J. Oh, A. Apte, R. Al-Lozi, J. Bradley, I. E. El Naqa
Radiation pneumonitis (RP) is a potentially fatal side effect arising in lung cancer patients who receive radiotherapy as part of their treatment. For the modeling of RP outcomes data, several predictive models based on traditional statistical methods and machine learning techniques have been reported. However, no guidance to variation in performance has been provided to date. In this study, we explore several machine learning algorithms for classification of RP data. The performance of these classification algorithms is investigated in conjunction with several feature selection strategies and the impact of the feature selection strategy on performance is further evaluated. The extracted features include patients demographic, clinical and pathological variables, treatment techniques, and dose-volume metrics. In conjunction, we have been developing an in-house Matlab-based open source software tool, called DREES, customized for modeling and exploring dose response in radiation oncology. This software has been upgraded with a popular classification algorithm called support vector machine (SVM), which seems to provide improved performance in our exploration analysis and has strong potential to strengthen the ability of radiotherapy modelers in analyzing radiotherapy outcomes data.
{"title":"Towards Prediction of Radiation Pneumonitis Arising from Lung Cancer Patients Using Machine Learning Approaches","authors":"J. Oh, A. Apte, R. Al-Lozi, J. Bradley, I. E. El Naqa","doi":"10.5166/JROI-1-1-5","DOIUrl":"https://doi.org/10.5166/JROI-1-1-5","url":null,"abstract":"Radiation pneumonitis (RP) is a potentially fatal side effect arising in lung cancer patients who receive radiotherapy as part of their treatment. For the modeling of RP outcomes data, several predictive models based on traditional statistical methods and machine learning techniques have been reported. However, no guidance to variation in performance has been provided to date. In this study, we explore several machine learning algorithms for classification of RP data. The performance of these classification algorithms is investigated in conjunction with several feature selection strategies and the impact of the feature selection strategy on performance is further evaluated. The extracted features include patients demographic, clinical and pathological variables, treatment techniques, and dose-volume metrics. In conjunction, we have been developing an in-house Matlab-based open source software tool, called DREES, customized for modeling and exploring dose response in radiation oncology. This software has been upgraded with a popular classification algorithm called support vector machine (SVM), which seems to provide improved performance in our exploration analysis and has strong potential to strengthen the ability of radiotherapy modelers in analyzing radiotherapy outcomes data.","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132553894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Fechter, J. Dolz, A. Chirindel, Matthias Schlachter, M. Carles, S. Adebahr, M. Mix, U. Nestle
Lung cancer is the major cause of cancer death worldwide. The most common form of lung cancer is non-small cell lung cancer(NSCLC). Stereotactic body radiation therapy (SBRT) has emerged as a good alternative to surgery in patients with peripheralstage I NSCLC, demonstrating favorable tumor control and low toxicity. Due to spatial relationship to several critical organs atrisk, SBRT of centrally located lesions is associated with more severe toxicity and requires modification in dose application andfractionation, which is currently evaluated in clinical trials. Therefore a classification of lung tumors into central or peripheralis required. In this work we present a novel, highly versatile, mulitmodality tool for tumor classification which requires no userinteraction. Furthermore the tool can automatically segment the trachea, proximal bronchial tree, mediastinum, gross target volumeand internal target volume. The proposed work is evaluated on 19 cases with different image modalities assessing segmentationquality as well as classification accuracy. Experiments showed a good segmentation quality and a classification accuracy of 95 %.These results suggest the use of the proposed tool for clinical trials to assist clinicians in their work and to fasten up the workflowin NSCLC patients treatment.
{"title":"Fully Automatic Danger Zone Determination for SBRT in NSCLC","authors":"T. Fechter, J. Dolz, A. Chirindel, Matthias Schlachter, M. Carles, S. Adebahr, M. Mix, U. Nestle","doi":"10.3933/JROI-7-1-26","DOIUrl":"https://doi.org/10.3933/JROI-7-1-26","url":null,"abstract":"Lung cancer is the major cause of cancer death worldwide. The most common form of lung cancer is non-small cell lung cancer(NSCLC). Stereotactic body radiation therapy (SBRT) has emerged as a good alternative to surgery in patients with peripheralstage I NSCLC, demonstrating favorable tumor control and low toxicity. Due to spatial relationship to several critical organs atrisk, SBRT of centrally located lesions is associated with more severe toxicity and requires modification in dose application andfractionation, which is currently evaluated in clinical trials. Therefore a classification of lung tumors into central or peripheralis required. In this work we present a novel, highly versatile, mulitmodality tool for tumor classification which requires no userinteraction. Furthermore the tool can automatically segment the trachea, proximal bronchial tree, mediastinum, gross target volumeand internal target volume. The proposed work is evaluated on 19 cases with different image modalities assessing segmentationquality as well as classification accuracy. Experiments showed a good segmentation quality and a classification accuracy of 95 %.These results suggest the use of the proposed tool for clinical trials to assist clinicians in their work and to fasten up the workflowin NSCLC patients treatment.","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125909725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The PROsaiq prototype, which is based on the use of smart devices, was developed to show the technical feasibility of a lean, low-cost ePRO system that integrated with the oncology information system MOSAIQ to provide the potential for benefits in routine patient care, and improved data for clinical research. The system was built with Free & Open Source Software and trialled for a limited number of assessments. The report describes the components used, the decisions made and the hurdles met during the project. An on-line demonstration system is available to showcase PROsaiqs functionality.
{"title":"PROsaiq: A Smart Device-Based and EMR-Integrated System for Patient-Reported Outcome Measurement in Routine Cancer Care","authors":"T. Schuler, Andrew Miller","doi":"10.5166/JROI-6-1-24","DOIUrl":"https://doi.org/10.5166/JROI-6-1-24","url":null,"abstract":"The PROsaiq prototype, which is based on the use of smart devices, was developed to show the technical feasibility of a lean, low-cost ePRO system that integrated with the oncology information system MOSAIQ to provide the potential for benefits in routine patient care, and improved data for clinical research. The system was built with Free & Open Source Software and trialled for a limited number of assessments. The report describes the components used, the decisions made and the hurdles met during the project. An on-line demonstration system is available to showcase PROsaiqs functionality.","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116976032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose/Objectives: Dose volume histogram (DVH) data are generally analyzed within the context of a treatment planning system (TPS) on a per-patient basis, with evaluation of single-plan or comparative dose distributions. However, TPS software generally cannot perform simultaneous comparative dosimetry among a cohort of patients. The same limitations apply to parallel analyses of three-dimensional structures and other clinical data. Materials/Methods: We developed a suite of tools ("RadOnc" package) using R statistical software to better compare pooled DVH data and empower analysis of structure data and clinical correlates. Representative patient data were identified among previously analyzed adult (n=13) and pediatric (n=1) cohorts and these data were used to demonstrate the performance and functionality of the RadOnc package. Results: The RadOnc package facilitates DVH data import from the TPS and includes automated methods for DVH visualization, dosimetric parameter extraction, statistical comparison among multiple DVHs, basic three-dimensional structural processing, and visualization tools to enable customizable production of publication-quality images. Conclusions: The RadOnc package provides a potent clinical research tool with the ability to integrate robust statistical software and dosimetric data from cohorts of patients. It is made freely available to the community for their current use and remains under active development.
{"title":"RadOnc: An R Package for Analysis of Dose-Volume Histogram and Three-Dimensional Structural Data","authors":"Reid F Thompson","doi":"10.3933/JROI-6-1-25","DOIUrl":"https://doi.org/10.3933/JROI-6-1-25","url":null,"abstract":"Purpose/Objectives: Dose volume histogram (DVH) data are generally analyzed within the context of a treatment planning system (TPS) on a per-patient basis, with evaluation of single-plan or comparative dose distributions. However, TPS software generally cannot perform simultaneous comparative dosimetry among a cohort of patients. The same limitations apply to parallel analyses of three-dimensional structures and other clinical data. Materials/Methods: We developed a suite of tools (\"RadOnc\" package) using R statistical software to better compare pooled DVH data and empower analysis of structure data and clinical correlates. Representative patient data were identified among previously analyzed adult (n=13) and pediatric (n=1) cohorts and these data were used to demonstrate the performance and functionality of the RadOnc package. Results: The RadOnc package facilitates DVH data import from the TPS and includes automated methods for DVH visualization, dosimetric parameter extraction, statistical comparison among multiple DVHs, basic three-dimensional structural processing, and visualization tools to enable customizable production of publication-quality images. Conclusions: The RadOnc package provides a potent clinical research tool with the ability to integrate robust statistical software and dosimetric data from cohorts of patients. It is made freely available to the community for their current use and remains under active development.","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126590224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Operations Research has a successful tradition of applying mathematical analysis to a wide range of applications, and problems in Medical Physics have been popular over the last couple of decades. The original application was in the optimal design of the uence map for a radiotherapy treatment, a problem that has continued to receive attention. However, Operations Research has been applied to other clinical problems like patient scheduling, vault design, and image alignment. The overriding theme of this article is to present how techniques in Operations Research apply to clinical problems, which we accomplish in three parts. First, we present the perspective from which an operations researcher addresses a clinical problem. Second, we succinctly introduce the underlying methods that are used to optimize a system, and third, we demonstrate how modern software facilitates problem design. Our discussion is supported by several publications to foster continued study. With numerous clinical, medical, and managerial decisions associated with a clinic, operations research has a promising future at improving how radiotherapy treatments are designed and delivered.
{"title":"Operations Research Methods for Optimization in Radiation Oncology","authors":"M. Ehrgott, A. Holder","doi":"10.3933/JROI-6-1-21","DOIUrl":"https://doi.org/10.3933/JROI-6-1-21","url":null,"abstract":"Operations Research has a successful tradition of applying mathematical analysis to a wide range of applications, and problems in Medical Physics have been popular over the last couple of decades. The original application was in the optimal design of the uence map for a radiotherapy treatment, a problem that has continued to receive attention. However, Operations Research has been applied to other clinical problems like patient scheduling, vault design, and image alignment. The overriding theme of this article is to present how techniques in Operations Research apply to clinical problems, which we accomplish in three parts. First, we present the perspective from which an operations researcher addresses a clinical problem. Second, we succinctly introduce the underlying methods that are used to optimize a system, and third, we demonstrate how modern software facilitates problem design. Our discussion is supported by several publications to foster continued study. With numerous clinical, medical, and managerial decisions associated with a clinic, operations research has a promising future at improving how radiotherapy treatments are designed and delivered.","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116080586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The purpose of the present work was to develop a relational database and associated applications to facilitate retrospective review of data present in radiation treatment plans. The data source was a commercial radiation treatment planning system (Pinnacle3, Philips Medical Systems, Milpitas CA), which is specifically characterized by an open data storage format and internal scripting capability. The database is an open-source, relational database (PostgreSQL, PostgreSQL Global Development Group, http://www.postgresql.org). The data is presented through a web interface in addition to being fully query-accessible using standard tools. A database schema was created to organize the large collection of parameters used to generate treatment plans as well as the parameters that characterized these plans. The system was implemented through a combination of the treatment planning systems internal scripting language and externally executed code. Data is exported in a way that is transparent to the user, through integration into an existing and routinely-used process. The system has been transparently incorporated into our radiation treatment planning workflow. The website-based database interface has allowed users with minimal training to extract information from the database.
本工作的目的是开发一个关系数据库和相关的应用程序，以促进对放射治疗计划中现有数据的回顾性审查。数据源是一个商业放射治疗计划系统(Pinnacle3, Philips Medical Systems, Milpitas CA)，其具体特点是开放的数据存储格式和内部脚本功能。该数据库是一个开源的关系数据库(PostgreSQL, PostgreSQL Global Development Group, http://www.postgresql.org)。除了使用标准工具完全可以查询之外，数据还通过web界面呈现。创建了一个数据库模式来组织用于生成治疗计划的大量参数集合以及表征这些计划的参数。该系统通过治疗计划系统内部脚本语言和外部执行代码的组合来实现。通过集成到现有的和常规使用的流程中，以一种对用户透明的方式导出数据。该系统已透明地纳入我们的放射治疗计划工作流程。基于网站的数据库接口允许用户以最少的训练从数据库中提取信息。
{"title":"Relational database of treatment planning system information","authors":"M. Kantor, G. Starkschall, P. Balter","doi":"10.3933/JROI-5-1-15","DOIUrl":"https://doi.org/10.3933/JROI-5-1-15","url":null,"abstract":"The purpose of the present work was to develop a relational database and associated applications to facilitate retrospective review of data present in radiation treatment plans. The data source was a commercial radiation treatment planning system (Pinnacle3, Philips Medical Systems, Milpitas CA), which is specifically characterized by an open data storage format and internal scripting capability. The database is an open-source, relational database (PostgreSQL, PostgreSQL Global Development Group, http://www.postgresql.org). The data is presented through a web interface in addition to being fully query-accessible using standard tools. A database schema was created to organize the large collection of parameters used to generate treatment plans as well as the parameters that characterized these plans. The system was implemented through a combination of the treatment planning systems internal scripting language and externally executed code. Data is exported in a way that is transparent to the user, through integration into an existing and routinely-used process. The system has been transparently incorporated into our radiation treatment planning workflow. The website-based database interface has allowed users with minimal training to extract information from the database.","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130758641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Colonias, D. Parda, S. Karlovits, R. Fuhrer, M. Trombetta, S. Strickland, Marc Luick, R. Billy, E. Werts
Purpose: The goal of this ongoing project is to develop and integrate a comprehensive electronic health record (EHR) throughout a multi-facility radiation oncology network to facilitate more efficient workflow and improve overall patient care and safety. Methodology: We required that the EHR provide pre-defined record and verify capability for radiation treatment while still providing a robust clinical health record. In 1996, we began to integrate the Local Area Network Treatment Information System (LANTIS®) across the West Penn Allegheny Radiation Oncology Network (currently including 9 sites). By 2001, we began modifying and expanding the assessment components and creating user-defined templates and have developed a comprehensive electronic health record across our network. Results: In addition to access to the technical record and verify information and imaging obtained for image-guided therapy, we designed and customized 6 modules according to our networks needs to facilitate information acquisition, tracking, and analysis as follows: 1) Demographics/scheduling; 2) Charge codes; 3) Transcription/clinical documents; 4) Clinical/technical assessments; 5) Physician orders 6) Quality assurance pathways. Each module was developed to acquire specific technical/clinical data prospectively in an efficient manner by various staff within the department in a format that facilitates data queries for outcomes/statistical analyses and promotes standardized quality guidelines resulting in a more efficient workflow and improved patient safety and care. Conclusions: Development of a comprehensive EHR across a radiation oncology network is feasible and can be customized to promote clinical/technical standards, facilitate outcomes studies, and improve communication and peer review. The EHR has improved patient care and network integration across a multi-facility radiation oncology system and has markedly reduced the flow and storage of paper across the network.
{"title":"A Radiation Oncology Based Electronic Health Record in an Integrated Radiation Oncology Network","authors":"A. Colonias, D. Parda, S. Karlovits, R. Fuhrer, M. Trombetta, S. Strickland, Marc Luick, R. Billy, E. Werts","doi":"10.3933/JROI-3-1-16","DOIUrl":"https://doi.org/10.3933/JROI-3-1-16","url":null,"abstract":"Purpose: The goal of this ongoing project is to develop and integrate a comprehensive electronic health record (EHR) throughout a multi-facility radiation oncology network to facilitate more efficient workflow and improve overall patient care and safety. Methodology: We required that the EHR provide pre-defined record and verify capability for radiation treatment while still providing a robust clinical health record. In 1996, we began to integrate the Local Area Network Treatment Information System (LANTIS®) across the West Penn Allegheny Radiation Oncology Network (currently including 9 sites). By 2001, we began modifying and expanding the assessment components and creating user-defined templates and have developed a comprehensive electronic health record across our network. Results: In addition to access to the technical record and verify information and imaging obtained for image-guided therapy, we designed and customized 6 modules according to our networks needs to facilitate information acquisition, tracking, and analysis as follows: 1) Demographics/scheduling; 2) Charge codes; 3) Transcription/clinical documents; 4) Clinical/technical assessments; 5) Physician orders 6) Quality assurance pathways. Each module was developed to acquire specific technical/clinical data prospectively in an efficient manner by various staff within the department in a format that facilitates data queries for outcomes/statistical analyses and promotes standardized quality guidelines resulting in a more efficient workflow and improved patient safety and care. Conclusions: Development of a comprehensive EHR across a radiation oncology network is feasible and can be customized to promote clinical/technical standards, facilitate outcomes studies, and improve communication and peer review. The EHR has improved patient care and network integration across a multi-facility radiation oncology system and has markedly reduced the flow and storage of paper across the network.\u0000","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127529396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Breithuth, J. Schiefer, M. Arn, S. Peters, W. Seelentag
It was the aim to develop and test a measurement technique for the source position of an afterloading system using an electronic two-dimensional detector array (2D array). A "GammaMed plus IX" high dose rate afterloading device (Varian Medical Systems, Palo Alto, USA), and a Seven29 2D detector array (PTW Freiburg GmbH, Freiburg, Germany) have been used. A hollow needle has been connected to the afterloading device. Its outer diameter is 3.0 mm and its length about 220mm. A 14 mm thick Perspex slab was fixed in a reproducible position on the 2D array. Above the 14th detector row, a groove was cut in the slab which accommodates the hollow needle in a fixed position relative to the 2D array. In order to define the position of the source, the signals of the detectors in the 14th detector row have been evaluated. A theoretical curve depending on the source position and strength, has been fitted to the acquired detector signals. It has been shown that the reproducibility of the measurement technique - including the reproducibility of the source placement - was within 0.15mm. This method can not only replace film measurements, it is also more exact and less time consuming.
其目的是开发和测试一种使用电子二维探测器阵列(2D阵列)测量后载系统源位置的技术。使用了“GammaMed plus IX”高剂量率后装装置(Varian Medical Systems, Palo Alto, USA)和Seven29 2D探测器阵列(PTW Freiburg GmbH, Freiburg, Germany)。一空心针已连接到后装装置。外径3.0 mm，长约220mm。将14毫米厚的有机玻璃板固定在二维阵列上的可重复位置。在所述第14排探测器上方，在所述平板上切割一凹槽，该凹槽将所述空心针置于相对于所述二维阵列的固定位置。为了确定源的位置，对第14排探测器的信号进行了评估。一个理论曲线取决于源的位置和强度，已拟合到采集的探测器信号。研究表明，测量技术的再现性——包括源位置的再现性——在0.15mm以内。该方法不仅可以代替胶片测量，而且精度更高，耗时更短。
{"title":"Determination of the source dwell position of an afterloading device with a detector array","authors":"F. Breithuth, J. Schiefer, M. Arn, S. Peters, W. Seelentag","doi":"10.5166/JROI-3-2-18","DOIUrl":"https://doi.org/10.5166/JROI-3-2-18","url":null,"abstract":"It was the aim to develop and test a measurement technique for the source position of an afterloading system using an electronic two-dimensional detector array (2D array). A \"GammaMed plus IX\" high dose rate afterloading device (Varian Medical Systems, Palo Alto, USA), and a Seven29 2D detector array (PTW Freiburg GmbH, Freiburg, Germany) have been used. A hollow needle has been connected to the afterloading device. Its outer diameter is 3.0 mm and its length about 220mm. A 14 mm thick Perspex slab was fixed in a reproducible position on the 2D array. Above the 14th detector row, a groove was cut in the slab which accommodates the hollow needle in a fixed position relative to the 2D array. In order to define the position of the source, the signals of the detectors in the 14th detector row have been evaluated. A theoretical curve depending on the source position and strength, has been fitted to the acquired detector signals. It has been shown that the reproducibility of the measurement technique - including the reproducibility of the source placement - was within 0.15mm. This method can not only replace film measurements, it is also more exact and less time consuming.\u0000","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130499123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose: A pilot study was undertaken to develop an integrated telemedicine platform for radiation oncology at Memorial Sloan-Kettering Cancer Center (MSKCC) and its regional sites. The platform consisted of a computer system with simultaneous display of multiple live data portals including 1) video-conferencing between physicians, 2) radiology, and 3) radiation treatment-planning system (RTPS). Methods and Materials: Two MSKCC regional centers were set up with a widescreen monitor, a dedicated computer, and a web camera with microphone. Each computer ran a Microsoft operating system, utilized video-conferencing software, and connected to the MSKCC Ethernet. This allowed for access to the health information system, radiology (web-based picture archiving and communication systems), RTPS, shared network drives and the internet. Results: After 3 months, physicians at two MSKCC sites were successfully able to implement the proposed telemedicine platform. A small sample of cases (prostate, breast, head and neck, and anal cases) were tested. Radiology images, radiation treatment volumes and plans, and portal images were reviewed. Side-by-side comparison of contouring techniques was performed. The platform allowed physicians to remotely review details of cases efficiently. The interactions of the telemedicine platform improved clinical understanding of each case and often resulted in contouring changes. Conclusion: From this experience, we feel that telemedicine could have a significant clinical impact on patient care, especially at centers with satellite clinics. The future goal of the system will be the development of a virtual tumor board for radiation oncologists. We envision the simultaneous display of multiple clinical components, including face photo, pathology, tumor images/videos of procedures, radiology, RTPS, and anatomy/contouring databases, on one screen surface.
{"title":"Pilot Study of a Radiation Oncology Telemedicine Platform","authors":"B. Mueller, C. Obcemea, James Lee, S. Sim","doi":"10.3933/JROI-2-1-10","DOIUrl":"https://doi.org/10.3933/JROI-2-1-10","url":null,"abstract":"Purpose: A pilot study was undertaken to develop an integrated telemedicine platform for radiation oncology at Memorial Sloan-Kettering Cancer Center (MSKCC) and its regional sites. The platform consisted of a computer system with simultaneous display of multiple live data portals including 1) video-conferencing between physicians, 2) radiology, and 3) radiation treatment-planning system (RTPS). Methods and Materials: Two MSKCC regional centers were set up with a widescreen monitor, a dedicated computer, and a web camera with microphone. Each computer ran a Microsoft operating system, utilized video-conferencing software, and connected to the MSKCC Ethernet. This allowed for access to the health information system, radiology (web-based picture archiving and communication systems), RTPS, shared network drives and the internet. Results: After 3 months, physicians at two MSKCC sites were successfully able to implement the proposed telemedicine platform. A small sample of cases (prostate, breast, head and neck, and anal cases) were tested. Radiology images, radiation treatment volumes and plans, and portal images were reviewed. Side-by-side comparison of contouring techniques was performed. The platform allowed physicians to remotely review details of cases efficiently. The interactions of the telemedicine platform improved clinical understanding of each case and often resulted in contouring changes. Conclusion: From this experience, we feel that telemedicine could have a significant clinical impact on patient care, especially at centers with satellite clinics. The future goal of the system will be the development of a virtual tumor board for radiation oncologists. We envision the simultaneous display of multiple clinical components, including face photo, pathology, tumor images/videos of procedures, radiology, RTPS, and anatomy/contouring databases, on one screen surface.\u0000","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130279278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Putora, Marcel Blattner, A. Papachristofilou, Fabio Mariotti, Beatrice Paoli, L. Plasswilm
Background: Treatment recommendations (guidelines) are commonly represented in text form. Based on parameters (questions) recommendations are defined (answers). Objectives: To improve handling, alternative forms of representation are required. Methods: The concept of Dodes (diagnostic nodes) has been developed. Dodes contain answers and questions. Dodes are based on linked nodes and additionally contain descriptive information and recommendations. Dodes are organized hierarchically into Dode trees. Dode categories must be defined to prevent redundancy. Results: A centralized and neutral Dode database can provide standardization, which is a requirement for the comparison of recommendations. Centralized administration of Dode categories can provide information about diagnostic criteria (Dode categories) underutilized in existing recommendations (Dode trees). Conclusions: Representing clinical recommendations in Dode trees improves their manageability, handling and updateability.
{"title":"Dodes (diagnostic nodes) for Guideline Manipulation","authors":"P. Putora, Marcel Blattner, A. Papachristofilou, Fabio Mariotti, Beatrice Paoli, L. Plasswilm","doi":"10.3933/JROI-2-1-6","DOIUrl":"https://doi.org/10.3933/JROI-2-1-6","url":null,"abstract":"Background: Treatment recommendations (guidelines) are commonly represented in text form. Based on parameters (questions) recommendations are defined (answers). Objectives: To improve handling, alternative forms of representation are required. Methods: The concept of Dodes (diagnostic nodes) has been developed. Dodes contain answers and questions. Dodes are based on linked nodes and additionally contain descriptive information and recommendations. Dodes are organized hierarchically into Dode trees. Dode categories must be defined to prevent redundancy. Results: A centralized and neutral Dode database can provide standardization, which is a requirement for the comparison of recommendations. Centralized administration of Dode categories can provide information about diagnostic criteria (Dode categories) underutilized in existing recommendations (Dode trees). Conclusions: Representing clinical recommendations in Dode trees improves their manageability, handling and updateability.\u0000","PeriodicalId":426862,"journal":{"name":"Journal of Radiation Oncology Informatics","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124471794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：