Item Relationship Graph Neural Networks for E-Commerce.

In a modern e-commerce recommender system, it is important to understand the relationships among products. Recognizing product relationships-such as complements or substitutes-accurately is an essential task for generating better recommendation results, as well as improving explainability in recommendation. Products and their associated relationships naturally form a product graph, yet existing efforts do not fully exploit the product graph's topological structure. They usually only consider the information from directly connected products. In fact, the connectivity of products a few hops away also contains rich semantics and could be utilized for improved relationship prediction. In this work, we formulate the problem as a multilabel link prediction task and propose a novel graph neural network-based framework, item relationship graph neural network (IRGNN), for discovering multiple complex relationships simultaneously. We incorporate multihop relationships of products by recursively updating node embeddings using the messages from their neighbors. An edge relational network is designed to effectively capture relational information between products. Extensive experiments are conducted on real-world product data, validating the effectiveness of IRGNN, especially on large and sparse product graphs.

Determining the Effectiveness of a New Device for Hand Therapy (The FEPSim Device): Feasibility Protocol for a Randomized Controlled Trial Study.

BACKGROUND: Impairments of the forearm, wrist, and hand affect a sizable proportion of individuals and impose a significant economic burden on health care systems. FEPSim is a medical device for hand and wrist rehabilitation. The FEPSim device could be part of the standard of care for upper extremity rehabilitation during therapeutic activities to increase range of motion, dexterity, and strength. FEPSim has not yet been tested in a health care setting; therefore, a trial of the effectiveness of FEPSim in upper extremity rehabilitation is warranted. OBJECTIVE: This study aims to assess the feasibility of conducting a definitive trial in terms of recruitment, eligibility criteria, the type and number of diagnoses included, the length and dosage of the intervention, and data collection methods. This study also aims to gather clinical and statistical information as well as information related to the cost and usability, which allows for an economic evaluation of the device. METHODS: The trial will use a randomized controlled design comprising 47 intervention participants and 47 control group participants. Participants will be adults (age≥18 years) attending outpatient rehabilitation with limitations in their forearm, wrist, or hand function due to distal radial or ulnar fractures, stroke, or osteoarthritis. This study's primary outcome variables are related to patients' range of motion and strength, specifically active and passive wrist flexion and extension range of motion; active and passive forearm pronation and supination range of motion; grip strength; and pinch strength. The secondary outcome variables are related to patients' perceived wrist pain and disability in activities of daily living. The patients' perceived wrist pain and disability in activities of daily living will be measured using the patient-rated wrist evaluation questionnaire. The control group will receive the standard of care at each of the 2 hospital facilities (Glenrose Rehabilitation and Royal Alexandra Hospitals). The intervention group will receive the same standard of care as the control group at each facility and will use the FEPSim device for therapeutic activities to increase strength, range of motion, resistance, and dexterity. All the participants will be assessed at baseline (week 0); weeks 2, 4, and 8; and postintervention (week 10). RESULTS: The FEPSim study was launched in April 2020. This study is currently on hold because of the global COVID-19 pandemic. The recruitment process is expected to resume by September 2020, and the primary impact analysis is expected to be conducted by December 2020. CONCLUSIONS: This study will provide valuable information on the measurement of comparative intervention effects, technology acceptance by hand therapists, and how associated treatment and product costs will contribute to the evidence planning process, which will be crucial for the future adoption of FEPSim. TRIAL REGISTRATION: International Standard Randomized Controlled Trial Number Registry ISRCTN13656014; https://www.isrctn.com/ISRCTN13656014. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/22145.

Clinical commissioning of intensity-modulated proton therapy systems: Report of AAPM Task Group 185.

Proton therapy is an expanding radiotherapy modality in the United States and worldwide. With the number of proton therapy centers treating patients increasing, so does the need for consistent, high-quality clinical commissioning practices. Clinical commissioning encompasses the entire proton therapy system's multiple components, including the treatment delivery system, the patient positioning system, and the image-guided radiotherapy components. Also included in the commissioning process are the x-ray computed tomography scanner calibration for proton stopping power, the radiotherapy treatment planning system, and corresponding portions of the treatment management system. This commissioning report focuses exclusively on intensity-modulated scanning systems, presenting details of how to perform the commissioning of the proton therapy and ancillary systems, including the required proton beam measurements, treatment planning system dose modeling, and the equipment needed.

Incremental Hash-Bit Learning for Semantic Image Retrieval in Nonstationary Environments.

Images are uploaded to the Internet over time which makes concept drifting and distribution change in semantic classes unavoidable. Current hashing methods being trained using a given static database may not be suitable for nonstationary semantic image retrieval problems. Moreover, directly retraining a whole hash table to update knowledge coming from new arriving image data may not be efficient. Therefore, this paper proposes a new incremental hash-bit learning method. At the arrival of new data, hash bits are selected from both existing and newly trained hash bits by an iterative maximization of a 3-component objective function. This objective function is also used to weight selected hash bits to re-rank retrieved images for better semantic image retrieval results. The three components evaluate a hash bit in three different angles: 1) information preservation; 2) partition balancing; and 3) bit angular difference. The proposed method combines knowledge retained from previously trained hash bits and new semantic knowledge learned from the new data by training new hash bits. In comparison to table-based incremental hashing, the proposed method automatically adjusts the number of bits from old data and new data according to the concept drifting in the given data via the maximization of the objective function. Experimental results show that the proposed method outperforms existing stationary hashing methods, table-based incremental hashing, and online hashing methods in 15 different simulated nonstationary data environments.

Facilitating integration of regulated pharmacy technicians into community pharmacy practice in Ontario: Results of an exploratory study.

BACKGROUND: The integration of regulated pharmacy technicians (RPTs) into community pharmacy practice was intended to relieve pharmacists of certain technical duties to facilitate greater provision of direct patient care services, commensurate with expanded scope of practice. There is scant data available regarding the success, value and impact of RPT integration, either in Canada or in other jurisdictions. METHODS: Pharmacists and RPTs working in community practices were interviewed. Qualitative data were categorized using an iterative coding process to identify themes related to barriers and facilitators to integrating and optimizing the role of the RPT in community practice in Ontario. RESULTS: A total of 16 RPTs and 12 pharmacists were interviewed from community sites in Ontario. Strategies for facilitating successful integration of RPTs into daily workflow were identified, based on 4 major themes: environmental factors, interpersonal factors, professional identity formation and innovative use of delegation. INTERPRETATION: Integration of RPTs into community practice is complex and requires careful management, planning, training and follow-up to ensure attainment of objectives. Simply hiring RPTs and placing them into existing workflow patterns is generally not a successful implementation strategy. CONCLUSIONS: Implementation strategies identified through this study can provide employers, managers, pharmacists and RPTs with opportunities to enhance RPT integration and optimize the role of both pharmacists and RPTs in community practice.

Prognostic factors of radiation dermatitis following passive-scattering proton therapy for breast cancer.

BACKGROUND: To identify prognostic factors for grade 3 radiation dermatitis following passive-scattering proton therapy for breast cancer. METHODS: This retrospective study included data on 23 (11 post-mastectomy and 12 post-lumpectomy) breast cancer patients who underwent proton therapy with the passive scattering technique in our institute from 2012 to 2016. Each patient received 50-50.4 cobalt Gy equivalent (CGE) at 1.8 or 2 CGE per daily fraction. Logistic regression analysis was performed to identify prognostic factors for grade 3 skin toxicity. Receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC) were used to evaluate the performance of the models. RESULTS: 43% of the studied patients developed grade 3 radiation dermatitis. The dose-volume histogram (DVH) parameters of V52.5CGE and D10cm3 to skin5mm were correlated with grade 3 radiation dermatitis in both univariate and multivariate logistic regression analyses. Univariate logistic regression analysis suggested that D10cm3 to skin5mm (AUC = 0.69) and V52.5CGE to skin5mm (AUC = 0.70) were prognostic for grade 3 skin toxicity. The models using the combination of D10cm3 to skin5mm or V52.5CGE to skin5mm with breast volume marginally increased the AUC to 0.72 and 0.73, respectively. Models using the combination of D10cm3 to skin5mm or V52.5CGE to skin5mm with history of smoking increased the AUC to 0.75 and 0.83, respectively. CONCLUSION: In the current study, we identified prognostic factors for grade 3 radiation dermatitis in patients treated with passive-scattering proton therapy for breast cancer. This study provides promising tool for identifying high risk patients for whom treatment plan adjustment could be done to reduce the risk of radiation-induced grade 3 skin toxicity.

Incremental Hashing for Semantic Image Retrieval in Nonstationary Environments.

A very large volume of images is uploaded to the Internet daily. However, current hashing methods for image retrieval are designed for static databases only. They fail to consider the fact that the distribution of images can change when new images are added to the database over time. The changes in the distribution of images include both discovery of a new class and a distribution of images within a class owing to concept drift. Retraining of hash tables using all images in the database requires a large computation effort. This is also biased to old data owing to the huge volume of old images which leads to a poor retrieval performance over time. In this paper, we propose the incremental hashing (ICH) method to deal with the two aforementioned types of changes in the data distribution. The ICH uses a multihashing to retain knowledge coming from images arriving over time and a weight-based ranking to make the retrieval results adaptive to the new data environment. Experimental results show that the proposed method is effective in dealing with changes in the database.

Evaluation of the range shifter model for proton pencil-beam scanning for the Eclipse v.11 treatment planning system.

Existing proton therapy pencil-beam scanning (PBS) systems have limitations on the minimum range to which a patient can be treated. This limitation arises from practical considerations, such as beam current intensity, layer spacing, and delivery time. The range shifter (RS) - a slab of stopping material inserted between the nozzle and the patient - is used to reduce the residual range of the incident beam so that the treatment ranges can be extended to shallow depths. Accurate modeling of the RS allows one to calculate the beam spot size entering the patient, given the proton energy, for arbitrary positions and thicknesses of the RS in the beam path. The Eclipse version 11 (v11) treatment planning system (TPS) models RS-induced beam widening by incorporating the scattering properties of the RS material into the V-parameter. Monte Carlo simulations with Geant4 code and analytical calculations using the Fermi-Eyges (FE) theory with Highland approximation of multiple Coulomb scattering (MCS) were employed to calculate proton beam widening due to scattering in the RS. We demonstrated that both methods achieved consistent results and could be used as a benchmark for evaluating the Eclipse V-parameter model. In most cases, the V-parameter model correctly predicted the beam spot size after traversing the RS. However, Eclipse did not enforce the constraint for a nonnegative covariance matrix when fitting the spot sizes to derive the phase space parameters, which resulted in incorrect calculations under specific conditions. In addition, Eclipse v11 incorrectly imposed limits on the individual values of the phase space parameters, which could lead to incorrect spot size values in the air calculated for beams with spot sigmas <3.8 mm. Notably, the TPS supplier (Varian) and hardware vendor (Ion Beam Applications) inconsistently refer to the RS position, which may result in improper spot size calculations.

Outcomes of Sinonasal Cancer Treated With Proton Therapy.

PURPOSE: To report disease outcomes after proton therapy (PT) for sinonasal cancer. METHODS AND MATERIALS: Eighty-four adult patients without metastases received primary (13%) or adjuvant (87%) PT for sinonasal cancers (excluding melanoma, sarcoma, and lymphoma). Common histologies were olfactory neuroblastoma (23%), squamous cell carcinoma (22%), and adenoid cystic carcinoma (17%). Advanced stage (T3 in 25% and T4 in 69%) and high-grade histology (51%) were common. Surgical procedures included endoscopic resection alone (45%), endoscopic resection with craniotomy (12%), or open resection (30%). Gross residual disease was present in 26% of patients. Most patients received hyperfractionated PT (1.2 Gy [relative biological effectiveness (RBE)] twice daily, 99%) and chemotherapy (75%). The median PT dose was 73.8 Gy (RBE), with 85% of patients receiving more than 70 Gy (RBE). Prognostic factors were analyzed using Kaplan-Meier analysis and proportional hazards regression for multiple regression. Dosimetric parameters were evaluated using logistic regression. Serious, late grade 3 or higher toxicity was reported using the National Cancer Institute Common Terminology Criteria for Adverse Events, version 4. The median follow-up was 2.4 years for all patients and 2.7 years among living patients. RESULTS: The local control (LC), neck control, freedom from distant metastasis, disease-free survival, cause-specific survival, and overall survival rates were 83%, 94%, 73%, 63%, 70%, and 68%, respectively, at 3 years. Gross total resection and PT resulted in a 90% 3-year LC rate. The 3-year LC rate was 61% for primary radiation therapy and 59% for patients with gross disease. Gross disease was the only significant factor for LC on multivariate analysis, whereas grade and continuous LC were prognostic for overall survival. Six of 12 local recurrences were marginal. Dural dissemination represented 26% of distant recurrences. Late toxicity occurred in 24% of patients (with grade 3 or higher unilateral vision loss in 2%). CONCLUSIONS: Dose-intensified, hyperfractionated PT with or without concurrent chemotherapy results in excellent LC after gross total resection, and results in patients with gross disease are encouraging. Patients with high-grade histology are at greater risk of death from distant dissemination. Continuous LC is a major determinant of survival justifying aggressive local therapy in nearly all cases.

Determinants of moderate to vigorous physical activity and obesity in children: a structural equation modeling analysis.

BACKGROUND: The determinants of physical activity (PA) and body fatness in Chinese adolescents are rarely examined. This study aimed to investigate the effect of attitude toward PA, screen time, parents' socioeconomic status (SES), and exercise habit on PA and body fatness among Chinese children by using structural equation modeling (SEM) analysis. METHODS: Data obtained from the second Community Fitness Survey in Hong Kong were utilized, in which students from one secondary school of each of the 18 districts of Hong Kong were recruited. A total of 2517 questionnaires with physical fitness items were successfully distributed to students aged 13-19 years in these districts. Families' SES, parents' exercise habit, children's intention to participate in PA, amount of moderate to vigorous PA (MVPA), screen time, children's attitude toward PA, and children's body fat percentage were measured and analyzed with SEM. The structural equation model was composed of a measurement model and a structural model. The model was tested with Mplus 6. The Chi-square test, root mean square error of approximation, comparative fit index, and Tucker-Lewis index were calculated to evaluate model fit. The model was then modified based on the model fit indices. RESULTS: Children's intention to participate in PA was a strong predictor of their engagement in MVPA. Parents' exercise habit had both direct and indirect (via attitude) effects on their children's intention to participate in PA. Screen time was not a predictor of body composition. Children's intention to participate in PA directly affected their body composition. Children's attitude toward PA, parents' exercise habit, and SES had significant effects on the children's intention to participate in PA. Furthermore, obesity had a negative effect on the children's attitude toward PA. CONCLUSION: To promote MVPA and prevent obesity in Chinese children of Hong Kong, it is important to design intervention that enhances children's intention and attitude in PA, as well as parent's exercise habits. Tailormade programs that take SES into consideration are also essential. Further studies are necessary to extend the results and test the model in other metropolitan areas in China.

Adversarial Feature Selection Against Evasion Attacks.

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion, and malware detection, although their security against well-crafted attacks that aim to evade detection by manipulating data at test time has not yet been thoroughly assessed. While previous work has been mainly focused on devising adversary-aware classification algorithms to counter evasion attempts, only few authors have considered the impact of using reduced feature sets on classifier security against the same attacks. An interesting, preliminary result is that classifier security to evasion may be even worsened by the application of feature selection. In this paper, we provide a more detailed investigation of this aspect, shedding some light on the security properties of feature selection against evasion attacks. Inspired by previous work on adversary-aware classifiers, we propose a novel adversary-aware feature selection model that can improve classifier security against evasion attacks, by incorporating specific assumptions on the adversary's data manipulation strategy. We focus on an efficient, wrapper-based implementation of our approach, and experimentally validate its soundness on different application examples, including spam and malware detection.

MLPNN Training via a Multiobjective Optimization of Training Error and Stochastic Sensitivity.

The training of a multilayer perceptron neural network (MLPNN) concerns the selection of its architecture and the connection weights via the minimization of both the training error and a penalty term. Different penalty terms have been proposed to control the smoothness of the MLPNN for better generalization capability. However, controlling its smoothness using, for instance, the norm of weights or the Vapnik-Chervonenkis dimension cannot distinguish individual MLPNNs with the same number of free parameters or the same norm. In this paper, to enhance generalization capabilities, we propose a stochastic sensitivity measure (ST-SM) to realize a new penalty term for MLPNN training. The ST-SM determines the expectation of the squared output differences between the training samples and the unseen samples located within their Q -neighborhoods for a given MLPNN. It provides a direct measurement of the MLPNNs output fluctuations, i.e., smoothness. We adopt a two-phase Pareto-based multiobjective training algorithm for minimizing both the training error and the ST-SM as biobjective functions. Experiments on 20 UCI data sets show that the MLPNNs trained by the proposed algorithm yield better accuracies on testing data than several recent and classical MLPNN training methods.

A Web application for the management of clinical workflow in image-guided and adaptive proton therapy for prostate cancer treatments.

Image-guided radiotherapy (IGRT), based on radiopaque markers placed in the prostate gland, was used for proton therapy of prostate patients. Orthogonal X-rays and the IBA Digital Image Positioning System (DIPS) were used for setup correction prior to treatment and were repeated after treatment delivery. Following a rationale for margin estimates similar to that of van Herk,(1) the daily post-treatment DIPS data were analyzed to determine if an adaptive radiotherapy plan was necessary. A Web application using ASP.NET MVC5, Entity Framework, and an SQL database was designed to automate this process. The designed features included state-of-the-art Web technologies, a domain model closely matching the workflow, a database-supporting concurrency and data mining, access to the DIPS database, secured user access and roles management, and graphing and analysis tools. The Model-View-Controller (MVC) paradigm allowed clean domain logic, unit testing, and extensibility. Client-side technologies, such as jQuery, jQuery Plug-ins, and Ajax, were adopted to achieve a rich user environment and fast response. Data models included patients, staff, treatment fields and records, correction vectors, DIPS images, and association logics. Data entry, analysis, workflow logics, and notifications were implemented. The system effectively modeled the clinical workflow and IGRT process.

Diversified Sensitivity-Based Undersampling for Imbalance Classification Problems.

Undersampling is a widely adopted method to deal with imbalance pattern classification problems. Current methods mainly depend on either random resampling on the majority class or resampling at the decision boundary. Random-based undersampling fails to take into consideration informative samples in the data while resampling at the decision boundary is sensitive to class overlapping. Both techniques ignore the distribution information of the training dataset. In this paper, we propose a diversified sensitivity-based undersampling method. Samples of the majority class are clustered to capture the distribution information and enhance the diversity of the resampling. A stochastic sensitivity measure is applied to select samples from both clusters of the majority class and the minority class. By iteratively clustering and sampling, a balanced set of samples yielding high classifier sensitivity is selected. The proposed method yields a good generalization capability for 14 UCI datasets.

A simplified methodology to produce Monte Carlo dose distributions in proton therapy.

The purpose of this study was to develop a simplified methodology that will produce Monte Carlo (MC) dose distribution for proton therapy which can be used as a clinical aid in determining the adequacy of proton plans produced from the treatment planning system (TPS). The Geant4 Monte Carlo toolkit was used for all simulations. The geometry of the double scatter nozzle in the simulation was a simplification of the treatment nozzle. The proton source was modeled as discrete energy layers, each with a unique energy distribution and weighting factor. The simplified MC system was designed to give the same dose distribution as the measured data used to commission the TPS. After the simplified MC system was finalized, a series of verification comparisons were made between it, measurements, and the clinically used TPS. Comparisons included the lateral profile of a stair-shaped compensator that simulated a sharp lateral heterogeneity and depth-dose measurements through heterogeneous materials. The simplified MC system matched measurements to within 2% or 2 mm for all commissioning data under investigation; moreover, the distal edge and lateral penumbra was within 1 mm of the measurements. The simplified MC system was able to better reproduce the measured profiles for a stair-shaped compensator than the TPS. Both MC and TPS matched the measured depth dose through heterogeneous materials to within 2% or 2 mm. The simplified MC system was straightforward to implement, and produced accurate results when compared to measurements. Therefore, it holds promise as a clinically useful methodology to validate the relative dose distribution of patient treatment plans produced by the treatment planning systems.

Proton therapy for skull base chordomas: an outcome study from the university of Florida proton therapy institute.

Objectives Skull base chordoma is a rare, locally aggressive tumor located adjacent to critical structures. Gross total resection is difficult to achieve, and proton therapy has the conformal advantage of delivering a high postoperative dose to the tumor bed. We present our experience using proton therapy to treat 33 patients with skull base chordomas. Design Retrospective outcomes study. Setting University of Florida Proton Therapy Institute; 2007 to 2011. Participants A total of 33 patients with skull base chordomas received postoperative three-dimensional conformal proton therapy. The patients were 79% male and 6% diabetic; 27% had received a gross total resection. Main Outcome Measures The gross tumor/tumor bed received a dose between 77.4 CGE and 79.4 CGE. Local control and overall survival were tracked, and radiation toxicity was assessed using a modified Radiation Therapy Oncology Group/European Organization for Research and Treatment of Cancer Late Radiation Morbidity Scoring Scheme. Results Median follow-up for all patients was 21 months. Local control and overall survival rates at 2 years were 86% and 92%, respectively. Grade 2 toxicity was observed in 18% of our cohort in the form of unilateral hearing loss partially corrected with a hearing aid. No grade 2 or higher optic or brainstem toxicities were observed. Conclusions Proton therapy is an effective treatment modality for skull base chordomas.

A dosimetric comparison of intensity-modulated proton therapy optimization techniques for pediatric craniopharyngiomas: a clinical case study.

BACKGROUND: To evaluate the dosimetric characteristics of intensity-modulated proton therapy (IMPT) optimization techniques and pencil-beam scanning (PBS) nozzle designs on pediatric craniopharyngiomas. PROCEDURE: We compared a double-scatter (DS) plan with IMPT plans using single-field uniform dose (SFUD) optimization or multi-field optimization (MFO) and different PBS nozzles. The clinical impacts of SFUD versus MFO, range shifters, and two different PBS nozzles were compared. For target coverage assessment, the conformity index and inhomogeneity coefficient were evaluated. RESULTS: Although both proton therapy techniques achieved adequate target coverage, IMPT achieved a better conformity index of 0.78 versus 0.60 for DS. For the inhomogeneity coefficient, IMPT with MFO performed better than using SFUD or DS. MFO with the dedicated nozzle (MFO-DN) achieved the best result of 0.023, as compared to values of 0.03 or higher for the other plans. IMPT achieved lower doses to the normal tissues, as compared to DS; MFO-DN had the best results. The DN provided the best beam-spot characteristics and the sharpest lateral penumbra. MFO reduced the need for range shifters. CONCLUSIONS: As compared to DS proton therapy for pediatric craniopharyngiomas, IMPT achieved significantly better target coverage and dose sparing of normal tissue. Nozzle designs that provided small beam spots and sharp lateral penumbra allowed for better target coverage and reduced dose to normal tissue. In the case of shallow targets, MFO, in contrast to SFUD, required minimal use of range shifters, which preserved the penumbra and the dosimetric advantage. MFO-DN proved to be the optimal technique for IMPT.

SU-E-T-218: The IHE-RO Helper Tool: Demonstrating the Connectivity Issues Solved by IHE-RO.

PURPOSE: To develop a Web-based application (IHE-RO Helper) to allow comprehensive review of the interconnectivity and interoperability of various radiotherapy devices established through testing sanctioned by the Integrating Healthcare Enterprise-Radiation Oncology (IHE-RO). MATERIAL AND METHODS: IHE-RO is an initiative sponsored by ASTRO to improve the way computer based systems in radiation oncology share information using well-defined data exchange standards (DICOM / HL7). At the IHE-RO Connectathon events over the last 4 years, 11 vendors with 14 different products have successfully tested and identified solutions to connectivity problems in treatment planning, simulation and delivery. Because the test results are highly technical, the interconnectivity issues amongst the RT devices may get overlooked by the end users. The IHE-RO helper tool is designed to operate in simple clinical terms with queries and presentations organized based on treatment techniques and clinical features that are familiar to the practitioners. For example, if you are planning to purchase a treatment planning system capable of generating plans (e.g. Stereotactic treatments) and are concerned whether the TPS can successfully transfer such data to your treatment management system (TMS) and subsequently to your treatment delivery system (TDS), the IHE-RO Helper can identify the connectivity requirements and list vendors that have successfully passed an IHE-RO Connectathon and validated their solution to the specific requirements. RESULTS: The IHE-RO helper tool provides a graphical and textual user interface to effectively demonstrate the solved interconnectivity problems between TPS, TMS and TDS. A report is also provided that explains the interconnectivity problems and its solutions. CONCLUSIONS: The IHE-RO helper is an effective tool to clearly identify vendor products that are IHE-RO compliant, thereby encourages vendor participation in testing and validation. Such a tool will be invaluable in procurement of new equipment to ensure a priori interoperability with anticipated RT devices deployed in the clinic. This research and development project is supported by the Bankhead-Coley Cancer Research Program grant # RC1-09BW-09-26833.

Proton therapy for head and neck cancer: rationale, potential indications, practical considerations, and current clinical evidence.

There is a strong rationale for potential benefits from proton therapy (PT) for selected cancers of the head and neck because of the opportunity to improve the therapeutic ratio by improving radiation dose distributions and because of the significant differences in radiation dose distribution achievable with x-ray-based radiation therapy (RT) and PT. Comparisons of dose distributions between x-ray-based and PT plans in selected cases show specific benefits in dose distribution likely to translate into improved clinical outcomes. However, the use of PT in head and neck cancers requires special considerations in the simulation and treatment planning process, and currently available PT technology may not permit realization of the maximum potential benefits of PT. To date, few clinical data are available, but early clinical experiences in sinonasal tumors in particular suggest significant improvements in both disease control and radiation-related toxicity.