Computer applications for diagnostic medical imaging provide generally a wide range of tools to support physicians in their daily diagnosis activities. Unfortunately, some functionalities are specialized for specific diseases or imaging modalities, while other ones are useless for the images under investigation. Nevertheless, the corresponding Graphical User Interface (GUI) widgets are still present on the screen reducing the image visualization area. As a consequence, the physician may be affected by cognitive overload and visual stress causing a degradation of performances, mainly due to unuseful widgets. In clinical environments, a GUI must represent a sequence of steps for image investigation following a well-defined workflow. This paper proposes a software framework aimed at addressing the issues outlined before. Specifically, we designed a DICOM based mechanism of data-driven GUI generation, referring to the examined body part and imaging modality as well as to the medical image analysis task to perform. In this way, the self-configuring GUI is generated on-the-fly, so that just specific functionalities are active according to the current clinical scenario. Such a solution provides also a tight integration with the DICOM standard, which considers various aspects of the technology in medicine but does not address GUI specification issues. The proposed workflow is designed for diagnostic workstations with a local file system on an interchange media acting inside or outside the hospital ward. Accordingly, the DICOMDIR conceptual data model, defined by a hierarchical structure, is exploited and extended to include the GUI information thanks to a new Information Object Module (IOM), which reuses the DICOM information model. The proposed framework exploits the DICOM standard representing an enabling technology for an auto-consistent solution in medical diagnostic applications. In this paper we present a detailed description of the framework, its software design, and a proof-of-concept implementation as a suitable plug-in of the OsiriX imaging software.

中文翻译：

---

基于DICOM的数据驱动的自适应GUI生成框架。

诊断医学成像的计算机应用程序通常提供广泛的工具，以支持医师的日常诊断活动。不幸的是，某些功能专门用于特定的疾病或成像方式，而其他功能对于正在研究的图像则无用。但是，相应的图形用户界面（GUI）小部件仍显示在屏幕上，从而减小了图像可视化区域。结果，医师可能会受到认知超负荷和视觉压力的影响，这主要是由于无用的小部件而导致性能下降。在临床环境中，GUI必须代表按照明确定义的工作流程进行图像调查的一系列步骤。本文提出了一个旨在解决之前概述的问题的软件框架。特别，我们设计了一种基于DICOM的数据驱动GUI生成机制，它参考了被检查的身体部位和成像方式以及要执行的医学图像分析任务。通过这种方式，可即时生成自配置GUI，从而根据当前临床情况仅激活特定功能。这样的解决方案还提供了与DICOM标准的紧密集成，该标准考虑了医学技术的各个方面，但没有解决GUI规范问题。拟议的工作流程专为诊断工作站设计，该工作站具有在医院病房内部或外部运行的交换媒体上的本地文件系统。因此，由分层结构定义的DICOMDIR概念数据模型 由于新的信息对象模块（IOM）可以重复利用DICOM信息模型，因此可以对其进行利用和扩展以包括GUI信息。提议的框架利用了DICOM标准，该标准代表了一种用于医学诊断应用程序中自动一致解决方案的启用技术。在本文中，我们将详细介绍该框架，其软件设计以及作为OsiriX成像软件的合适插件的概念验证实现。