INTEGRATED PACS--RADIOLOGICAL EVALUATION/TREATMENT NEUROLOGICAL DISEASE

现代神经放射学的复杂性要求神经放射科医生从庞大而复杂的数据集中提取、解释和交流重要内容。需要一种新的图像和数据管理模式，以智能地利用临床管理方案(路径)中固有的信息，并确定用于图像采集、组织、显示、处理和将患者的主观发现客观化的最佳方案；(B)提供及时的ANC准确诊断；以及(C)通过简化审查和潜在地减少进行的测试数量来减少医疗保健服务的低效。我们假设，这些PACS技术将促进快速的临床行动，并通过促进智能报告的工具，创建新的报告和教学方法，并形成可搜索的数据库用于研究和医疗目的，提高医生的满意度。该项目的目标有两个：[1]通过开发临床驱动的自适应阅读协议，实施对神经疾病患者的成像研究和相关文件的定制管理和呈现的新策略；[2]通过开发智能自适应报告编写协议，帮助自动编写包含关键图像的多媒体报告，并找到SIN脑瘤患者。这些目标将通过开发面向对象的成像过程、任务以及患者护理过程中使用和生成的数据的过程和数据模型来实现，从而开发用于数据呈现、在线量化和自动报告创建的自适应成像协议。对这些模型、协议和工具包的技术性能进行了正式评估。最后，我们将评估由此产生的基于PACS工作站的系统对神经放射科医生和神经肿瘤科医生的表现、信心和满意度的临床影响。

The complexity of contemporary neuroradiology requires neuroradiologists to extract, interpret, and communicate important content from large and complex data sets. A new paradigm for image and data management is required to intelligently utilizes the information inherent in clinical management schemes (pathways) and to determine the optimal protocols for image acquisition, organization, display, processing and objectifying patients' subjective findings; (b) providing timely anc accurate diagnosis; and (c) reducing the inefficiency of healthcare delivery by streamlining review and potentially reducing the number of tests performed. We hypothesize that these PACS technologies will facilitate rapid clinical actions and increase physician satisfaction by facilitating tools for intelligent reporting, creating new reporting, and teaching methods, and forming searchable databases for research and medical care purposes. This project's goals are twofold: [1] to implement a new strategy for customized management and presentation of imaging studies and related documents in patients with neurological disease by developing clinically driven adaptive reading protocols; and [2] to assist automatic authoring of multi-media reports containing critical images and finding sin brain tumor patients by developing intelligent adaptive report authoring protocols. These objectives will be achieved by developing object-oriented process and data models of the imaging processes, the tasks, and the data used and generated in the course of patient care, leading to the development of adaptive imaging protocols for data presentation, online quantification, and automated report creation. The technical performance of these models, protocols, and toolkits are formally evaluated. Lastly, we will evaluate the clinical impact of the resulting PACS-workstation-based system on the performance, confidence, and satisfaction of neuroradiologists and neuro-oncologists.