Junger D, Kücherer C, Hirt B, Burgert O
School of Informatics, Research Group Computer Assisted Medicine (CaMed), Reutlingen University, Reutlingen, Germany.
Faculty of Medicine, Department of Anatomy, Institute for Clinical Anatomy and Cell Analytics, Eberhard Karls University Tübingen, Tübingen, Germany.
Int J Comput Assist Radiol Surg. 2025 Mar;20(3):579-590. doi: 10.1007/s11548-024-03283-z. Epub 2024 Nov 27.
Surgical interventions and the intraoperative environment can vary greatly. A system that reliably recognizes the situation in the operating room should therefore be flexibly applicable to different surgical settings. To achieve this, transferability should be focused during system design and development. In this paper, we demonstrated the feasibility of a transferable, scenario-independent situation recognition system (SRS) by the definition and evaluation based on non-functional requirements.
Based on a high-level concept for a transferable SRS, a proof of concept implementation was demonstrated using scenarios. The architecture was evaluated with a focus on non-functional requirements of compatibility, maintainability, and portability. Moreover, transferability aspects beyond the requirements, such as the effort to cover new scenarios, were discussed in a subsequent argumentative evaluation.
The evaluation demonstrated the development of an SRS that can be applied to various scenarios. Furthermore, the investigation of the transferability to other settings highlighted the system's characteristics regarding configurability, interchangeability, and expandability. The components can be optimized step by step to realize a versatile and efficient situation recognition that can be easily adapted to different scenarios.
The prototype provides a framework for scenario-independent situation recognition, suggesting greater applicability and transferability to different surgical settings. For the transfer into clinical routine, the system's modules need to be evolved, further transferability challenges be addressed, and comprehensive scenarios be integrated.
手术干预措施和术中环境可能有很大差异。因此，一个能可靠识别手术室情况的系统应能灵活应用于不同的手术场景。为实现这一点，在系统设计和开发过程中应注重可转移性。在本文中，我们通过基于非功能需求的定义和评估，展示了一个可转移的、与场景无关的情况识别系统（SRS）的可行性。
基于可转移SRS的高级概念，通过场景展示了概念验证的实现。对该架构进行了评估，重点关注兼容性、可维护性和可移植性等非功能需求。此外，在随后的论证评估中讨论了超出需求的可转移性方面，例如覆盖新场景的工作量。
评估表明开发出了一个可应用于各种场景的SRS。此外，对向其他环境的可转移性的研究突出了该系统在可配置性、互换性和可扩展性方面的特点。这些组件可以逐步优化，以实现一种通用且高效的情况识别，能够轻松适应不同场景。
该原型为与场景无关的情况识别提供了一个框架，表明对不同手术场景具有更高的适用性和可转移性。为了将其转化为临床常规应用，需要改进系统模块，解决进一步的可转移性挑战，并整合全面的场景。
