A randomised controlled trial of Standard Of Care versus RadioAblaTion in Early Stage HepatoCellular Carcinoma (SOCRATES HCC).

BACKGROUND: Therapeutic options for early-stage hepatocellular carcinoma (HCC) in individual patients can be limited by tumor and location, liver dysfunction and comorbidities. Many patients with early-stage HCC do not receive curative-intent therapies. Stereotactic ablative body radiotherapy (SABR) has emerged as an effective, non-invasive HCC treatment option, however, randomized evidence for SABR in the first line setting is lacking. METHODS: Trans-Tasman Radiation Oncology Group (TROG) 21.07 SOCRATES-HCC is a phase II, prospective, randomised trial comparing SABR to other current standard of care therapies for patients with a solitary HCC ≤ 8 cm, ineligible for surgical resection or transplantation. The study is divided into 2 cohorts. Cohort 1 will compromise 118 patients with tumors ≤ 3 cm eligible for thermal ablation randomly assigned (1:1 ratio) to thermal ablation or SABR. Cohort 2 will comprise 100 patients with tumors > 3 cm up to 8 cm in size, or tumors ≤ 3 cm ineligible for thermal ablation, randomly assigned (1:1 ratio) to SABR or best other standard of care therapy including transarterial therapies. The primary objective is to determine whether SABR results in superior freedom from local progression (FFLP) at 2 years compared to thermal ablation in cohort 1 and compared to best standard of care therapy in cohort 2. Secondary endpoints include progression free survival, overall survival, adverse events, patient reported outcomes and health economic analyses. DISCUSSION: The SOCRATES-HCC study will provide the first randomized, multicentre evaluation of the efficacy, safety and cost effectiveness of SABR versus other standard of care therapies in the first line treatment of unresectable, early-stage HCC. It is a broad, multicentre collaboration between hepatology, interventional radiology and radiation oncology groups around Australia, coordinated by TROG Cancer Research. TRIAL REGISTRATION: anzctr.org.au, ACTRN12621001444875, registered 21 October 2021.

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.

Improving motion management in radiation therapy: findings from a workshop and survey in Australia and New Zealand.

Motion management has become an integral part of radiation therapy. Multiple approaches to motion management have been reported in the literature. To allow the sharing of experiences on current practice and emerging technology, the University of Sydney and the New South Wales/Australian Capital Territory branch of the Australasian College of Physical Scientists and Engineers in Medicine (ACPSEM) held a two-day motion management workshop. To inform the workshop program, participants were invited to complete a survey prior to the workshop on current use of motion management techniques and their opinion on the effectiveness of each approach. A post-workshop survey was also conducted, designed to capture changes in opinion as a result of workshop participation. The online workshop was the most well attended ever hosted by the ACPSEM, with over 300 participants and a response to the pre-workshop survey was received from at least 60% of the radiation therapy centres in Australia and New Zealand. Motion management is extensively used in the region with use of deep inspiration breath-hold (DIBH) reported by 98% of centres for left-sided breast treatments and 91% for at least some right-sided breast treatments. Surface guided radiation therapy (SGRT) was the most popular session at the workshop and survey results showed that the use of SGRT is likely to increase. The workshop provided an excellent opportunity for the exchange of knowledge and experience, with most survey respondents indicating that their participation would lead to improvements in the quality of delivery of treatments at their centres.

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.

Local hero: A phase II study of local therapy only (stereotactic radiosurgery and / or surgery) for treatment of up to five brain metastases from HER2+ breast cancer. (TROG study 16.02).

Introduction, A decade ago, stereotactic radiosurgery (SRS) without whole brain radiotherapy (WBRT) was emerging as preferred treatment for oligometastatic brain metastases. Studies of cavity SRS after neurosurgery were underway. Data specific to metastatic HER2 breast cancer (MHBC), describing intracranial, systemic and survival outcomes without WBRT, were lacking. A Phase II study was designed to address this gap. Method, Adults with MHBC, performance status 0-2, ≤ five BrM, receiving/planned to receive HER2-targeted therapy were eligible. Exclusions included leptomeningeal disease and prior WBRT. Neurosurgery allowed ≤6 weeks before registration and required for BrM >4 cm. Primary endpoint was 12-month requirement for WBRT. Secondary endpoints; freedom from (FF-) local failure (LF), distant brain failure (DBF), extracranial disease failure (ECDF), overall survival (OS), cause of death, mini-mental state examination (MMSE), adverse events (AE). Results, Twenty-five patients accrued Decembers 2016-2020. The study closed early after slow accrual. Thirty-seven BrM and four cavities received SRS. Four cavities and five BrM were observed. At 12 months: one patient required WBRT (FF-WBRT 95 %, 95 % CI 72-99), FFLF 91 % (95 % CI 69-98), FFDBF 57 % (95 % CI 34-74), FFECDF 64 % (95 % CI 45-84), OS 96 % (95 % CI 74-99). Two grade 3 AE occurred. MMSE was abnormal for 3/24 patients at baseline and 1/17 at 12 months. Conclusion, At 12 months, SRS and/or neurosurgery provided good control with low toxicity. WBRT was not required in 95 % of cases. This small study supports the practice change from WBRT to local therapies for MHBC BrM.

Robustness of magnetic resonance imaging and positron emission tomography radiomic features in prostate cancer: Impact on recurrence prediction after radiation therapy.

Background and purpose: Radiomic features from MRI and PET are an emerging tool with potential to improve prostate cancer outcomes. However, feature robustness due to image segmentation variations is currently unknown. Therefore, this study aimed to evaluate the robustness of radiomic features with segmentation variations and their impact on predicting biochemical recurrence (BCR). Materials and methods: Multi-scanner, pre-radiation therapy imaging from 142 patients with localised prostate cancer was used. Imaging included T2-weighted (T2), apparent diffusion coefficient (ADC) MRI, and prostate-specific membrane antigen (PSMA)-PET. The prostate gland and intraprostatic tumours were manually and automatically segmented, and differences were quantified using Dice Coefficient (DC). Radiomic features including shape, first-order, and texture features were extracted for each segmentation from original and filtered images. Intraclass Correlation Coefficient (ICC) and Mean Absolute Percentage Difference (MAPD) were used to assess feature robustness. Random forest (RF) models were developed for each segmentation using robust features to predict BCR. Results: Prostate gland segmentations were more consistent (mean DC = 0.78) than tumour segmentations (mean DC = 0.46). 112 (3.6 %) radiomic features demonstrated 'excellent' robustness (ICC > 0.9 and MAPD < 1 %), and 480 features (15.4 %) demonstrated 'good' robustness (ICC > 0.75 and MAPD < 5 %). PET imaging provided more features with excellent robustness than T2 and ADC. RF models showed strong predictive power for BCR with a mean area under the receiver-operator-characteristics curve (AUC) of 0.89 (range 0.85-0.93). Conclusion: When using radiomic features for predictive modelling, segmentation variability should be considered. To develop BCR predictive models, radiomic features from the entire prostate gland are preferable over tumour segmentation-based features.

Towards optimal heterogeneous prostate radiotherapy dose prescriptions based on patient-specific or population-based biological features.

BACKGROUND: Escalation of prescribed dose in prostate cancer (PCa) radiotherapy enables improvement in tumor control at the expense of increased toxicity. Opportunities for reduction of treatment toxicity may emerge if more efficient dose escalation can be achieved by redistributing the prescribed dose distribution according to the known heterogeneous, spatially-varying characteristics of the disease. PURPOSE: To examine the potential benefits, limitations and characteristics of heterogeneous boost dose redistribution in PCa radiotherapy based on patient-specific and population-based spatial maps of tumor biological features. METHOD: High-resolution prostate histology images, from a cohort of 63 patients, annotated with tumor location and grade, provided patient-specific "maps" and a population-based "atlas" of cell density and tumor probability. Dose prescriptions were derived for each patient based on a heterogeneous redistribution of the boost dose to the intraprostatic lesions, with the prescription maximizing patient tumor control probability (TCP). The impact on TCP was assessed under scenarios where the distribution of population-based biological data was ignored, partially included, or fully included in prescription generation. Heterogeneous dose prescriptions were generated for three combinations of maps and atlas, and for conventional fractionation (CF), extreme hypo-fractionation (EH), moderate hypo-fractionation (MH), and whole Pelvic RT + SBRT Boost (WPRT + SBRT). The predicted efficacy of the heterogeneous prescriptions was compared with equivalent homogeneous dose prescriptions. RESULTS: TCPs for heterogeneous dose prescriptions were generally higher than those for homogeneous dose prescriptions. TCP escalation by heterogeneous dose prescription was the largest for CF. When only using population-based atlas data, the generated heterogeneous dose prescriptions of 55 to 58 patients (out of 63) had a higher TCP than for the corresponding homogeneous dose prescriptions. The TCPs of the heterogeneous dose prescriptions generated with the population-based atlas and tumor probability maps did not differ significantly from those using patient-specific biological information. The generated heterogeneous dose prescriptions achieved significantly higher TCP than homogeneous dose prescriptions in the posterior section of the prostate. CONCLUSION: Heterogeneous dose prescriptions generated via biologically-optimized dose redistribution can produce higher TCP than the homogeneous dose prescriptions for the majority of the patients in the studied cohort. For scenarios where patient-specific biological information was unavailable or partially available, the generated heterogeneous dose prescriptions can still achieve TCP improvement relative to homogeneous dose prescriptions.

The rationale for a carbon ion radiation therapy facility in Australia.

Australia has taken a collaborative nationally networked approach to achieve particle therapy capability. This supports the under-construction proton therapy facility in Adelaide, other potential proton centres and an under-evaluation proposal for a hybrid carbon ion and proton centre in western Sydney. A wide-ranging overview is presented of the rationale for carbon ion radiation therapy, applying observations to the case for an Australian facility and to the clinical and research potential from such a national centre.

Focal Boost in Prostate Cancer Radiotherapy: A Review of Planning Studies and Clinical Trials.

BACKGROUND: Focal boost radiotherapy was developed to deliver elevated doses to functional sub-volumes within a target. Such a technique was hypothesized to improve treatment outcomes without increasing toxicity in prostate cancer treatment. PURPOSE: To summarize and evaluate the efficacy and variability of focal boost radiotherapy by reviewing focal boost planning studies and clinical trials that have been published in the last ten years. METHODS: Published reports of focal boost radiotherapy, that specifically incorporate dose escalation to intra-prostatic lesions (IPLs), were reviewed and summarized. Correlations between acute/late ≥G2 genitourinary (GU) or gastrointestinal (GI) toxicity and clinical factors were determined by a meta-analysis. RESULTS: By reviewing and summarizing 34 planning studies and 35 trials, a significant dose escalation to the GTV and thus higher tumor control of focal boost radiotherapy were reported consistently by all reviewed studies. Reviewed trials reported a not significant difference in toxicity between focal boost and conventional radiotherapy. Acute ≥G2 GU and late ≥G2 GI toxicities were reported the most and least prevalent, respectively, and a negative correlation was found between the rate of toxicity and proportion of low-risk or intermediate-risk patients in the cohort. CONCLUSION: Focal boost prostate cancer radiotherapy has the potential to be a new standard of care.

Viability of focal dose escalation to prostate cancer intraprostatic lesions using HDR prostate brachytherapy.

PURPOSE: This study aimed to determine the viability of focal dose escalation to prostate cancer intraprostatic lesions (IPLs) from multiparametric magnetic resonance (mpMRI) and prostate-specific membrane antigen positron emission tomography (PSMA-PET) images using high-dose-rate (HDR) prostate brachytherapy (pBT). METHODS AND MATERIALS: Retrospective data from 20 patients treated with HDR pBT was utilized. The interobserver contouring variability of 5 observers was quantified using the dice similarity coefficient (DSC) and mean distance to agreement (MDA). Uncertainty in propagating IPL contours to trans-rectal ultrasound (TRUS) was quantified using a tissue equivalent prostate phantom. Feasibility of incorporating IPLs into HDR pBT planning was tested on retrospective patient data. RESULTS: The average observer DSC was 0.65 (PSMA-PET) and 0.52 (mpMRI). The uncertainty in propagating IPL contours was 0.6 mm (PSMA-PET), and 0.4 mm (mpMRI). Uncertainties could be accounted for by expanding IPL contours by 2 mm to create IPL PTVs. The mean D98% achieved using HDR pBT was 166% and 135% for the IPL and IPL PTV contours, respectively. CONCLUSIONS: Focal dose escalation to IPLs identified on either PSMA-PET or mpMRI is viable using TRUS-based HDR pBT. Utilizing HDR pBT allows dose escalation of up to 166% of the prescribed dose to the prostate.

Genomic and Phenotypic Biomarkers for Precision Medicine Guidance in Advanced Prostate Cancer.

OPINION STATEMENT: Prostate cancer (PCa) is the second most diagnosed malignant neoplasm and is one of the leading causes of cancer-related death in men worldwide. Despite significant advances in screening and treatment of PCa, given the heterogeneity of this disease, optimal personalized therapeutic strategies remain limited. However, emerging predictive and prognostic biomarkers based on individual patient profiles in combination with computer-assisted diagnostics have the potential to guide precision medicine, where patients may benefit from therapeutic approaches optimally suited to their disease. Also, the integration of genotypic and phenotypic diagnostic methods is supporting better informed treatment decisions. Focusing on advanced PCa, this review discusses polygenic risk scores for screening of PCa and common genomic aberrations in androgen receptor (AR), PTEN-PI3K-AKT, and DNA damage response (DDR) pathways, considering clinical implications for diagnosis, prognosis, and treatment prediction. Furthermore, we evaluate liquid biopsy, protein biomarkers such as serum testosterone levels, SLFN11 expression, total alkaline phosphatase (tALP), neutrophil-to-lymphocyte ratio (NLR), tissue biopsy, and advanced imaging tools, summarizing current phenotypic biomarkers and envisaging more effective utilization of diagnostic and prognostic biomarkers in advanced PCa. We conclude that prognostic and treatment predictive biomarker discovery can improve the management of patients, especially in metastatic stages of advanced PCa. This will result in decreased mortality and enhanced quality of life and help design a personalized treatment regimen.

AAPM WGDCAB Report 372: A joint AAPM, ESTRO, ABG, and ABS report on commissioning of model-based dose calculation algorithms in brachytherapy.

The introduction of model-based dose calculation algorithms (MBDCAs) in brachytherapy provides an opportunity for a more accurate dose calculation and opens the possibility for novel, innovative treatment modalities. The joint AAPM, ESTRO, and ABG Task Group 186 (TG-186) report provided guidance to early adopters. However, the commissioning aspect of these algorithms was described only in general terms with no quantitative goals. This report, from the Working Group on Model-Based Dose Calculation Algorithms in Brachytherapy, introduced a field-tested approach to MBDCA commissioning. It is based on a set of well-characterized test cases for which reference Monte Carlo (MC) and vendor-specific MBDCA dose distributions are available in a Digital Imaging and Communications in Medicine-Radiotherapy (DICOM-RT) format to the clinical users. The key elements of the TG-186 commissioning workflow are now described in detail, and quantitative goals are provided. This approach leverages the well-known Brachytherapy Source Registry jointly managed by the AAPM and the Imaging and Radiation Oncology Core (IROC) Houston Quality Assurance Center (with associated links at ESTRO) to provide open access to test cases as well as step-by-step user guides. While the current report is limited to the two most widely commercially available MBDCAs and only for 192 Ir-based afterloading brachytherapy at this time, this report establishes a general framework that can easily be extended to other brachytherapy MBDCAs and brachytherapy sources. The AAPM, ESTRO, ABG, and ABS recommend that clinical medical physicists implement the workflow presented in this report to validate both the basic and the advanced dose calculation features of their commercial MBDCAs. Recommendations are also given to vendors to integrate advanced analysis tools into their brachytherapy treatment planning system to facilitate extensive dose comparisons. The use of the test cases for research and educational purposes is further encouraged.

Clinical target volume delineation quality assurance for MRI-guided prostate radiotherapy using deep learning with uncertainty estimation.

BACKGROUND AND PURPOSE: Previous studies on automatic delineation quality assurance (QA) have mostly focused on CT-based planning. As MRI-guided radiotherapy is increasingly utilized in prostate cancer treatment, there is a need for more research on MRI-specific automatic QA. This work proposes a clinical target volume (CTV) delineation QA framework based on deep learning (DL) for MRI-guided prostate radiotherapy. MATERIALS AND METHODS: The proposed workflow utilized a 3D dropblock ResUnet++ (DB-ResUnet++) to generate multiple segmentation predictions via Monte Carlo dropout which were used to compute an average delineation and area of uncertainty. A logistic regression (LR) classifier was employed to classify the manual delineation as pass or discrepancy based on the spatial association between the manual delineation and the network's outputs. This approach was evaluated on a multicentre MRI-only prostate radiotherapy dataset and compared with our previously published QA framework based on AN-AG Unet. RESULTS: The proposed framework achieved an area under the receiver operating curve (AUROC) of 0.92, a true positive rate (TPR) of 0.92 and a false positive rate of 0.09 with an average processing time per delineation of 1.3 min. Compared with our previous work using AN-AG Unet, this method generated fewer false positive detections at the same TPR with a much faster processing speed. CONCLUSION: To the best of our knowledge, this is the first study to propose an automatic delineation QA tool using DL with uncertainty estimation for MRI-guided prostate radiotherapy, which can potentially be used for reviewing prostate CTV delineation in multicentre clinical trials.

U-Net Architecture for Prostate Segmentation: The Impact of Loss Function on System Performance.

Segmentation of the prostate gland from magnetic resonance images is rapidly becoming a standard of care in prostate cancer radiotherapy treatment planning. Automating this process has the potential to improve accuracy and efficiency. However, the performance and accuracy of deep learning models varies depending on the design and optimal tuning of the hyper-parameters. In this study, we examine the effect of loss functions on the performance of deep-learning-based prostate segmentation models. A U-Net model for prostate segmentation using T2-weighted images from a local dataset was trained and performance compared when using nine different loss functions, including: Binary Cross-Entropy (BCE), Intersection over Union (IoU), Dice, BCE and Dice (BCE + Dice), weighted BCE and Dice (W (BCE + Dice)), Focal, Tversky, Focal Tversky, and Surface loss functions. Model outputs were compared using several metrics on a five-fold cross-validation set. Ranking of model performance was found to be dependent on the metric used to measure performance, but in general, W (BCE + Dice) and Focal Tversky performed well for all metrics (whole gland Dice similarity coefficient (DSC): 0.71 and 0.74; 95HD: 6.66 and 7.42; Ravid 0.05 and 0.18, respectively) and Surface loss generally ranked lowest (DSC: 0.40; 95HD: 13.64; Ravid -0.09). When comparing the performance of the models for the mid-gland, apex, and base parts of the prostate gland, the models' performance was lower for the apex and base compared to the mid-gland. In conclusion, we have demonstrated that the performance of a deep learning model for prostate segmentation can be affected by choice of loss function. For prostate segmentation, it would appear that compound loss functions generally outperform singles loss functions such as Surface loss.

Detecting localised prostate cancer using radiomic features in PSMA PET and multiparametric MRI for biologically targeted radiation therapy.

BACKGROUND: Prostate-Specific Membrane Antigen (PSMA) PET/CT and multiparametric MRI (mpMRI) are well-established modalities for identifying intra-prostatic lesions (IPLs) in localised prostate cancer. This study aimed to investigate the use of PSMA PET/CT and mpMRI for biologically targeted radiation therapy treatment planning by: (1) analysing the relationship between imaging parameters at a voxel-wise level and (2) assessing the performance of radiomic-based machine learning models to predict tumour location and grade. METHODS: PSMA PET/CT and mpMRI data from 19 prostate cancer patients were co-registered with whole-mount histopathology using an established registration framework. Apparent Diffusion Coefficient (ADC) maps were computed from DWI and semi-quantitative and quantitative parameters from DCE MRI. Voxel-wise correlation analysis was conducted between mpMRI parameters and PET Standardised Uptake Value (SUV) for all tumour voxels. Classification models were built using radiomic and clinical features to predict IPLs at a voxel level and then classified further into high-grade or low-grade voxels. RESULTS: Perfusion parameters from DCE MRI were more highly correlated with PET SUV than ADC or T2w. IPLs were best detected with a Random Forest Classifier using radiomic features from PET and mpMRI rather than either modality alone (sensitivity, specificity and area under the curve of 0.842, 0.804 and 0.890, respectively). The tumour grading model had an overall accuracy ranging from 0.671 to 0.992. CONCLUSIONS: Machine learning classifiers using radiomic features from PSMA PET and mpMRI show promise for predicting IPLs and differentiating between high-grade and low-grade disease, which could be used to inform biologically targeted radiation therapy planning.

A survey of compliance with stereotactic ablative body radiotherapy quality recommendations.

INTRODUCTION: Many publications have proposed quality standards for stereotactic ablative body radiotherapy (SABR). However, data on the level of compliance with these guidelines is lacking in the literature. This study aimed to understand how these guidelines are applied in the clinic and to identify barriers to implementing such recommendations. METHODS: Interviews were conducted with multidisciplinary staff at radiation oncology centres across New South Wales formulated around the RANZCR Guidelines for Safe Practice of Stereotactic Body (Ablative) Radiation Therapy. The interview responses were grouped into 20 topics, assessed against the guidelines and thematically analysed. RESULTS: Good compliance with the guidelines was found, with more than 80% of centres achieving satisfactory results in more than half the topics. The areas with the lowest compliance were auditing, risk assessment and reporting recommendations. Barriers to the quality of SABR treatments included limited training opportunities, low patient numbers and a lack of clear requirements on comprehensive auditing and reporting. CONCLUSION: Overall, the centres surveyed reported good compliance with most of the RANZCR SABR guidelines. The tasks with the lowest compliance were those that monitor quality outcomes. Potential strategies for improvement include inclusion in clinical trials and the use of databases which link treatment parameters, dosimetry and outcomes. Further work will focus on the barriers identified in this survey and propose practical solutions to improve compliance in these areas.

Patient-specific voxel-level dose prescription for prostate cancer radiotherapy considering tumor cell density and grade distribution.

BACKGROUND: In prostate radiation therapy, recent studies have indicated a benefit in increasing the dose to intraprostatic lesions (IPL) compared with standard whole gland radiation therapy. Such approaches typically aim to deliver a target dose to the IPL(s) with no deliberate effort to modulate the dose within the IPL. Prostate cancers demonstrate intra-tumor heterogeneity and hence it is hypothesized that further gains in the optimal delivery of radiation therapy can be achieved through modulation of the dose distribution within the tumor. To account for tumor heterogeneity, biologically targeted radiation therapy (BiRT) aims to utilize a voxel-wise approach to IPL dose prescription by incorporating knowledge of the spatial distribution of tumor characteristics. PURPOSE: The aim of this study was to develop a workflow for generating voxel-wise optimal dose prescriptions that maximize patient tumor control probability (TCP), and evaluate the feasibility and benefits of applying this workflow on a cohort of 62 prostate cancer patients. METHOD: The source data for this proof-of-concept study included high resolution histology images annotated with tumor location and grade. Image processing techniques were used to compute voxel-level cell density distribution maps. An absolute tumor cell distribution was calculated via linearly scaling according to published estimated tumor cell numbers. For the IPLs of each patient, optimal dose prescriptions were obtained via three alternative methods for redistribution of IPL boost doses according to maximization of TCP. The radiosensitivity uncertainties were considered using a truncated log-normally distributed linear radiosensitivity parameter ( α k ${\alpha }_k$ ) and compared with Gleason pattern (GP) dependent radiosensitivity parameters that were derived based on previously published methods. An ensemble machine learning method was implemented to identify patient-specific features that predict the TCP improvement resulting from dose redistribution relative to a uniform dose distribution. RESULTS: The Gleason pattern-dependent radiosensitivity parameters were calculated for 20 published prostate cancer α / ß ${{\alpha}}/{{\beta}}$ ratios. Optimal voxel-level dose prescriptions were generated for all 62 PCa patients. For all dose redistribution scenarios, the optimal dose distribution always shows a higher (or equivalent) TCP level than the uniform dose distribution. The applied random forest regressor could predict patient-specific TCP improvement with low root mean square error (≤1.5%) by using total tumor number, volume of IPLs and the standard deviation of tumor cell number among all voxels. CONCLUSION: Biologically-optimized redistribution of a boost dose can yield TCP improvement relative to a uniform-boost dose distribution. Patient-specific tumor characteristics can be used to predict the likelihood of benefit from a redistribution approach for the individual patient.

Role of Functional MRI in Liver SBRT: Current Use and Future Directions.

Stereotactic body radiation therapy (SBRT) is an emerging treatment for liver cancers whereby large doses of radiation can be delivered precisely to target lesions in 3-5 fractions. The target dose is limited by the dose that can be safely delivered to the non-tumour liver, which depends on the baseline liver functional reserve. Current liver SBRT guidelines assume uniform liver function in the non-tumour liver. However, the assumption of uniform liver function is false in liver disease due to the presence of cirrhosis, damage due to previous chemo- or ablative therapies or irradiation, and fatty liver disease. Anatomical information from magnetic resonance imaging (MRI) is increasingly being used for SBRT planning. While its current use is limited to the identification of target location and size, functional MRI techniques also offer the ability to quantify and spatially map liver tissue microstructure and function. This review summarises and discusses the advantages offered by functional MRI methods for SBRT treatment planning and the potential for adaptive SBRT workflows.

Semi-quantitative and quantitative dynamic contrast-enhanced (DCE) MRI parameters as prostate cancer imaging biomarkers for biologically targeted radiation therapy.

BACKGROUND: Biologically targeted radiation therapy treatment planning requires voxel-wise characterisation of tumours. Dynamic contrast enhanced (DCE) DCE MRI has shown promise in defining voxel-level biological characteristics. In this study we consider the relative value of qualitative, semi-quantitative and quantitative assessment of DCE MRI compared with diffusion weighted imaging (DWI) and T2-weighted (T2w) imaging to detect prostate cancer at the voxel level. METHODS: Seventy prostate cancer patients had multiparametric MRI prior to radical prostatectomy, including T2w, DWI and DCE MRI. Apparent Diffusion Coefficient (ADC) maps were computed from DWI, and semi-quantitative and quantitative parameters computed from DCE MRI. Tumour location and grade were validated with co-registered whole mount histology. Kolmogorov-Smirnov tests were applied to determine whether MRI parameters in tumour and benign voxels were significantly different. Cohen's d was computed to quantify the most promising biomarkers. The Parker and Weinmann Arterial Input Functions (AIF) were compared for their ability to best discriminate between tumour and benign tissue. Classifier models were used to determine whether DCE MRI parameters improved tumour detection versus ADC and T2w alone. RESULTS: All MRI parameters had significantly different data distributions in tumour and benign voxels. For low grade tumours, semi-quantitative DCE MRI parameter time-to-peak (TTP) was the most discriminating and outperformed ADC. For high grade tumours, ADC was the most discriminating followed by DCE MRI parameters Ktrans, the initial rate of enhancement (IRE), then TTP. Quantitative parameters utilising the Parker AIF better distinguished tumour and benign voxel values than the Weinmann AIF. Classifier models including DCE parameters versus T2w and ADC alone, gave detection accuracies of 78% versus 58% for low grade tumours and 85% versus 72% for high grade tumours. CONCLUSIONS: Incorporating DCE MRI parameters with DWI and T2w gives improved accuracy for tumour detection at a voxel level. DCE MRI parameters should be used to spatially characterise tumour biology for biologically targeted radiation therapy treatment planning.

Evaluating the utility of knowledge-based planning for clinical trials using the TROG 08.03 post prostatectomy radiation therapy planning data.

Background and purpose: Poor quality radiotherapy can detrimentally affect outcomes in clinical trials. Our purpose was to explore the potential of knowledge-based planning (KBP) for quality assurance (QA) in clinical trials. Materials and methods: Using 30 in-house post-prostatectomy radiation treatment (PPRT) plans, an iterative KBP model was created according to the multicentre clinical trial protocol, delivering 64 Gy in 32 fractions. KBP was used to replan 137 plans. The KB (knowledge based) plans were evaluated for their ability to fulfil the trial constraints and were compared against their corresponding original treatment plans (OTP). A second analysis between only the 72 inversely planned OTPs (IP-OTPs) and their corresponding KB plans was performed. Results: All dose constraints were met in 100% of KB plans versus 69% of OTPs. KB plans demonstrated significantly less variation in PTV coverage (Mean dose range: KB plans 64.1 Gy-65.1 Gy vs OTP 63.1 Gy-67.3 Gy, p < 0.01). KBP resulted in significantly lower doses to OARs. Rectal V60Gy and V40Gy were 17.7% vs 27.7% (p < 0.01) and 40.5% vs 53.9% (p < 0.01) for KB plans and OTP respectively. Left femoral head (FH) V45Gy and V35Gy were 0.4% vs 7.4% (p < 0.01) and 7.9% vs 34.9% (p < 0.01) respectively. In the second analysis plan improvements were maintained. Conclusions: KBP created high quality PPRT plans using the data from a multicentre clinical trial in a single optimisation. It is a powerful tool for utilisation in clinical trials for patient specific QA, to reduce dose to surrounding OARs and variations in plan quality which could impact on clinical trial outcomes.