排序方式: 共有92条查询结果,搜索用时 15 毫秒
1.
2.
3.
胰腺的自动分割一直是医学图像分割中一项具有挑战性的问题。胰腺是一个具有高度解剖变异性的器官,目前的多图谱分割方法很难对胰腺的边缘产生精确的分割。针对这一问题,采用了基于多图谱配准的分割算法对胰腺进行分割,优化了一种局部动态阈值的后处理方法。在标签融合阶段,采用概率阈值融合算法、Majority voting(MV)算法、STAPLE算法和SIMPLE算法四种标签融合算法进行对比。在后处理阶段,采用局部动态阈值处理方法,首先通过初步分割结果对目标图像提取目标区域,然后自动确定阈值实现该区域的二值化,最终与初步分割结果取交集作为最终分割结果。采用留一交叉验证策略对80例NIH胰腺CT图像和22例来自上海本地医院的胰腺CT图像进行分割,最终得到的DSC分别为79.98%和81.30%。实验结果表明,所提方法实现了对胰腺的有效分割。 相似文献
4.
5.
6.
严琰 《数学的实践与认识》2016,(13):39-45
RFID技术可以对供应链系统中的产品信息进行有效追溯和实时共享,以化解系统管理效率、安全防范、监控和保障能力极其低下等问题.但是,由于应用成本的制约,使很多附加值较低的行业仍望而却步,严重制约了RFID技术的发展和普及.以单个零售商和供应商组成的供应链系统为研究对象,首先,对基于RFID的供应链产品入库及日常盘点管理流程进行了简要分析;在此基础上,分别构建了集中决策下采用与不采用RFID技术时的供应链利润模型,并对其最优决策问题进行详细分析,得出供应链系统在集中决策下实施RFID技术的投资决策条件,所得结论可以为供应链系统在集中决策下实施RFID技术应用决策问题提供理论支持. 相似文献
7.
The photoproduction of K+ mesons from the nucleon provides important constraints on the nucleon excitation spectrum and at threshold energies challenges effective field theories based on chiral perturbation in the strange quark sector. Preliminary cross-section measurements for γ(P, K+)A are presented at an unprecedented beam energy resolution. The data was collected at the MAMI-C facility in Mainz using the Crystal Ball Detector. A new method of K+ detection was used in which the K+ is tagged from its weak decay products in the detector crystals. This technique has application with other calorimeters at present and future hadron facilities. 相似文献
8.
KurtStockinger 《高能物理与核物理计算国际会议公报》2001,(1):256-257
This paper presents a performance analysis of accessing tag data clustered in two different ways,namely event-wise clustering (generic tag)vs.attribute-wise clustering (sliced tag).The results show that especially “Prefetch-optimisation“ results in an additional performance gain of sliced tags over generic tags when only a subset of all the tag attributes is accessed. 相似文献
9.
10.
A joint clustering and classification approach is proposed.This approach exploits unlabeled data for efficient clustering,which is applied in the classification with support vector machine(SVM) in the case of small-size training samples.The proposed method requires no prior information on data labels,and yields better cluster structures.Through cluster assumption and the notions of support vectors,the most confident k cluster centers and data points near the cluster boundaries are labeled and used to train a reliable SVM classifier.Our method gains better estimation of data distributions and mitigates the unrepresentative problem of small-size training samples.The data set collected from Landsat Thematic Mapper(Landsat TM-5) validates the effectiveness of the proposed approach. 相似文献