A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy.

Purpose/objectives: Auto-segmentation with artificial intelligence (AI) offers an opportunity to reduce inter- and intra-observer variability in contouring, to improve the quality of contours, as well as to reduce the time taken to conduct this manual task. In this work we benchmark the AI auto-segmentation contours produced by five commercial vendors against a common dataset. Methods and materials: The organ at risk (OAR) contours generated by five commercial AI auto-segmentation solutions (Mirada (Mir), MVision (MV), Radformation (Rad), RayStation (Ray) and TheraPanacea (Ther)) were compared to manually-drawn expert contours from 20 breast, 20 head and neck, 20 lung and 20 prostate patients. Comparisons were made using geometric similarity metrics including volumetric and surface Dice similarity coefficient (vDSC and sDSC), Hausdorff distance (HD) and Added Path Length (APL). To assess the time saved, the time taken to manually draw the expert contours, as well as the time to correct the AI contours, were recorded. Results: There are differences in the number of CT contours offered by each AI auto-segmentation solution at the time of the study (Mir 99; MV 143; Rad 83; Ray 67; Ther 86), with all offering contours of some lymph node levels as well as OARs. Averaged across all structures, the median vDSCs were good for all systems and compared favorably with existing literature: Mir 0.82; MV 0.88; Rad 0.86; Ray 0.87; Ther 0.88. All systems offer substantial time savings, ranging between: breast 14-20 mins; head and neck 74-93 mins; lung 20-26 mins; prostate 35-42 mins. The time saved, averaged across all structures, was similar for all systems: Mir 39.8 mins; MV 43.6 mins; Rad 36.6 min; Ray 43.2 mins; Ther 45.2 mins. Conclusions: All five commercial AI auto-segmentation solutions evaluated in this work offer high quality contours in significantly reduced time compared to manual contouring, and could be used to render the radiotherapy workflow more efficient and standardized.

IPEM topical report: guidance for the clinical implementation of online treatment monitoring solutions for IMRT/VMAT.

This report provides guidance for the implementation of online treatment monitoring (OTM) solutions in radiotherapy (RT), with a focus on modulated treatments. Support is provided covering the implementation process, from identification of an OTM solution to local implementation strategy. Guidance has been developed by a RT special interest group (RTSIG) working party (WP) on behalf of the Institute of Physics and Engineering in Medicine (IPEM). Recommendations within the report are derived from the experience of the WP members (in consultation with manufacturers, vendors and user groups), existing guidance or legislation and a UK survey conducted in 2020 (Stevenset al2021). OTM is an inclusive term representing any system capable of providing a direct or inferred measurement of the delivered dose to a RT patient. Information on each type of OTM is provided but, commensurate with UK demand, guidance is largely influenced byin vivodosimetry methods utilising the electronic portal imager device (EPID). Sections are included on the choice of OTM solutions, acceptance and commissioning methods with recommendations on routine quality control, analytical methods and tolerance setting, clinical introduction and staffing/resource requirements. The guidance aims to give a practical solution to sensitivity and specificity testing. Functionality is provided for the user to introduce known errors into treatment plans for local testing. Receiver operating characteristic analysis is discussed as a tool to performance assess OTM systems. OTM solutions can help verify the correct delivery of radiotherapy treatment. Furthermore, modern systems are increasingly capable of providing clinical decision-making information which can impact the course of a patient's treatment. However, technical limitations persist. It is not within the scope of this guidance to critique each available solution, but the user is encouraged to carefully consider workflow and engage with manufacturers in resolving compatibility issues.

Deep learning based automated delineation of the intraprostatic gross tumour volume in PSMA-PET for patients with primary prostate cancer.

PURPOSE: With the increased use of focal radiation dose escalation for primary prostate cancer (PCa), accurate delineation of gross tumor volume (GTV) in prostate-specific membrane antigen PET (PSMA-PET) becomes crucial. Manual approaches are time-consuming and observer dependent. The purpose of this study was to create a deep learning model for the accurate delineation of the intraprostatic GTV in PSMA-PET. METHODS: A 3D U-Net was trained on 128 different 18F-PSMA-1007 PET images from three different institutions. Testing was done on 52 patients including one independent internal cohort (Freiburg: n = 19) and three independent external cohorts (Dresden: n = 14 18F-PSMA-1007, Boston: Massachusetts General Hospital (MGH): n = 9 18F-DCFPyL-PSMA and Dana-Farber Cancer Institute (DFCI): n = 10 68Ga-PSMA-11). Expert contours were generated in consensus using a validated technique. CNN predictions were compared to expert contours using Dice similarity coefficient (DSC). Co-registered whole-mount histology was used for the internal testing cohort to assess sensitivity/specificity. RESULTS: Median DSCs were Freiburg: 0.82 (IQR: 0.73-0.88), Dresden: 0.71 (IQR: 0.53-0.75), MGH: 0.80 (IQR: 0.64-0.83) and DFCI: 0.80 (IQR: 0.67-0.84), respectively. Median sensitivity for CNN and expert contours were 0.88 (IQR: 0.68-0.97) and 0.85 (IQR: 0.75-0.88) (p = 0.40), respectively. GTV volumes did not differ significantly (p > 0.1 for all comparisons). Median specificity of 0.83 (IQR: 0.57-0.97) and 0.88 (IQR: 0.69-0.98) were observed for CNN and expert contours (p = 0.014), respectively. CNN prediction took 3.81 seconds on average per patient. CONCLUSION: The CNN was trained and tested on internal and external datasets as well as histopathology reference, achieving a fast GTV segmentation for three PSMA-PET tracers with high diagnostic accuracy comparable to manual experts.

IPEM topical report: results of a 2020 UK survey on the use of online treatment monitoring solutions for IMRT/VMAT.

Numerous commercial technologies for online treatment monitoring (OTM) in radiotherapy (RT) are currently available including electronic portal imaging device (EPID)in vivodosimetry (IVD), transmission detectors and log files analysis. Despite this, in the UK there exists limited guidance on how to implement and commission a system for clinical use or information about the resources required to set up and maintain a service. A Radiotherapy Special Interest Group working party, established by Institute of Physics and Engineering in Medicine was formed with a view to reassess the current practice for OTM in the UK and an aim to develop consensus guidelines for the implementation of a system. A survey distributed to Heads of Medical Physics at 71 UK RT departments investigated: availability of OTM in the UK; estimates of workload; clinical implementation; methods of analysis; quality assurance; and opinions on future directions. The survey achieved a 76% response rate and demonstrated that OTM is widely supported in the UK, with 87% of respondents indicating all patients should undergo OTM. EPID IVD (EIVD) was the most popular form of OTM. An active EIVD service was reported by 37% of respondents, with 84% believing it was the optimal solution. This demonstrates a steady increase in adoption since 2012. Other forms of OTM were in use but they had only been adopted by a minority of centres. Financial barriers and the increase of staff workload continue to hinder wider implementation in other centres. Device automation and integration is a key factor for successful future adoption and requires support between treatment machine and OTM manufacturers. The survey has provided an updated analysis on the use of OTM methods across the UK. Future guidance is recommended on commissioning, adoption of local tolerances and root-cause analysis strategies to assist departments intending to implement OTM.

Assessment of a commercial EPID dosimetry system to detect radiotherapy treatment errors.

One method for detecting radiotherapy treatment errors is to capture the exit dose using an electronic portal imaging device. In comparison with a baseline integrated image, subsequent fractions can be compared and differences in images suggest a difference in the radiation treatment delivered. The aim of this work was to assess the sensitivity of a commercial software PerFRACTION in detecting such differences, arising from three possible sources: (i) changes in the radiation beam or EPID position; (ii) changes in the patient position; and (iii) changes in the patient anatomy. By systematically introducing errors, PerFRACTION was shown to be very sensitive to changes in the radiation beam. Variation in the beam output could be detected within 0.3%, field size within 0.4 mm, collimator rotation within 0.3° and MLC positioning could be verified to within 0.1 mm. EPID misalignment could be detected within 0.3 mm. PerFRACTION was able to detect the mispositioning of an anthropomorphic phantom by 3 mm with static beams, however there was a relative dependency between the patient geometry and the direction of the shift. VMAT beams were less sensitive to patient misalignments, with a shift of 10 mm only detectable once a strict criterion of 1% dose difference was applied. In another simulated scenario PerFRACTION was also able to detect a weight loss equivalent to a 5 mm change in patient separation in VMAT plans and 10 mm in conformal plans. This work showed that the PerFRACTION software could be relied upon to detect potential radiotherapy treatment errors, arising from a variety of sources.

Computed tomography guided interstitial percutaneous high-dose-rate brachytherapy in the management of lung malignancies. A review of the literature.

A growing number of patients with lung cancer are not amenable to surgery due to their age or comorbidities. For this reason, local ablative techniques have gained increasing interest recently in the management of inoperable lung tumors. High-dose-rate percutaneous interstitial brachytherapy, performed under CT-guidance, is a newer form of brachytherapy and is a highly conformal radiotherapy technique. The aim of this study was to describe this method and review the existing literature. Eight articles comprising 234 patients reported toxicity and clinical outcome. The follow-up ranged from 6 to 28 months. Diverse fractionation schemes were reported, with 20 Gy in a single fraction being the most frequently utilized. Toxicity was limited; major pneumothoraces occurred after only 8% of the interventions. Local control rates at one year ranged between 37% and 91%. In conclusion, high-dose-rate percutaneous interstitial brachytherapy is a safe, fast, and efficient treatment option for inoperable lung tumors.

Breast Cancer Brain Metastasis: The Potential Role of MRI Beyond Current Clinical Applications.

PURPOSE: Breast cancer brain metastasis (BCBM) represents a major clinical challenge. Can MRI help in advancements in the management of BCBM? This review discusses MRI developments and the corresponding potential advancements in BCBM management. METHODS: An exhaustive literature search was undertaken to identify studies which look into the potential of MRI in BCBM management. Seven hundred and eighty-four studies published from September 1984 to May 2020 were identified. Three topics are covered where MRI is not clinically established yet: 1) the prognosis of BCBM; 2) the screening of BC patients for BCBM development, and 3) the assessment of imaging features correlated to BC subtype. RESULTS: Thirty-six studies were considered eligible for the purposes of this review. On-going progress is made with the identification of different BCBM characteristics and MRI metrics that might be related to prognosis. Progress has been made with the identification of different BCBM characteristics, including BCBM location, degree of edema, white matter disruption, tumor edge sharpness, and temporal muscle thickness. A more accurate prediction of prognosis could lead to more suitable patient management and treatment. The use of MRI in BCBM screening of the high-risk breast cancer population remains a controversial subject. To date, there are no results from clinical trials; however, there is a rising number of relatively small studies that show concern on this subject and support BCBM screening. It is important to oncologists to be able to assess the tumor subtype non-invasively. MRI features, which have shown some correlation with subtype, include the number of tumors, location, and their distribution in the brain. Advanced tools and metrics have been produced to carry out radiological characteristics analysis on MRI images. Assessing MRI features in more detail could provide a more personalized management of patients. CONCLUSION: Developments in the use of MRI have the potential to improve BCBM management.

Impact of varying planning parameters on proton pencil beam scanning dose distributions in four commercial treatment planning systems.

PURPOSE: In pencil beam scanning proton therapy, target coverage is achieved by scanning the pencil beam laterally in the x- and y-directions and delivering spots of dose to positions at a given radiological depth (layer). Dose is delivered to the spots on different layers by pencil beams of different energy until the entire volume has been irradiated. The aim of this study is to investigate the implementation of proton planning parameters (spot spacing, layer spacing and margins) in four commercial proton treatment planning systems (TPSs): Eclipse, Pinnacle3 , RayStation and XiO. MATERIALS AND METHODS: Using identical beam data in each TPS, plans were created on uniform material synthetic phantoms with cubic targets. The following parameters were systematically varied in each TPS to observe their different implementations: spot spacing, layer spacing and margin. Additionally, plans were created in Eclipse to investigate the impact of these parameters on plan delivery and optimal values are suggested. RESULTS: It was found that all systems except Eclipse use a variable layer spacing per beam, based on the Bragg peak width of each energy layer. It is recommended that if this cannot be used, then a constant value of 5 mm will ensure good dose homogeneity. Only RayStation varies the spot spacing according to the variable spot size with depth. If a constant spot spacing is to be used, a value of 5 mm is recommended as a good compromise between dose homogeneity, plan robustness and planning time. It was found that both Pinnacle3 and RayStation position spots outside of the defined volume (target plus margin). CONCLUSIONS: All four systems are capable of delivering uniform dose distributions to simple targets, but their implementation of the various planning parameters is different. In this paper comparisons are made between the four systems and recommendations are made as to the values that will provide the best compromise in dose homogeneity and planning time.

Developing a phenomenological model of the proton trajectory within a heterogeneous medium required for proton imaging.

To develop an accurate phenomenological model of the cubic spline path estimate of the proton path, accounting for the initial proton energy and water equivalent thickness (WET) traversed. Monte Carlo (MC) simulations were used to calculate the path of protons crossing various WET (10-30 cm) of different material (LN300, water and CB2-50% CaCO3) for a range of initial energies (180-330 MeV). For each MC trajectory, cubic spline trajectories (CST) were constructed based on the entrance and exit information of the protons and compared with the MC using the root mean square (RMS) metric. The CST path is dependent on the direction vector magnitudes (|P0,1|). First, |P0,1| is set to the proton path length (with factor Λ(Norm)(0,1) = 1.0). Then, two optimal factor Λ(0,1) are introduced in |P0,1|. The factors are varied to minimize the RMS difference with MC paths for every configuration. A set of Λ(opt)(0,1) factors, function of WET/water equivalent path length (WEPL), that minimizes the RMS are presented. MTF analysis is then performed on proton radiographs of a line-pair phantom reconstructed using the CST trajectories. Λ(opt)(0,1) was fitted to the WET/WEPL ratio using a quadratic function (Y = A + BX(2) where A = 1.01,0.99, B = 0.43,- 0.46 respectively for Λ(opt)(0), Λ(opt)(1)). The RMS deviation calculated along the path, between the CST and the MC, increases with the WET. The increase is larger when using Λ(Norm)(0,1) than Λ(opt)(0,1) (difference of 5.0% with WET/WEPL = 0.66). For 230/330 MeV protons, the MTF10% was found to increase by 40/16% respectively for a thin phantom (15 cm) when using the Λ(opt)(0,1) model compared to the Λ(Norm)(0,1) model. Calculation times for Λ(opt)(0,1) are scaled down compared to MLP and RMS deviation are similar within standard deviation.B ased on the results of this study, using CST with the Λ(opt)(0,1) factors reduces the RMS deviation and increases the spatial resolution when reconstructing proton trajectories.

A comparison of the dose distributions from three proton treatment planning systems in the planning of meningioma patients with single-field uniform dose pencil beam scanning.

With the number of new proton centers increasing rapidly, there is a need for an assessment of the available proton treatment planning systems (TPSs). This study compares the dose distributions of complex meningioma plans produced by three proton TPSs: Eclipse, Pinnacle3, and XiO. All three systems were commissioned with the same beam data and, as best as possible, matched configuration settings. Proton treatment plans for ten patients were produced on each system with a pencil beam scanning, single-field uniform dose approach, using a fixed horizontal beamline. All 30 plans were subjected to identical dose constraints, both for the target coverage and organ at risk (OAR) sparing, with a consistent order of priority. Beam geometry, lateral field margins, and lateral spot resolutions were made consistent across all systems. Few statistically significant differences were found between the target coverage and OAR sparing of each system, with all optimizers managing to produce plans within clinical tolerances (D2 < 107% of prescribed dose, D5 < 105%, D95 > 95%, D99 > 90%, and OAR maximum doses) despite strict constraints and overlapping structures.

Review of backscatter measurement in kilovoltage radiotherapy using novel detectors and reduction from lack of underlying scattering material.

Lack of underlying material can lead to dose reduction in kilovoltage radiotherapy treatments because of backscatter reduction. Conversely, the use of lead shielding can lead to large dose enhancement close to the lead interface. GAFCHROMIC film has been shown to be of use in verification of local backscatter factors compared to reference data in codes of practice, but careful handling and multiple readings are required to reduce systematic uncertainties to between 3% and 4%. Monte Carlo modeling of the specific treatment unit should be performed in cases which are found to differ from reference values before alternative values are adopted clinically, but these cases are expected to be few. GAFCHROMIC film may also be used to estimate backscatter reduction more readily than customized ionization chambers, for a range of beam qualities, applicator sizes and depth, with and without lead shielding. Differences were found between different studies, and it is not clear to what extent these are due to variation in equipment and/or technique. However, a layer of wax around lead shielding of 1 mm thickness should be sufficient to eliminate lead enhancement effects for all kilovoltage energies from 40 kV to 300 kV.

Evaluation of quality control strategies in Scutellaria herbal medicines.

The statutory regulation of herbal medicines is under review within the United Kingdom (UK) and by 2011 all herbal medicines will require either a Product Licence or a Traditional Herbal Registration. The species Scutellaria baicalensis has been shown to possess anti-inflammatory, anti-viral and anti-tumor properties and is one of the most widely used Chinese herbal extracts in Eastern and Western medicines. The bioactivity of this herbal medicine is due to the radical scavenging activities of the flavone components of which there are more than 60. This research has characterised 5 key flavones in 18 extracts of Scutellaria using a combination of HPLC with DAD and MS detection. Employing an internal standard approach, the validated HPLC method afforded good sensitivity and excellent assay precision. Assays for the ferric reducing antioxidant power (FRAP) and total phenol determinations enabled determination of the antioxidant coefficient (PAC) of each Scutellaria extract. The potential usefulness of employing multivariate statistical analysis using a combination of the key parameters collected namely, FRAP activity, total phenol content, levels of 5 flavone biomarkers and the PAC as a means of quality evaluation of the Scutellaria herbal extracts was investigated. The PAC value was predicted by soft independent modelling of class analogy (SIMCA) as being the most discriminatory parameter and applying this ranking the herbal extracts were grouped into 3 clusters. The second most influential parameter in determining the clustering of the samples was the level of baicalin in each extract. It is proposed that the PAC value alone or in combination with a chromatographic fingerprint of key biomarkers [e.g. baicalin or (baicalin+baicalein)] may be useful indicators to adopt for the quality control of S. baicalensis.