Changes in serial multiparametric MRI and FDG-PET/CT functional imaging during radiation therapy can predict treatment response in patients with head and neck cancer.

OBJECTIVES: To test if tumour changes measured using combination of diffusion-weighted imaging (DWI) MRI and FDG-PET/CT performed serially during radiotherapy (RT) in mucosal head and neck carcinoma can predict treatment response. METHODS: Fifty-five patients from two prospective imaging biomarker studies were analysed. FDG-PET/CT was performed at baseline, during RT (week 3), and post RT (3 months). DWI was performed at baseline, during RT (weeks 2, 3, 5, 6), and post RT (1 and 3 months). The ADCmean from DWI and FDG-PET parameters SUVmax, SUVmean, metabolic tumour volume (MTV), and total lesion glycolysis (TLG) were measured. Absolute and relative change (%∆) in DWI and PET parameters were correlated to 1-year local recurrence. Patients were categorised into favourable, mixed, and unfavourable imaging response using optimal cut-off (OC) values of DWI and FDG-PET parameters and correlated to local control. RESULTS: The 1-year local, regional, and distant recurrence rates were 18.2% (10/55), 7.3% (4/55), and 12.7% (7/55), respectively. ∆Week 3 ADCmean (AUC 0.825, p = 0.003; OC ∆ > 24.4%) and ∆MTV (AUC 0.833, p = 0.001; OC ∆ > 50.4%) were the best predictors of local recurrence. Week 3 was the optimal time point for assessing DWI imaging response. Using a combination of ∆ADCmean and ∆MTV improved the strength of correlation to local recurrence (p ≤ 0.001). In patients who underwent both week 3 MRI and FDG-PET/CT, significant differences in local recurrence rates were seen between patients with favourable (0%), mixed (17%), and unfavourable (78%) combined imaging response. CONCLUSIONS: Changes in mid-treatment DWI and FDG-PET/CT imaging can predict treatment response and could be utilised in the design of future adaptive clinical trials. CLINICAL RELEVANCE STATEMENT: Our study shows the complementary information provided by two functional imaging modalities for mid-treatment response prediction in patients with head and neck cancer. KEY POINTS: •FDG-PET/CT and DWI MRI changes in tumour during radiotherapy in head and neck cancer can predict treatment response. •Combination of FDG-PET/CT and DWI parameters improved correlation to clinical outcome. •Week 3 was the optimal time point for DWI MRI imaging response assessment.

Infrastructure platform for privacy-preserving distributed machine learning development of computer-assisted theragnostics in cancer.

INTRODUCTION: Emerging evidence suggests that data-driven support tools have found their way into clinical decision-making in a number of areas, including cancer care. Improving them and widening their scope of availability in various differing clinical scenarios, including for prognostic models derived from retrospective data, requires co-ordinated data sharing between clinical centres, secondary analyses of large multi-institutional clinical trial data, or distributed (federated) learning infrastructures. A systematic approach to utilizing routinely collected data across cancer care clinics remains a significant challenge due to privacy, administrative and political barriers. METHODS: An information technology infrastructure and web service software was developed and implemented which uses machine learning to construct clinical decision support systems in a privacy-preserving manner across datasets geographically distributed in different hospitals. The infrastructure was deployed in a network of Australian hospitals. A harmonized, international ontology-linked, set of lung cancer databases were built with the routine clinical and imaging data at each centre. The infrastructure was demonstrated with the development of logistic regression models to predict major cardiovascular events following radiation therapy. RESULTS: The infrastructure implemented forms the basis of the Australian computer-assisted theragnostics (AusCAT) network for radiation oncology data extraction, reporting and distributed learning. Four radiation oncology departments (across seven hospitals) in New South Wales (NSW) participated in this demonstration study. Infrastructure was deployed at each centre and used to develop a model predicting for cardiovascular admission within a year of receiving curative radiotherapy for non-small cell lung cancer. A total of 10,417 lung cancer patients were identified with 802 being eligible for the model. Twenty features were chosen for analysis from the clinical record and linked registries. After selection, 8 features were included and a logistic regression model achieved an area under the receiver operating characteristic (AUROC) curve of 0.70 and C-index of 0.65 on out-of-sample data. CONCLUSION: The infrastructure developed was demonstrated to be usable in practice between clinical centres to harmonize routinely collected oncology data and develop models with federated learning. It provides a promising approach to enable further research studies in radiation oncology using real world clinical data.

Development of a vendor neutral MRI distortion quality assurance workflow.

With the utilization of magnetic resonance (MR) imaging in radiotherapy increasing, routine quality assurance (QA) of these systems is necessary. The assessment of geometric distortion in images used for radiotherapy treatment planning needs to be quantified and monitored over time. This work presents an adaptable methodology for performing routine QA for systematic MRI geometric distortion. A software tool and compatible protocol (designed to work with any CT and MR compatible phantom on any scanner) were developed to quantify geometric distortion via deformable image registration. The MR image is deformed to the CT, generating a deformation field, which is sampled, quantifying geometric distortion as a function of distance from scanner isocenter. Configurability of the QA tool was tested, and results compared to those provided from commercial solutions. Registration accuracy was investigated by repeating the deformable registration step on the initial deformed MR image to define regions with residual distortions. The geometric distortion of four clinical systems was quantified using the customisable QA method presented. Maximum measured distortions varied from 2.2 to 19.4 mm (image parameter and sampling volume dependent). The workflow was successfully customized for different phantom configurations and volunteer imaging studies. Comparison to a vendor supplied solution showed good agreement in regions where the two procedures were sampling the same imaging volume. On a large field of view phantom across various scanners, the QA tool accurately quantified geometric distortions within 17-22 cm from scanner isocenter. Beyond these regions, the geometric integrity of images in clinical applications should be considered with a higher degree of uncertainty due to increased gradient nonlinearity and B0 inhomogeneity. This tool has been successfully integrated into routine QA of the MRI scanner utilized for radiotherapy within our department. It enables any low susceptibility MR-CT compatible phantom to quantify the geometric distortion on any MRI scanner with a configurable, user friendly interface for ease of use and consistency in data collection and analysis.

Intrinsic detector sensitivity analysis as a tool to characterize ArcCHECK and EPID sensitivity to variations in delivery for lung SBRT VMAT plans.

PURPOSE: To investigate intrinsic sensitivity of an electronic portal imaging device (EPID) and the ArcCHECK detector and to use this in assessing their performance in detecting delivery variations for lung SBRT VMAT. The effect of detector spatial resolution and dose matrix interpolation on the gamma pass rate was also considered. MATERIALS AND METHODS: Fifteen patients' lung SBRT VMAT plans were used. Delivery variations (errors) were introduced by modifying collimator angles, multi-leaf collimator (MLC) field sizes and MLC field shifts by ±5, ±2, and ±1 degrees or mm (investigating 103 plans in total). EPID and ArcCHECK measured signals with introduced variations were compared to measured signals without variations (baseline), using OmniPro-I'mRT software and gamma criteria of 3%/3 mm, 2%/2 mm, 2%/1 mm, and 1%/1 mm, to test each system's basic performance. The measurement sampling resolution for each was also changed to 1 mm and results compared to those with the default detector system resolution. RESULTS: Intrinsic detector sensitivity analysis, that is, comparing measurement to baseline measurement, rather than measurement to plan, demonstrated the intrinsic constraints of each detector and indicated the limiting performance that users might expect. Changes in the gamma pass rates for ArcCHECK, for a given introduced error, were affected only by dose difference (DD %) criteria. However, the EPID showed only slight changes when changing DD%, but greater effects when changing distance-to-agreement criteria. This is pertinent for lung SBRT where the minimum dose to the target will drop dramatically with geometric errors. Detector resolution and dose matrix interpolation have an impact on the gamma results for these SBRT plans and can lead to false positives or negatives in error detection if not understood. CONCLUSION: The intrinsic sensitivity approach may help in the selection of more meaningful gamma criteria and the choice of optimal QA device for site-specific dose verification.

Determining the longitudinal accuracy and reproducibility of T1 and T2 in a 3T MRI scanner.

PURPOSE: To determine baseline accuracy and reproducibility of T1 and T2 relaxation times over 12 months on a dedicated radiotherapy MRI scanner. METHODS: An International Society of Magnetic Resonance in Medicine/National Institute of Standards and Technology (ISMRM/NIST) System Phantom was scanned monthly on a 3T MRI scanner for 1 year. T1 was measured using inversion recovery (T1 -IR) and variable flip angle (T1 -VFA) sequences and T2 was measured using a multi-echo spin echo (T2 -SE) sequence. For each vial in the phantom, accuracy errors (%bias) were determined by the relative differences in measured T1 and T2 times compared to reference values. Reproducibility was measured by the coefficient of variation (CV) of T1 and T2 measurements across monthly scans. Accuracy and reproducibility were mainly assessed on vials with relaxation times expected to be in physiological ranges at 3T. RESULTS: A strong linear correlation between measured and reference relaxation times was found for all sequences tested (R2  > 0.997). Baseline bias (and CV[%]) for T1 -IR, T1 -VFA and T2 -SE sequences were +2.0% (2.1), +6.5% (4.2), and +8.5% (1.9), respectively. CONCLUSIONS: The accuracy and reproducibility of T1 and T2 on the scanner were considered sufficient for the sequences tested. No longitudinal trends of variation were deduced, suggesting less frequent measurements are required following the establishment of baselines.

Evaluation of the ability of three commercially available dosimeters to detect systematic delivery errors in step-and-shoot IMRT plans.

BACKGROUND: There is limited data on error detectability for step-and-shoot intensity modulated radiotherapy (sIMRT) plans, despite significant work on dynamic methods. However, sIMRT treatments have an ongoing role in clinical practice. This study aimed to evaluate variations in the sensitivity of three patient-specific quality assurance (QA) devices to systematic delivery errors in sIMRT plans. MATERIALS AND METHODS: Four clinical sIMRT plans (prostate and head and neck) were edited to introduce errors in: Multi-Leaf Collimator (MLC) position (increasing field size, leaf pairs offset (1-3 mm) in opposite directions; and field shift, all leaves offset (1-3 mm) in one direction); collimator rotation (1-3 degrees) and gantry rotation (0.5-2 degrees). The total dose for each plan was measured using an ArcCHECK diode array. Each field, excluding those with gantry offsets, was also measured using an Electronic Portal Imager and a MatriXX Evolution 2D ionisation chamber array. 132 plans (858 fields) were delivered, producing 572 measured dose distributions. Measured doses were compared to calculated doses for the no-error plan using Gamma analysis with 3%/3 mm, 3%/2 mm, and 2%/2 mm criteria (1716 analyses). RESULTS: Generally, pass rates decreased with increasing errors and/or stricter gamma criteria. Pass rate variations with detector and plan type were also observed. For a 3%/3 mm gamma criteria, none of the devices could reliably detect 1 mm MLC position errors or 1 degree collimator rotation errors. CONCLUSIONS: This work has highlighted the need to adapt QA based on treatment plan type and the need for detector specific assessment criteria to detect clinically significant errors.

A prediction model for early death in non-small cell lung cancer patients following curative-intent chemoradiotherapy.

BACKGROUND: Early death after a treatment can be seen as a therapeutic failure. Accurate prediction of patients at risk for early mortality is crucial to avoid unnecessary harm and reducing costs. The goal of our work is two-fold: first, to evaluate the performance of a previously published model for early death in our cohorts. Second, to develop a prognostic model for early death prediction following radiotherapy. MATERIAL AND METHODS: Patients with NSCLC treated with chemoradiotherapy or radiotherapy alone were included in this study. Four different cohorts from different countries were available for this work (N = 1540). The previous model used age, gender, performance status, tumor stage, income deprivation, no previous treatment given (yes/no) and body mass index to make predictions. A random forest model was developed by learning on the Maastro cohort (N = 698). The new model used performance status, age, gender, T and N stage, total tumor volume (cc), total tumor dose (Gy) and chemotherapy timing (none, sequential, concurrent) to make predictions. Death within 4 months of receiving the first radiotherapy fraction was used as the outcome. RESULTS: Early death rates ranged from 6 to 11% within the four cohorts. The previous model performed with AUC values ranging from 0.54 to 0.64 on the validation cohorts. Our newly developed model had improved AUC values ranging from 0.62 to 0.71 on the validation cohorts. CONCLUSIONS: Using advanced machine learning methods and informative variables, prognostic models for early mortality can be developed. Development of accurate prognostic tools for early mortality is important to inform patients about treatment options and optimize care.

Nodal parameters of FDG PET/CT performed during radiotherapy for locally advanced mucosal primary head and neck squamous cell carcinoma can predict treatment outcomes: SUVmean and response rate are useful imaging biomarkers.

PURPOSE: To evaluate the prognostic utility of nodal metabolic parameters derived from FDG PET/CT performed before radiotherapy (prePET) and during the third week of radiotherapy (iPET) in patients with mucosal primary head and neck squamous cell carcinoma (MPHNSCC). METHODS: This analysis included 75 patients with newly diagnosed locally advanced node-positive MPHNSCC treated with radical radiotherapy and concurrent systemic therapy who underwent prePET and iPET: N1 11 patients, N2a 38, N2b 12, N2c 9, N3 5. The median follow-up was 28 months (9 - 70 months). The maximum and mean standardized uptake values (SUVmax and SUVmean), metabolic tumour volume (MTV) and total lesional glycolysis (TLG) of the index lymph node (node with the highest TLG) and the combined total lymph nodes, and their percentage reductions on iPET were determined, and the results were correlated with 3-year Kaplan-Meier locoregional, regional and distant metastatic failure-free survival (FFS), disease-free survival (DFS) and overall survival (OS). Optimal cut-off values were derived from receiver operating characteristic curves. Cox regression univariate and multivariate analyses with clinical covariates were performed. RESULTS: Based on assessment of residual nodal metabolic burden during treatment, the iPET index node SUVmean (optimal cut-off value 2.95 g/ml) and the total node SUVmean (optimal cut-off value 3.25) were the best independent predictors of outcome in the multivariate analysis: index node SUVmean for DFS and OS p = 0.033 and 0.003, respectively, and the total node SUVmean for locoregional FFS, DFS and OS p = 0.028, 0.025 and 0.014, respectively. Based on the assessment of response rates during treatment, a reduction of more than 50 % in the total node TLG was the best biomarker for locoregional and regional FFS, DFS and OS in the multivariate analysis (p = 0.001, 0.016, 0.001 and 0.004, respectively), and reduction in the total node MTV for locoregional FFS, DFS and OS (p = 0.026, 0.003 and 0.014, respectively). There were no significant correlations between oncological outcomes and prePET nodal parameters. CONCLUSION: We demonstrated that the index node and total node SUVmean on iPET and a reduction of more than 50 % in MTV and TLG are useful imaging biomarkers, and can potentially identify those patients with MPHNSCC who have a high risk of locoregional metastatic failure and death.

Multiparametric magnetic resonance imaging in mucosal primary head and neck cancer: a prospective imaging biomarker study.

BACKGROUND: Radical radiotherapy, with or without concomitant chemotherapy forms the mainstay of organ preservation approaches in mucosal primary head and neck cancer. Despite technical advances in cancer imaging and radiotherapy administration, a significant proportion of patients fail to achieve a complete response to treatment. For those patients who do achieve a complete response, acute and late toxicities remain a cause of morbidity. A critical need therefore exists for imaging biomarkers which are capable of informing patient selection for both treatment intensification and de-escalation strategies. METHODS/DESIGN: A prospective imaging study has been initiated, aiming to recruit patients undergoing radical radiotherapy (RT) or chemoradiotherapy (CRT) for mucosal primary head and neck cancer (MPHNC). Eligible patients are imaged using FDG-PET/CT before treatment, at the end of week 3 of treatment and 12 weeks after treatment completion according to local imaging policy. Functional MRI using diffusion weighted (DWI), blood oxygen level-dependent (BOLD) and dynamic contrast enhanced (DCE) sequences is carried out prior to, during and following treatment. Information regarding treatment outcomes will be collected, as well as physician-scored and patient-reported toxicity. DISCUSSION: The primary objective is to determine the correlation of functional MRI sequences with tumour response as determined by FDG-PET/CT and clinical findings at 12 weeks post-treatment and with local control at 12 months post-treatment. Secondary objectives include prospective correlation of functional MRI and PET imaging with disease-free survival and overall survival, defining the optimal time points for functional MRI assessment of treatment response, and determining the sensitivity and specificity of functional MRI sequences for assessment of potential residual disease following treatment. If the study is able to successfully characterise tumours based on their functional MRI scan characteristics, this would pave the way for further studies refining treatment approaches based on prognostic and predictive imaging data. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry (ANZCTR): ACTRN12616000534482 (26 April 2016).

Comparison of automatic image registration uncertainty for three IGRT systems using a male pelvis phantom.

A series of phantom images using the CIRS Virtual Human Male Pelvis was acquired across available dose ranges for three image-guided radiotherapy (IGRT) imaging systems: Elekta XVI CBCT, Varian TrueBeam CBCT, and TomoTherapy MV CT. Each image was registered to a fan-beam CT within the XVI software 100 times with random initial offsets. The residual registration error was analyzed to assess the role of imaging hardware and reconstruction in the uncertainty of the IGRT process. Residual translation errors were similar for all systems and < 0.5 mm. Over the clinical dose range for prostate IGRT images (10-25 mGy), all imaging systems provided acceptable matches in > 90% of registrations when incorporating residual rotational error using a dual quaternion derived distance metric. Outside normal dose settings, large uncertainties were observed at very low and very high dose levels. No trend between initial offset and residual registration error was observed. Patient images may incur higher uncertainties than this phantom study; however, these results encourage automatic matching for standard dose settings with review by treatment staff.

MRI geometric distortion: Impact on tangential whole-breast IMRT.

The purpose of this study was to determine the impact of magnetic resonance imaging (MRI) geometric distortions when using MRI for target delineation and planning for whole-breast, intensity-modulated radiotherapy (IMRT). Residual system distortions and combined systematic and patient-induced distortions are considered. This retrospective study investigated 18 patients who underwent whole-breast external beam radiotherapy, where both CT and MRIs were acquired for treatment planning. Distortion phantoms were imaged on two MRI systems, dedicated to radiotherapy planning (a wide, closed-bore 3T and an open-bore 1T). Patient scans were acquired on the 3T system. To simulate MRI-based planning, distortion maps representing residual system distortions were generated via deformable registration between phantom CT and MRIs. Patient CT images and structures were altered to match the residual system distortion measured by the phantoms on each scanner. The patient CTs were also registered to the corresponding patient MRI scans, to assess patient and residual system effects. Tangential IMRT plans were generated and optimized on each resulting CT dataset, then propagated to the original patient CT space. The resulting dose distributions were then evaluated with respect to the standard clinically acceptable DVH and visual assessment criteria. Maximum residual systematic distortion was measured to be 7.9 mm (95%<4.7mm) and 11.9 mm (95%<4.6mm) for the 3T and 1T scanners, respectively, which did not result in clinically unacceptable plans. Eight of the plans accounting for patient and systematic distortions were deemed clinically unacceptable when assessed on the original CT. For these plans, the mean difference in PTV V95 (volume receiving 95% prescription dose) was 0.13±2.51% and -0.73±1.93% for right- and left-sided patients, respectively. Residual system distortions alone had minimal impact on the dosimetry for the two scanners investigated. The combination of MRI systematic and patient-related distortions can result in unacceptable dosimetry for whole-breast IMRT, a potential issue when considering MRI-only radiotherapy treatment planning. PACS number(s): 87.61.-c, 87.57.cp, 87.57.nj, 87.55.D.

Dose calibration of EPIDs for segmented IMRT dosimetry.

The purpose of this study was to investigate the dose response of amorphous silicon (a-Si) electronic portal imaging devices (EPIDs) under different acquisi- tion settings for both open jaw defined fields and segmented intensity-modulated radiation therapy (IMRT) fields. Four different EPIDs were used. Two Siemens and one Elekta plus a standalone Perkin Elmer research EPID. Each was operated with different acquisition systems and settings. Dose response linearity was measured for open static jaw defined fields and 'simple' segmented IMRT fields for a range of equipment and system settings. Six 'simple' segmented IMRT fields were used. The segments of each IMRT field were fixed at 10 × 10 cm2 field size with equal MU per segment, each field having a total of 20 MU. Simultaneous measurements with an ionization chamber array (ICA) and EPID were performed to separate beam and detector response characteristics. Three different pixel calibration meth- ods were demonstrated and compared for an example 'clinical IMRT field'. The dose response with the Elekta EPID for 'simple' segmented IMRT fields versus static fields agreed to within 2.5% for monitor unit (MU) ≥ 2. The dose response for the Siemens systems was difficult to interpret due to the poor reproducibility for segmented delivery, at MU ≤ 5, which was not observed with the standalone research EPID nor ICA on the same machine. The dose response measured under different acquisition settings and different linac/EPID combinations matched closely (≤ 1%), except for the Siemens EPID. Clinical IMRT EPID dosimetry implemented with the different pixel-to-dose calibration methods indicated that calibration at 20 MU provides equivalent results to implementing a ghosting correction model. The nonlinear dose response was consistent across both clinical EPIDs and the standalone research EPID, with the exception of the poor reproducibility seen with Siemens EPID images of IMRT fields. The nonlinear dose response was relatively insensitive to acquisition settings and appears to be primarily due to gain ghosting effects. No additional ghosting correction factor is necessary when the pixel-to- dose calibration factor at small MU calibration method is used. 

Automatic segmentation of tumour and organs at risk in 3D MRI for cervical cancer radiation therapy with anatomical variations.

Cervical cancer is a common cancer in women globally, with treatment usually involving radiation therapy (RT). Accurate segmentation for the tumour site and organ-at-risks (OARs) could assist in the reduction of treatment side effects and improve treatment planning efficiency. Cervical cancer Magnetic Resonance Imaging (MRI) segmentation is challenging due to a limited amount of training data available and large inter- and intra- patient shape variation for OARs. The proposed Masked-Net consists of a masked encoder within the 3D U-Net to account for the large shape variation within the dataset, with additional dilated layers added to improve segmentation performance. A new loss function was introduced to consider the bounding box loss during training with the proposed Masked-Net. Transfer learning from a male pelvis MRI data with a similar field of view was included. The approaches were compared to the 3D U-Net which was widely used in MRI image segmentation. The data used consisted of 52 volumes obtained from 23 patients with stage IB to IVB cervical cancer across a maximum of 7 weeks of RT with manually contoured labels including the bladder, cervix, gross tumour volume, uterus and rectum. The model was trained and tested with a 5-fold cross validation. Outcomes were evaluated based on the Dice Similarity Coefficients (DSC), the Hausdorff Distance (HD) and the Mean Surface Distance (MSD). The proposed method accounted for the small dataset, large variations in OAR shape and tumour sizes with an average DSC, HD and MSD for all anatomical structures of 0.790, 30.19mm and 3.15mm respectively.

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.

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.

ACPSEM position paper: dosimetry for magnetic resonance imaging linear accelerators.

Consistency and clear guidelines on dosimetry are essential for accurate and precise dosimetry, to ensure the best patient outcomes and to allow direct dose comparison across different centres. Magnetic Resonance Imaging Linac (MRI-linac) systems have recently been introduced to Australasian clinics. This report provides recommendations on reference dosimetry measurements for MRI-linacs on behalf of the Australiasian College of Physical Scientists and Engineers in Medicine (ACPSEM) MRI-linac working group. There are two configurations considered for MRI-linacs, perpendicular and parallel, referring to the relative direction of the magnetic field and radiation beam, with different impacts on dose deposition in a medium. These recommendations focus on ion chambers which are most commonly used in the clinic for reference dosimetry. Water phantoms must be MR safe or conditional and practical limitations on phantom set-up must be considered. Solid phantoms are not advised for reference dosimetry. For reference dosimetry, IAEA TRS-398 recommendations cannot be followed completely due to physical differences between conventional linac and MRI-linac systems. Manufacturers' advice on reference conditions should be followed. Beam quality specification of TPR20,10 is recommended. The configuration of the central axis of the ion chamber relative to the magnetic field and radiation beam impacts the chamber response and must be considered carefully. Recommended corrections to delivered dose are [Formula: see text], a correction for beam quality and [Formula: see text], for the impact of the magnetic field on dosimeter response in the magnetic field. Literature based values for [Formula: see text] are given. It is important to note that this is a developing field and these recommendations should be used together with a review of current literature.

Magnetic resonance biomarker assessment software (MR-BIAS): an automated open-source tool for the ISMRM/NIST system phantom.

Objective.To provide an open-source software for repeatable and efficient quantification ofT1andT2relaxation times with the ISMRM/NIST system phantom. Quantitative magnetic resonance imaging (qMRI) biomarkers have the potential to improve disease detection, staging and monitoring of treatment response. Reference objects, such as the system phantom, play a major role in translating qMRI methods into the clinic. The currently available open-source software for ISMRM/NIST system phantom analysis, Phantom Viewer (PV), includes manual steps that are subject to variability.Approach.We developed the Magnetic Resonance BIomarker Assessment Software (MR-BIAS) to automatically extract system phantom relaxation times. The inter-observer variability (IOV) and time efficiency of MR-BIAS and PV was observed in six volunteers analysing three phantom datasets. The IOV was measured with the coefficient of variation (CV) of percent bias (%bias) inT1andT2with respect to NMR reference values. The accuracy of MR-BIAS was compared to a custom script from a published study of twelve phantom datasets. This included comparison of overall bias and %bias for variable inversion recovery (T1VIR), variable flip angle (T1VFA) and multiple spin-echo (T2MSE) relaxation models.Main results.MR-BIAS had a lower mean CV withT1VIR(0.03%) andT2MSE(0.05%) in comparison to PV withT1VIR(1.28%) andT2MSE(4.55%). The mean analysis duration was 9.7 times faster for MR-BIAS (0.8 min) than PV (7.6 min). There was no statistically significant difference in the overall bias, or the %bias for the majority of ROIs, as calculated by MR-BIAS or the custom script for all models.Significance.MR-BIAS has demonstrated repeatable and efficient analysis of the ISMRM/NIST system phantom, with comparable accuracy to previous studies. The software is freely available to the MRI community, providing a framework to automate required analysis tasks, with the flexibility to explore open questions and accelerate biomarker research.

Prognostic and predictive values of baseline and mid-treatment FDG-PET in oropharyngeal carcinoma treated with primary definitive (chemo)radiation and impact of HPV status: Review of current literature and emerging roles.

BACKGROUND AND PURPOSE: This study provides a review of the literature assessing whether semiquantitative PET parameters acquired at baseline and/or during definitive (chemo)radiotherapy ("prePET" and "iPET") can predict survival outcomes in patients with oropharyngeal squamous cell carcinoma (OPC), and the impact of human papilloma virus (HPV) status. MATERIAL AND METHODS: A literature search was carried out using PubMed and Embase between 2001 to 2021 in accordance with PRISMA. RESULTS: The analysis included 22 FDG-PET/CT studies [1-22], 19 pre-PET and 3 both pre-PET and iPET, The analysis involved 2646 patients, of which 1483 are HPV-positive (17 studies: 10 mixed and 7 HPV-positive only), 589 are HPV-negative, and 574 have unknown HPV status. Eighteen studies found significant correlations of survival outcomes with pre-PET parameters, most commonly primary or "Total" (combined primary and nodal) metabolic tumour volume and/or total lesional glycolysis. Two studies could not establish significant correlations and both employed SUVmax only. Two studies also could not establish significant correlations when taking into account of the HPV-positive population only. Because of the heterogeneity and lack of standardized methodology, no conclusions on optimal cut-off values can be drawn. Ten studies specifically evaluated HPV-positive patients: five showed positive correlation of pre-PET parameters and survival outcomes, but four of these studies did not include advanced T or N staging in multivariate analysis, and two studies only showed positive correlations after excluding high risk patients with smoking history or adverse CT features. Two studies found that prePET parameters predicted treatment outcomes only in HPV-negative but not HPV-positive patients. Two studies found that iPET parameters could predict outcomes in HPV-positive patients but not prePET parameters. CONCLUSION: The current literature supports high pre-treatment metabolic burden prior to definitive (chemo)radiotherapy can predict poor treatment outcomes for HPV-negative OPC patients. Evidence is conflicting and currently does not support correlation in HPV-positive patients.

Clinical validation of MR imaging time reduction for substitute/synthetic CT generation for prostate MRI-only treatment planning.

Radiotherapy treatment planning based only on magnetic resonance imaging (MRI) has become clinically achievable. Though computed tomography (CT) is the gold standard for radiotherapy imaging, directly providing the electron density values needed for planning calculations, MRI has superior soft tissue visualisation to guide treatment planning decisions and optimisation. MRI-only planning removes the need for the CT scan, but requires generation of a substitute/synthetic/pseudo CT (sCT) for electron density information. Shortening the MRI imaging time would improve patient comfort and reduce the likelihood of motion artefacts. A volunteer study was previously carried out to investigate and optimise faster MRI sequences for a hybrid atlas-voxel conversion to sCT for prostate treatment planning. The aim of this follow-on study was to clinically validate the performance of the new optimised sequence for sCT generation in a treated MRI-only prostate patient cohort. 10 patients undergoing MRI-only treatment were scanned on a Siemens Skyra 3T MRI as part of the MRI-only sub-study of the NINJA clinical trial (ACTRN12618001806257). Two sequences were used, the standard 3D T2-weighted SPACE sequence used for sCT conversion which has been previously validated against CT, and a modified fast SPACE sequence, selected based on the volunteer study. Both were used to generate sCT scans. These were then compared to evaluate the fast sequence conversion for anatomical and dosimetric accuracy against the clinically approved treatment plans. The average Mean Absolute Error (MAE) for the body was 14.98 ± 2.35 HU, and for bone was 40.77 ± 5.51 HU. The external volume contour comparison produced a Dice Similarity Coefficient (DSC) of at least 0.976, and an average of 0.985 ± 0.004, and the bony anatomy contour comparison a DSC of at least 0.907, and an average of 0.950 ± 0.018. The fast SPACE sCT agreed with the gold standard sCT within an isocentre dose of -0.28% ± 0.16% and an average gamma pass rate of 99.66% ± 0.41% for a 1%/1 mm gamma tolerance. In this clinical validation study, the fast sequence, which reduced the required imaging time by approximately a factor of 4, produced an sCT with similar clinical dosimetric results compared to the standard sCT, demonstrating its potential for clinical use for treatment planning.

Outcome prediction models incorporating clinical variables for Head and Neck Squamous cell Carcinoma: A systematic review of methodological conduct and risk of bias.

Multiple outcome prediction models have been developed for Head and Neck Squamous Cell Carcinoma (HNSCC). This systematic review aimed to identify HNSCC outcome prediction model studies, assess their methodological quality and identify those with potential utility for clinical practice. Inclusion criteria were mucosal HNSCC prognostic prediction model studies (development or validation) incorporating clinically available variables accessible at time of treatment decision making and predicting tumour-related outcomes. Eligible publications were identified from PubMed and Embase. Methodological quality and risk of bias were assessed using the checklist for critical appraisal and data extraction for systematic reviews of prediction modelling studies (CHARMS) and prediction model risk of bias assessment tool (PROBAST). Eligible publications were categorised by study type for reporting. 64 eligible publications were identified; 55 reported model development, 37 external validations, with 28 reporting both. CHARMS checklist items relating to participants, predictors, outcomes, handling of missing data, and some model development and evaluation procedures were generally well-reported. Less well-reported were measures accounting for model overfitting and model performance measures, especially model calibration. Full model information was poorly reported (3/55 model developments), specifically model intercept, baseline survival or full model code. Most publications (54/55 model developments, 28/37 external validations) were found to have high risk of bias, predominantly due to methodological issues in the PROBAST analysis domain. The identified methodological issues may affect prediction model accuracy in heterogeneous populations. Independent external validation studies in the local population and demonstration of clinical impact are essential for the clinical implementation of outcome prediction models.