![]() ![]() These groundbreaking efforts have benefitted immensely from the availability of large-scale highly annotated datasets, such as the ImageNet visual recognition task dataset, 1 or the Modified National Institute of Standards and Technology (MNIST) handwriting dataset. The rise of artificial intelligence (AI) and machine learning in recent years has seen an explosion in technical approaches to statistical modeling, driven mostly by innovation on large datasets in the computational science community. Through FAIR principles and standardized approaches to data dissemination, radiation oncology AI research has nothing to lose and everything to gain. Moreover, we provide historical context of FAIR data dissemination protocols, difficulties in the current distribution of radiation oncology data, and recommendations regarding data dissemination for eventual utilization in AI models. ![]() ![]() This manuscript reviews the current and future state of radiation oncology data dissemination, with a particular emphasis on published imaging datasets, AI data challenges, and associated infrastructure. Importantly, the recent establishment of Findable, Accessible, Interoperable, Reusable (FAIR) principles for scientific data management have enabled an increasing number of radiation oncology related datasets to be disseminated through data repositories, thereby acting as a rich source of data for AI model building. However, large curated datasets - often involving imaging data and corresponding annotations - are required to develop radiation oncology AI models. RAONDT 78, 119–122 (2006).10.1016/j.radonc.2005.12.Artificial intelligence (AI) has exceptional potential to positively impact the field of radiation oncology. C., Yorke E., and Fuks Z., “From IMRT to IGRT: Frontierland or Neverland?,” Radiother. B., “Image-guided radiotherapy: Rationale, benefits, and limitations,” Lancet Oncol. et al., “Implementing IMRT in clinical practice: A joint document of the American Society for Therapeutic Radiology and Oncology and the American Association of Physicists in Medicine,” Int. J., “Oncology: Practice guidelines and outcomes measurement,” Ambul. H., “Integration of database for radiotherapy outcomes analysis,” J. In addition the database is web-based and accessible by multiple users, facilitating its convenient application and use. ![]() Given the limited number of general-purpose computational environments for radiotherapy research and outcome studies, this computational platform represents a powerful and convenient tool that is well suited for analyzing dose distributions biologically and correlating them with the delivered radiation dose distributions and other patient-related clinical factors. This computational platform consists of (1) an infrastructural database that stores patient diagnosis, IMRT treatment details, and follow-up information, (2) an interface tool that is used to import and export IMRT plans in DICOM RT and AAPM/RTOG formats from a wide range of planning systems to facilitate reproducible research, (3) a graphical data analysis and programming tool that visualizes all aspects of an IMRT plan including dose, contour, and image data to aid the analysis of treatment plans, and (4) a software package that calculates radiobiological models to evaluate IMRT treatment plans. In this article, a computational platform is presented to facilitate radiotherapy research and outcome studies in radiation oncology. Radiotherapy research and outcome analyses are essential for evaluating new methods of radiation delivery and for assessing the benefits of a given technology on locoregional control and overall survival. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |