Development and dosimetric assessment of an automatic dental artifact classification tool to guide artifact management techniques in a fully automated treatment planning workflow.

PURPOSE: We conducted our study to develop a tool capable of automatically detecting dental artifacts in a CT scan on a slice-by-slice basis and to assess the dosimetric impact of implementing the tool into the Radiation Planning Assistant (RPA), a web-based platform designed to fully automate the radiation therapy treatment planning process. METHODS: We developed an automatic dental artifact identification tool and assessed the dosimetric impact of its use in the RPA. Three users manually annotated 83,676 head-and-neck (HN) CT slices (549 patients). Majority-voting was applied to the individual annotations to determine the presence or absence of dental artifacts. The patients were divided into train, cross-validation, and test data sets (ratio: 3:1:1, respectively). A random subset of images without dental artifacts was used to balance classes (1:1) in the training data set. The Inception-V3 deep learning model was trained with the binary cross-entropy loss function. With use of this model, we automatically identified artifacts on 15 RPA HN plans on a slice-by-slice basis and investigated three dental artifact management methods applied before and after volumetric modulated arc therapy (VMAT) plan optimization. The resulting dose distributions and target coverage were quantified. RESULTS: Per-slice accuracy, sensitivity, and specificity were 99 %, 91 %, and 99 %, respectively. The model identified all patients with artifacts. Small dosimetric differences in total plan dose were observed between the various density-override methods (±1 Gy). For the pre- and post-optimized plans, 90 % and 99 %, respectively, of dose comparisons resulted in normal structure dose differences of ±1 Gy. Differences in the volume of structures receiving 95 % of the prescribed dose (V95[%]) were ≤0.25 % for 100 % of plans. CONCLUSION: The dosimetric impact of applying dental artifact management before and after artifact plan optimization was minor. Our results suggest that not accounting for dental artifacts in the current RPA workflow (where only post-optimization dental artifact management is possible) may result in minor dosimetric differences. If RPA users choose to override CT densities as a solution to managing dental artifacts, our results suggest segmenting the volume of the artifact and overriding its density to water is a safe option.

The Emergence of Artificial Intelligence within Radiation Oncology Treatment Planning.

BACKGROUND: The future of artificial intelligence (AI) heralds unprecedented change for the field of radiation oncology. Commercial vendors and academic institutions have created AI tools for radiation oncology, but such tools have not yet been widely adopted into clinical practice. In addition, numerous discussions have prompted careful thoughts about AI's impact upon the future landscape of radiation oncology: How can we preserve innovation, creativity, and patient safety? When will AI-based tools be widely adopted into the clinic? Will the need for clinical staff be reduced? How will these devices and tools be developed and regulated? SUMMARY: In this work, we examine how deep learning, a rapidly emerging subset of AI, fits into the broader historical context of advancements made in radiation oncology and medical physics. In addition, we examine a representative set of deep learning-based tools that are being made available for use in external beam radiotherapy treatment planning and how these deep learning-based tools and other AI-based tools will impact members of the radiation treatment planning team. Key Messages: Compared to past transformative innovations explored in this article, such as the Monte Carlo method or intensity-modulated radiotherapy, the development and adoption of deep learning-based tools is occurring at faster rates and promises to transform practices of the radiation treatment planning team. However, accessibility to these tools will be determined by each clinic's access to the internet, web-based solutions, or high-performance computing hardware. As seen by the trends exhibited by many technologies, high dependence on new technology can result in harm should the product fail in an unexpected manner, be misused by the operator, or if the mitigation to an expected failure is not adequate. Thus, the need for developers and researchers to rigorously validate deep learning-based tools, for users to understand how to operate tools appropriately, and for professional bodies to develop guidelines for their use and maintenance is essential. Given that members of the radiation treatment planning team perform many tasks that are automatable, the use of deep learning-based tools, in combination with other automated treatment planning tools, may refocus tasks performed by the treatment planning team and may potentially reduce resource-related burdens for clinics with limited resources.

Cost-effective immobilization for whole brain radiation therapy.

To investigate the inter- and intra-fraction motion associated with the use of a low-cost tape immobilization technique as an alternative to thermoplastic immobilization masks for whole-brain treatments. The results of this study may be of interest to clinical staff with severely limited resources (e.g., in low-income countries) and also when treating patients who cannot tolerate standard immobilization masks. Setup reproducibility of eight healthy volunteers was assessed for two different immobilization techniques. (a) One strip of tape was placed across the volunteer's forehead and attached to the sides of the treatment table. (b) A second strip was added to the first, under the chin, and secured to the table above the volunteer's head. After initial positioning, anterior and lateral photographs were acquired. Volunteers were positioned five times with each technique to allow calculation of inter-fraction reproducibility measurements. To estimate intra-fraction reproducibility, 5-minute anterior and lateral videos were taken for each technique per volunteer. An in-house software was used to analyze the photos and videos to assess setup reproducibility. The maximum intra-fraction displacement for all volunteers was 2.8 mm. Intra-fraction motion increased with time on table. The maximum inter-fraction range of positions for all volunteers was 5.4 mm. The magnitude of inter-fraction and intra-fraction motion found using the "1-strip" and "2-strip" tape immobilization techniques was comparable to motion restrictions provided by a thermoplastic mask for whole-brain radiotherapy. The results suggest that tape-based immobilization techniques represent an economical and useful alternative to the thermoplastic mask.

The Incremental Value of Subjective and Quantitative Assessment of 18F-FDG PET for the Prediction of Pathologic Complete Response to Preoperative Chemoradiotherapy in Esophageal Cancer.

UNLABELLED: A reliable prediction of a pathologic complete response (pathCR) to chemoradiotherapy before surgery for esophageal cancer would enable investigators to study the feasibility and outcome of an organ-preserving strategy after chemoradiotherapy. So far no clinical parameters or diagnostic studies are able to accurately predict which patients will achieve a pathCR. The aim of this study was to determine whether subjective and quantitative assessment of baseline and postchemoradiation (18)F-FDG PET can improve the accuracy of predicting pathCR to preoperative chemoradiotherapy in esophageal cancer beyond clinical predictors. METHODS: This retrospective study was approved by the institutional review board, and the need for written informed consent was waived. Clinical parameters along with subjective and quantitative parameters from baseline and postchemoradiation (18)F-FDG PET were derived from 217 esophageal adenocarcinoma patients who underwent chemoradiotherapy followed by surgery. The associations between these parameters and pathCR were studied in univariable and multivariable logistic regression analysis. Four prediction models were constructed and internally validated using bootstrapping to study the incremental predictive values of subjective assessment of (18)F-FDG PET, conventional quantitative metabolic features, and comprehensive (18)F-FDG PET texture/geometry features, respectively. The clinical benefit of (18)F-FDG PET was determined using decision-curve analysis. RESULTS: A pathCR was found in 59 (27%) patients. A clinical prediction model (corrected c-index, 0.67) was improved by adding (18)F-FDG PET-based subjective assessment of response (corrected c-index, 0.72). This latter model was slightly improved by the addition of 1 conventional quantitative metabolic feature only (i.e., postchemoradiation total lesion glycolysis; corrected c-index, 0.73), and even more by subsequently adding 4 comprehensive (18)F-FDG PET texture/geometry features (corrected c-index, 0.77). However, at a decision threshold of 0.9 or higher, representing a clinically relevant predictive value for pathCR at which one may be willing to omit surgery, there was no clear incremental value. CONCLUSION: Subjective and quantitative assessment of (18)F-FDG PET provides statistical incremental value for predicting pathCR after preoperative chemoradiotherapy in esophageal cancer. However, the discriminatory improvement beyond clinical predictors does not translate into a clinically relevant benefit that could change decision making.

Technical Note: A Monte Carlo study of magnetic-field-induced radiation dose effects in mice.

PURPOSE: Magnetic fields are known to alter radiation dose deposition. Before patients receive treatment using an MRI-linear accelerator (MRI-Linac), preclinical studies are needed to understand the biological consequences of magnetic-field-induced dose effects. In the present study, the authors sought to identify a beam energy and magnetic field strength combination suitable for preclinical murine experiments. METHODS: Magnetic field dose effects were simulated in a mouse lung phantom using various beam energies (225 kVp, 350 kVp, 662 keV [Cs-137], 2 MV, and 1.25 MeV [Co-60]) and magnetic field strengths (0.75, 1.5, and 3 T). The resulting dose distributions were compared with those in a simulated human lung phantom irradiated with a 6 or 8 MV beam and orthogonal 1.5 T magnetic field. RESULTS: In the human lung phantom, the authors observed a dose increase of 45% and 54% at the soft-tissue-to-lung interface and a dose decrease of 41% and 48% at the lung-to-soft-tissue interface for the 6 and 8 MV beams, respectively. In the mouse simulations, the magnetic fields had no measurable effect on the 225 or 350 kVp dose distribution. The dose increases with the Cs-137 beam for the 0.75, 1.5, and 3 T magnetic fields were 9%, 29%, and 42%, respectively. The dose decreases were 9%, 21%, and 37%. For the 2 MV beam, the dose increases were 16%, 33%, and 31% and the dose decreases were 9%, 19%, and 30%. For the Co-60 beam, the dose increases were 19%, 54%, and 44%, and the dose decreases were 19%, 42%, and 40%. CONCLUSIONS: The magnetic field dose effects in the mouse phantom using a Cs-137, 3 T combination or a Co-60, 1.5 or 3 T combination most closely resemble those in simulated human treatments with a 6 MV, 1.5 T MRI-Linac. The effects with a Co-60, 1.5 T combination most closely resemble those in simulated human treatments with an 8 MV, 1.5 T MRI-Linac.

Quality assurance assessment of diagnostic and radiation therapy-simulation CT image registration for head and neck radiation therapy: anatomic region of interest-based comparison of rigid and deformable algorithms.

PURPOSE: To develop a quality assurance (QA) workflow by using a robust, curated, manually segmented anatomic region-of-interest (ROI) library as a benchmark for quantitative assessment of different image registration techniques used for head and neck radiation therapy-simulation computed tomography (CT) with diagnostic CT coregistration. MATERIALS AND METHODS: Radiation therapy-simulation CT images and diagnostic CT images in 20 patients with head and neck squamous cell carcinoma treated with curative-intent intensity-modulated radiation therapy between August 2011 and May 2012 were retrospectively retrieved with institutional review board approval. Sixty-eight reference anatomic ROIs with gross tumor and nodal targets were then manually contoured on images from each examination. Diagnostic CT images were registered with simulation CT images rigidly and by using four deformable image registration (DIR) algorithms: atlas based, B-spline, demons, and optical flow. The resultant deformed ROIs were compared with manually contoured reference ROIs by using similarity coefficient metrics (ie, Dice similarity coefficient) and surface distance metrics (ie, 95% maximum Hausdorff distance). The nonparametric Steel test with control was used to compare different DIR algorithms with rigid image registration (RIR) by using the post hoc Wilcoxon signed-rank test for stratified metric comparison. RESULTS: A total of 2720 anatomic and 50 tumor and nodal ROIs were delineated. All DIR algorithms showed improved performance over RIR for anatomic and target ROI conformance, as shown for most comparison metrics (Steel test, P < .008 after Bonferroni correction). The performance of different algorithms varied substantially with stratification by specific anatomic structures or category and simulation CT section thickness. CONCLUSION: Development of a formal ROI-based QA workflow for registration assessment demonstrated improved performance with DIR techniques over RIR. After QA, DIR implementation should be the standard for head and neck diagnostic CT and simulation CT allineation, especially for target delineation.

Statistical assessment of proton treatment plans under setup and range uncertainties.

PURPOSE: To evaluate a method for quantifying the effect of setup errors and range uncertainties on dose distribution and dose-volume histogram using statistical parameters; and to assess existing planning practice in selected treatment sites under setup and range uncertainties. METHODS AND MATERIALS: Twenty passively scattered proton lung cancer plans, 10 prostate, and 1 brain cancer scanning-beam proton plan(s) were analyzed. To account for the dose under uncertainties, we performed a comprehensive simulation in which the dose was recalculated 600 times per given plan under the influence of random and systematic setup errors and proton range errors. On the basis of simulation results, we determined the probability of dose variations and calculated the expected values and standard deviations of dose-volume histograms. The uncertainties in dose were spatially visualized on the planning CT as a probability map of failure to target coverage or overdose of critical structures. RESULTS: The expected value of target coverage under the uncertainties was consistently lower than that of the nominal value determined from the clinical target volume coverage without setup error or range uncertainty, with a mean difference of -1.1% (-0.9% for breath-hold), -0.3%, and -2.2% for lung, prostate, and a brain cases, respectively. The organs with most sensitive dose under uncertainties were esophagus and spinal cord for lung, rectum for prostate, and brain stem for brain cancer. CONCLUSIONS: A clinically feasible robustness plan analysis tool based on direct dose calculation and statistical simulation has been developed. Both the expectation value and standard deviation are useful to evaluate the impact of uncertainties. The existing proton beam planning method used in this institution seems to be adequate in terms of target coverage. However, structures that are small in volume or located near the target area showed greater sensitivity to uncertainties.

Assessment of shoulder position variation and its impact on IMRT and VMAT doses for head and neck cancer.

BACKGROUND: For radiotherapy of the head and neck, 5-point mask immobilization is used to stabilize the shoulders. Still, the daily position of the shoulders during treatment may be different from the position in the treatment plan despite correct isocenter setup. The purpose of this study was to determine the interfractional displacement of the shoulders relative to isocenter over the course of treatment and the associated dosimetric effect of this displacement. METHODS: The extent of shoulder displacements relative to isocenter was assessed for 10 patients in 5-point thermoplastic masks using image registration and daily CT-on-rails scans. Dosimetric effects on IMRT and VMAT plans were evaluated in Pinnacle based on simulation CTs modified to represent shoulder shifts between 3 and 15 mm in the superior-inferior, anterior-posterior, and right-left directions. The impact of clinically observed shoulder shifts on the low-neck dose distributions was examined. RESULTS: Shoulder motion was 2-5 mm in each direction on average but reached 20 mm. Superior shifts resulted in coverage loss, whereas inferior shifts increased the dose to the brachial plexus. These findings were generally consistent for both IMRT and VMAT plans. Over a course of observed shifts, the dose to 99% of the CTV decreased by up to 101 cGy, and the brachial plexus dose increased by up to 72 cGy. CONCLUSIONS: he position of the shoulder affects target coverage and critical structure dose, and may therefore be a concern during the setup of head and neck patients, particularly those with low neck primary disease.

Evaluation of the dose calculation accuracy in intensity-modulated radiation therapy for mesothelioma, focusing on low doses to the contralateral lung.

This study compares Monte Carlo (MC) with conventional treatment planning system (TPS) calculations. The EGS4nrc MC code, BEAMnrc, was commissioned to simulate a Varian 21Ex Linac. The accuracy of the simulations, including points blocked by the jaws, was evaluated by comparing MC with ion chamber and MOSFET measurements. Eight mesothelioma IMRT cases were planned using Eclipse (pencil beam and superposition convolution algorithms). Dose distributions were recalculated using BEAMnrc/DOSxyz, and compared with TPS. MC agreed with experimental results for IMRT fields within 3% (96% of points). For regions blocked by the jaws, average agreement between MC and experiment was better than 5% up to 20 cm from isocenter. The pencil beam algorithm underestimated lung MLD, V20, and V5, compared with MC, by a mean (range) of 16% (11-22%), 9.0% (2.4-30.1%), and 11.8% (2-30%), respectively. The superposition convolution algorithm gave better agreement of 8.5% (0-17%), 4% (0-12%) and 0% (-6-6%). Mean dose to the targets was better than +/- 5% in all cases. In conclusion, there is excellent correlation between TPS and MC calculations for the target doses. The pencil beam algorithm and superposition convolution algorithms both underestimate lung dose parameters, but the superposition convolution dose offers improvements in dose calculation accuracy for these patients.

Effect of dental restorations and prostheses on radiotherapy dose distribution: a Monte Carlo study.

Dental restorations, fixed prosthodontics, and implants affect dose distribution in head and neck radiation therapy due to the high atomic number of the materials utilized. The backscatter of electrons from metallic materials due to the impinging treatment x-ray results in localized dose enhancements. These dose enhancements cause localized mucositis in patients who have dental work, a significant clinical complication. We investigated the backscatter effect of 23 configurations of dental work using the EGS4nrc Monte Carlo (MC) simulation system. We found that all-metal fixed partial dentures caused the highest amount of dose enhancement--up to 33%--while amalgam restorations did not cause a significant amount. Restorations with a ceramic veneer caused up to 8% enhancement. Between 3 mm and 5 mm of water-equivalent material almost completely absorbed the backscatter. MC simulations provide an accurate estimate of backscatter dose, and may provide patient-specific estimates in future.

Monte Carlo calculation of rectal dose when using an intrarectal balloon during prostate radiation therapy.

Air-filled intrarectal balloons can be used to localize and immobilize the prostate for radiation therapy, allowing dose escalation to the prostate and reducing the probability of radiation proctitis, but also introducing potentially significant heterogeneity. We compare the Eclipse treatment planning system (TPS) with Monte Carlo (MC) simulations for 5 patients to assess how well a conventional TPS includes the effect of the balloon on doses near the rectum. The MC results show that, for a 27-Gy prescription to the 95% isodose line, Eclipse overestimates the volume of the rectum receiving more than 26 Gy (96%) by 2 approximately 10 cc and the volume of the rectum receiving between 12 approximately 15 Gy by 10 approximately 20 cc. Differential dose volume histograms are also computed and compared for individual fields in the anterior expansion of the rectum, and the TPS is again shown to predict higher mean dose in the region by 0.3 approximately 1.0 Gy.

Build-up and surface dose measurements on phantoms using micro-MOSFET in 6 and 10 MV x-ray beams and comparisons with Monte Carlo calculations.

This work is intended to investigate the application and accuracy of micro-MOSFET for superficial dose measurement under clinically used MV x-ray beams. Dose response of micro-MOSFET in the build-up region and on surface under MV x-ray beams were measured and compared to Monte Carlo calculations. First, percentage-depth-doses were measured with micro-MOSFET under 6 and 10 MV beams of normal incidence onto a flat solid water phantom. Micro-MOSFET data were compared with the measurements from a parallel plate ionization chamber and Monte Carlo dose calculation in the build-up region. Then, percentage-depth-doses were measured for oblique beams at 0 degrees-80 degrees onto the flat solid water phantom with micro-MOSFET placed at depths of 2 cm, 1 cm, and 2 mm below the surface. Measurements were compared to Monte Carlo calculations under these settings. Finally, measurements were performed with micro-MOSFET embedded in the first 1 mm layer of bolus placed on a flat phantom and a curved phantom of semi-cylindrical shape. Results were compared to superficial dose calculated from Monte Carlo for a 2 mm thin layer that extends from the surface to a depth of 2 mm. Results were (1) Comparison of measurements with MC calculation in the build-up region showed that micro-MOSFET has a water-equivalence thickness (WET) of 0.87 mm for 6 MV beam and 0.99 mm for 10 MV beam from the flat side, and a WET of 0.72 mm for 6 MV beam and 0.76 mm for 10 MV beam from the epoxy side. (2) For normal beam incidences, percentage depth dose agree within 3%-5% among micro-MOSFET measurements, parallel-plate ionization chamber measurements, and MC calculations. (3) For oblique incidence on the flat phantom with micro-MOSFET placed at depths of 2 cm, 1 cm, and 2 mm, measurements were consistent with MC calculations within a typical uncertainty of 3%-5%. (4) For oblique incidence on the flat phantom and a curved-surface phantom, measurements with micro-MOSFET placed at 1.0 mm agrees with the MC calculation within 6%, including uncertainties of micro-MOSFET measurements of 2%-3% (1 standard deviation), MOSFET angular dependence of 3.0%-3.5%, and 1%-2% systematical error due to phantom setup geometry asymmetry. Micro-MOSFET can be used for skin dose measurements in 6 and 10 MV beams with an estimated accuracy of +/- 6%.

Dynamic IMRT treatments of sinus region tumors: comparison of Monte Carlo calculations with treatment planning system calculations and ion chamber measurements.

Results are presented comparing Monte Carlo (MC) calculations for dynamic IMRT treatments of tumors in the sinus region with Eclipse treatment planning system dose calculations, and ion chamber measurements. The EGS4nrc MC code, BEAMnrc, was commissioned to simulate a Varian 21Ex Linac for both open and IMRT fields. The accuracy of the simulation for IMRT plans was evaluated using a head phantom by comparing MC, Eclipse, TLD results, and ion chamber in solid water phantom measurements. The MC code was then used to simulate dose distributions for five patients who were treated using dynamic IMRT for tumors in the sinus region. The results were compared with absolute and relative dose distributions calculated using Eclipse (pencil beam, modified-Batho inhomogeneity correction). Absolute dose differences were also compared with ion chamber results. Comparison of the doses calculated on the head phantom using MC, compared with Eclipse, ion chamber, and TLD measurements showed differences of -3.9%, -1.4%, and -2.0%, respectively (MC is colder). Relative dose distributions for the patient plans calculated using MC agreed well with those calculated using Eclipse with respect to targets and critical organs, indicating the modified-Batho correction is adequate. Average agreement for mean absolute target doses between MC and Eclipse was -3.0 +/-; 2.3% (1 s.d.). Agreement between ion chamber and Eclipse for these patients was -2.2 +/- 1.9%, compared with 0.2 +/- 2.0% for all head and neck IMRT patients. When Eclipse doses were corrected based on ion chamber results, agreement between MC and Eclipse was -0.7 +/- 2.0%, indicating a small systematic uncertainty in the doses calculated using the treatment planning system for this subset of patients.

A three-dimensional computed tomography-assisted Monte Carlo evaluation of ovoid shielding on the dose to the bladder and rectum in intracavitary radiotherapy for cervical cancer.

PURPOSE: To determine the effects of Fletcher Suit Delclos ovoid shielding on dose to the bladder and rectum during intracavitary radiotherapy for cervical cancer. METHODS AND MATERIALS: The Monte Carlo method was used to calculate the dose in 12 patients receiving low-dose-rate intracavitary radiotherapy with both shielded and unshielded ovoids. Cumulative dose-difference surface histograms were computed for the bladder and rectum. Doses to the 2-cm(3) and 5-cm(3) volumes of highest dose were computed for the bladder and rectum with and without shielding. RESULTS: Shielding affected dose to the 2-cm(3) and 5-cm(3) volumes of highest dose for the rectum (10.1% and 11.1% differences, respectively). Shielding did not have a major impact on the dose to the 2-cm(3) and 5-cm(3) volumes of highest dose for the bladder. The average dose reduction to 5% of the surface area of the bladder was 53 cGy. Reductions as large as 150 cGy were observed to 5% of the surface area of the bladder. The average dose reduction to 5% of the surface area of the rectum was 195 cGy. Reductions as large as 405 cGy were observed to 5% of the surface area of the rectum. CONCLUSIONS: Our data suggest that the ovoid shields can greatly reduce the radiation dose delivered to the rectum. We did not find the same degree of effect on the dose to the bladder. To calculate the dose accurately, however, the ovoid shields must be included in the dose model.