min. Points of interest (POIs) were defined and a validated tracking algorithm measured displacement of these points over the 4.3 min in the anteroposterior, superior-inferior and left-right directions. Plans were generated with and without a RDD to examine the impact on dosimetry. RESULTS: There was an overall trend for increasing displacement in all directions as time progressed when no RDD was in situ . points of interest remained comparatively stable with the RDD. In the sagittal plane, the RDD resulted in statistically significant improvement in the range of anteroposterior displacement for the rectal wall, anterior prostate, prostate apex and base. Dosimetrically, the use of a RDD significantly reduced rectal V16, V14 and Dmax, as well as the percentage of posterior rectal wall receiving 8.5 Gy. CONCLUSION: The RDD used in stereotactic prostate radiotherapy leads to reduced intrafraction motion of the prostate and rectum, with increasing improvement with time. It also results in significant improvement in rectal wall dosimetry. ADVANCES IN KNOWLEDGE: It was found that the rectal displacement device improved prostate stabilization significantly, improved rectum stabilization and dosimetry significantly. The rectal displacement device did not improve target volume dosimetry.

PROstate Multicentre External beam radioTHErapy Using a Stereotactic boost: the PROMETHEUS study protocol.

BACKGROUND: High Dose Rate Brachytherapy (HDRB) boost is a well-established treatment for prostate cancer (PC). We describe the PROstate Multicentre External beam radioTHErapy Using Stereotactic boost (PROMETHEUS) study. Non-surgical stereotactic techniques are used to deliver similar doses to HDRB boost regimens with a dose escalation sub-study. METHODS: Eligible patients have intermediate or high risk PC. PROMETHEUS explores the safety, efficacy and feasibility of multiple Australian centres cooperating in the delivery of Prostate Stereotactic Body Radiotherapy (SBRT) technology. A SBRT boost component Target Dose (TD) of 19Gy in two fractions is to be delivered, followed by a subsequent EBRT component of 46Gy in 23 fractions. Once accrual triggers have been met, SBRT doses can be escalated in 1 Gy increments to a maximum of 22Gy in two fractions. Patient safety will also be measured with the rate of both acute and late moderate to severe Gastro-Intestinal (GI) and Genito-Urinary (GU) Common Terminology Criteria for Adverse Events (CTCAE) toxicities as well as patient reported quality of life. Efficacy will be assessed via biochemical control after 3 years. DISCUSSION: PROMETHEUS aims to generate evidence for a non-surgical possible future alternative to HDRB boost regimens, and introduce advanced radiotherapy techniques across multiple Australian cancer centres. TRIAL REGISTRATION: The study was retrospectively registered on the ANZCTR (Australian New Zealand Clinical Trials Registry) with trial ID: ACTRN12615000223538 .

Rectal protection in prostate stereotactic radiotherapy: a retrospective exploratory analysis of two rectal displacement devices.

INTRODUCTION: High rectal doses are associated with increased toxicity. A rectal displacement device (RDD) reduces rectal dose in prostate stereotactic body radiation therapy (SBRT). This study investigates any dosimetric difference between two methods of rectal displacement (Rectafix and SpaceOAR) for prostate SBRT. METHODS: Rectal dosimetry of 45 men who received SBRT within the PROMETHEUS trial was retrospectively examined, across two radiation therapy centres using the two RDD's. Men received a total dose (TD) of 19 or 20 Gy in two fractions followed by 46 Gy in 23 fractions. Centre 1 contributed 16 Rectafix and 10 SpaceOAR patients. Centre 2 contributed 19 Rectafix patients. Rectal dose volume histogram (DVH) data were recorded as a TD percentage at the following volume intervals; V1%, V2%, V5%, V10% and then 10% increments to V80%. As only one centre employed both RDD's, three sequential rectal dosimetry comparisons were performed; (1) centre 1 Rectafix versus centre 1 SpaceOAR; (2) centre 1 Rectafix versus centre 2 Rectafix and (3) centre 1+ centre 2 Rectafix versus centre 1 SpaceOAR. RESULTS: In comparison (1) Rectafix demonstrated lower mean doses at 9 out of 11 measured intervals (P = 0.0012). Comparison (2) demonstrated a moderate difference with centre 2 plans producing slightly lower rectal doses (P = 0.013). Comparison (3) further demonstrated that Rectafix returned lower mean doses than SpaceOAR (P < 0.001). Although all dose levels were in favour of Rectafix, in absolute terms differences were small (2.6-9.0%). CONCLUSIONS: In well-selected prostate SBRT patients, Rectafix and SpaceOAR RDD's provide approximately equivalent rectal sparing.

Superior target volume and organ stability with the use of endorectal balloons in post-prostatectomy radiotherapy.

INTRODUCTION: We investigated the endorectal balloon (ERB) as a method to improve post-prostatectomy clinical target volume (CTV) stability. METHODS: Seventy cone-beam CT (CBCT) obtained during radiotherapy treatment from seven patients treated with an ERB and 68 CBCT from seven patients treated without an ERB were contoured according to published guidelines. CTV was subdivided into superior and inferior CTV; whole rectal volume was subdivided into superior and inferior rectum and anal volume. Concordance index (CI) of CBCT treatment volumes compared with planning volumes was calculated and displacements were measured. RESULTS: Whole rectal, superior and inferior rectum and anal CI were significantly improved with the ERB by 21%, 17%, 26% and 17% respectively (P < 0.0001). Overall CTV and inferior CTV CI was improved by 4% with the ERB (overall CTV P = 0.021; Inferior CTV P < 0.0001). In the ERB cohort, average displacement for superior CTV was 0.37 cm anterior-posterior (AP) and 0.10 cm left-right (LR). Average standard deviation was 0.27 cm AP and 0.11 cm LR. Inferior CTV average displacement was 0.11 cm AP and 0.02 cm LR. Average standard deviation was 0.11 cm AP and 0.02 cm LR. In the non-ERB cohort, average displacement for superior CTV was 0.43 cm AP and 0.10 mm left-right (LR). Average standard deviation was 0.45 cm AP and 0.13 cm LR. Inferior CTV average displacement was 0.16 cm AP and 0.01 cm LR. Average standard deviation was 0.17 cm AP and 0.03 cm LR. There was no statistically significant impact of bladder filling on CTV CI in ERB patients (P = 0.551) as opposed to non-ERB patients (P = 0.0421). CONCLUSION: ERBs in the post-prostatectomy setting resulted in increased rectal and CTV stability while negating the effects of bladder filling on CTV stability.

Endorectal balloons in the post prostatectomy setting: do gains in stability lead to more predictable dosimetry?

PURPOSE: To perform a comparative study assessing potential benefits of endorectal-balloons (ERB) in post-prostatectomy patients. METHOD AND MATERIALS: Ten retrospective post-prostatectomy patients treated without ERB and ten prospective patients treated with the ERB in situ were recruited. All patients received IMRT and IGRT using kilovoltage cone-beam computed tomography (kVCBCT). kVCBCT datasets were registered to the planning dataset, recontoured and the original plan recalculated on the kVCBCTs to recreate anatomical conditions during treatment. The imaging, structure and dose data were imported into in-house software for the assessment of geometric variation and cumulative equivalent uniform dose (EUD) in the two groups. RESULTS: The difference in location (ΔCOV) for the bladder between planning and each CBCT was similar for each group. The range of mean ΔCOV for the rectum was 0.15-0.58 cm and 0.15-0.59 cm for the non-ERB and ERB groups. For superior-CTV and inferior-CTV the difference between planned and delivered D95% (mean ± SD) for the non-ERB group was 2.1 ± 6.0 Gy and -0.04 ± 0.20 Gy. While for the ERB group the difference in D95% was 8.7 ± 12.6 Gy and 0.003 ± 0.104 Gy. CONCLUSIONS: The use of ERBs in the post-prostatectomy setting did improve geometric reproducibility of the target and surrounding normal tissues, however no improvement in dosimetric stability was observed for the margins employed.