首先比对传统家居设计方式介绍了当前虚拟现实技术的发展情况,关注当前流行的几款虚拟建模软件,阐述了目前UE4软件国外与国内的研究现状。详细介绍了UE4家居建模的流程,包括前置工作与UE4部分两个模块。使用3ds Max 2018软件搭建卧室环...首先比对传统家居设计方式介绍了当前虚拟现实技术的发展情况,关注当前流行的几款虚拟建模软件,阐述了目前UE4软件国外与国内的研究现状。详细介绍了UE4家居建模的流程,包括前置工作与UE4部分两个模块。使用3ds Max 2018软件搭建卧室环境模型,接着对比两种方法将3ds Max 2018生成的模型导入到UE4软件中,着重介绍使用DataSmith插件导出udatasmith文件再导入到UE4软件中的过程,在UE4中对卧室家居环境详细修改、调整光源、物体材质等,最后对日后UE4大型场景的创建与研究进行了展望。展开更多
Objective:Traditional medical image visualization technologies present several limitations including the poor intuitiveness of 2D images,overlapping imaging blind spots,and insufficient interactivity.These shortcoming...Objective:Traditional medical image visualization technologies present several limitations including the poor intuitiveness of 2D images,overlapping imaging blind spots,and insufficient interactivity.These shortcomings make them unable to satisfy the demands of precision medicine and medical education.This study aims to develop a universal medical image demonstration system based on extended reality(XR)technology,which is compatible with devices such as the HoloLens.By employing 3D visualization and multimodal interaction design,the system provides a more efficient and intuitive approach for clinical diagnosis,medical education,and surgical simulation.Methods:The system employs Unreal Engine as the core platform for architecture framework construction,supporting customized medical image visualization for XR devices.Real chest CT images were utilized in this study.Image segmentation was performed using 3D Slicer,while mask preprocessing was conducted via Anaconda.The masked images and raw data were then imported into Unreal Engine.The core framework of the proposed system was developed using Unreal Engine's Blueprint visual scripting and Unreal Motion Graphics(UMG)interface designer.A self-directed learning assessment experiment was designed to evaluate the efficacy and performance of the system.Results:The experimental group achieved a pulmonary window recognition accuracy of 82%,a mediastinal window accuracy of 88%,and an overall accuracy of 85%.By comparison,the control group exhibited a pulmonary window accuracy of 50%,a mediastinal window accuracy of 44%,and an overall accuracy of 47%.Conclusions:The medically oriented imaging demonstration system significantly improves recognition accuracy and learning effectiveness,verifying its practical utility and validity.展开更多
文摘首先比对传统家居设计方式介绍了当前虚拟现实技术的发展情况,关注当前流行的几款虚拟建模软件,阐述了目前UE4软件国外与国内的研究现状。详细介绍了UE4家居建模的流程,包括前置工作与UE4部分两个模块。使用3ds Max 2018软件搭建卧室环境模型,接着对比两种方法将3ds Max 2018生成的模型导入到UE4软件中,着重介绍使用DataSmith插件导出udatasmith文件再导入到UE4软件中的过程,在UE4中对卧室家居环境详细修改、调整光源、物体材质等,最后对日后UE4大型场景的创建与研究进行了展望。
基金supported by the Nanchong Science and Technology Planning Project Fund(Grant No.22YYJCYJ0068)the Sichuan Provincial Department of Science and Technology(Project No.:2023NSFSC0646).
文摘Objective:Traditional medical image visualization technologies present several limitations including the poor intuitiveness of 2D images,overlapping imaging blind spots,and insufficient interactivity.These shortcomings make them unable to satisfy the demands of precision medicine and medical education.This study aims to develop a universal medical image demonstration system based on extended reality(XR)technology,which is compatible with devices such as the HoloLens.By employing 3D visualization and multimodal interaction design,the system provides a more efficient and intuitive approach for clinical diagnosis,medical education,and surgical simulation.Methods:The system employs Unreal Engine as the core platform for architecture framework construction,supporting customized medical image visualization for XR devices.Real chest CT images were utilized in this study.Image segmentation was performed using 3D Slicer,while mask preprocessing was conducted via Anaconda.The masked images and raw data were then imported into Unreal Engine.The core framework of the proposed system was developed using Unreal Engine's Blueprint visual scripting and Unreal Motion Graphics(UMG)interface designer.A self-directed learning assessment experiment was designed to evaluate the efficacy and performance of the system.Results:The experimental group achieved a pulmonary window recognition accuracy of 82%,a mediastinal window accuracy of 88%,and an overall accuracy of 85%.By comparison,the control group exhibited a pulmonary window accuracy of 50%,a mediastinal window accuracy of 44%,and an overall accuracy of 47%.Conclusions:The medically oriented imaging demonstration system significantly improves recognition accuracy and learning effectiveness,verifying its practical utility and validity.
