期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
基于深度学习的人体腰椎MRI图像自动分割 被引量:2
1
作者 冯鹏程 曹圣伟 +5 位作者 覃兵 伍彪 吴济文 周璐 钱志余 祝桥桥 《生命科学仪器》 2023年第5期53-57,共5页
腰椎间盘病变是导致下背部疼痛的主要原因之一,而腰椎磁共振成像(MRI)图像在其诊断中发挥了关键作用。本研究引入了一种基于深度学习的自动分割方法,旨在增强椎间盘形态结构的识别和分割,从而减轻医疗专业人员手动分割所带来的不便和不... 腰椎间盘病变是导致下背部疼痛的主要原因之一,而腰椎磁共振成像(MRI)图像在其诊断中发挥了关键作用。本研究引入了一种基于深度学习的自动分割方法,旨在增强椎间盘形态结构的识别和分割,从而减轻医疗专业人员手动分割所带来的不便和不一致性。我们采用了著名的分割网络Mask-Rcnn(Mask Region-based Convolutional Neural Network),该网络以其卓越的特征提取能力、出色的目标检测性能和精确的实例分割结果而闻名,因此成为最佳选择。通过利用PyTorch中的神经网络模型库,我们重构了数据集接口并微调了输出层参数,以更好地适应识别和分割腰椎间盘的任务。本研究使用了包含1545张腰椎MRI图像的公开数据集,每张图像都标注了椎间盘等结构。在对数据集进行预处理以保留有关椎间盘的标注后,我们随机选择了450张图像进行测试,其余用于训练。在经过20个训练周期后,我们实现了97.7%的平均精度和98.6%的平均召回率,96.9%的DICE系数。本研究强调了基于深度学习的自动分割方法在显著改善腰椎MRI图像中椎间盘的识别和分割方面的潜力。这种方法在临床应用中具有巨大前景,可能提高疾病诊断的准确性和效率,减轻了医疗专业人员的负担。 展开更多
关键词 深度学习 神经网络 生物医学图像 腰椎间盘自动切割
暂未订购
An origami shield with supporting frame structures optimized by a feature-driven topology optimization method
2
作者 Dongsheng Jia pengcheng feng +5 位作者 Liangdi Wang Longcan Chen Jun Wang Jihong Zhu Yingjie Xu Weihong Zhang 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2024年第1期447-456,共10页
In this paper,the design,manufacture and testing of an origami protective shield with a supporting frame structure are presented.It consists of an origami shield surface and a deployable supporting frame structure tha... In this paper,the design,manufacture and testing of an origami protective shield with a supporting frame structure are presented.It consists of an origami shield surface and a deployable supporting frame structure that needs to be portable and sufficiently stiff.First,for the design of the shield surface,a threestage origami crease pattern is developed to reduce the shield size in the folded state.The shield surface consists of several stiff modular panels and layered with flexible fabric.The modular panels are made of a multi-layer composite where a ceramic layer is made of small pieces to improve durability as those small pieces enable restriction of crack propagation.Then,the supporting frame structure is designed as a chain-of-bars structure in order to fold into a highly compact state as a bundle of bars and deploy in sequence.Thus,a feature-driven topology structural optimization method preserving component sequence is developed where the inter-dependence of sub-structures is taken into account.A bar with semi-circular ends is used as a basic design feature.The positions of the bar’s end points are treated as design variables and the width of the bars is kept constant.Then,a constraint on the total length of the chain of bars is introduced.Finally,the modular panels made of multi-layer composite and the full-scale prototype of the origami shield are fabricated and tested to verify the bullet-proof performance. 展开更多
关键词 ORIGAMI Deployable structure Structure design SHIELD Composite materials
在线阅读 下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部