医疗信息科学与技术

基于LabVIEW的磁共振射频接收单元自动化测试系统 

  刘瀚文，万遂人

（东南大学生物科学与医学工程学院，南京 210000）

摘要：为了解决磁共振射频接收单元手动测试繁杂耗时的问题，设计了一套基于LabVIEW的自动化测试系统。采用信号源、计算机配合自制的采集控制单元和时钟源组成测试系统的硬件平台。系统软件基于LabVIEW开发，采用分层次模块化架构，借助VISA软件包、动态链接库和AcitveX技术分别实现了仪器控制、数据采集和数据保存。利用该系统对某射频接收单元进行了实际测试，结果表明，该系统高效、稳定且扩展灵活，具有很强的实用意义。

关键字：自动化测试；射频接收单元；LabVIEW；动态链接库；AcitveX

中图分类号：TP206+.1                         文献标识码：   A

A LabVIEW-Based Automatic TestSystem for MRI RF Receiving Unit

LIUHan-wen ,WAN Sui-ren

(School of Biological Science and MedicalEngineering, Southeast University, Nanjing, 210000, China)

【Abstract】 It is complicatedand time-consuming to test MRI RF receiving unit manually. In order to solvethis problem, a set of automatic test system based on LabVIEW is presented here.The hardware platform is composed of a signal source and a computer togetherwith homemade acquisition control unit and clock source. The software isdeveloped based on LabVIEW and adopt the hierarchical modular architecture. UsingVISA package, DLL and AcitveX, it realizes the instrument control, dataacquisition and data storage. Actual tests for RF receiving unit is carried onwith this system. The results show that the system is efficient, stable andflexible expansion, which has a strong practical significance.

【Keywords】Automatic test; RFreceiving unit; LabVIEW; DLL; AcitveX

 

---

作者简介：万遂人，教授，主要研究方向：医学电子学.  

 

基于模型的旋转冠状动脉造影三维重建*
李泽文1，胡轶宁2
(1.东南大学生物科学与医学工程学院，南京 210096;2.东南大学计算机科学与工程学院，南京，210096）
摘要：本文提出了一种基于模型的稀疏角度投影图像冠状动脉体数据重建方法，本文的工作主要包括：1）提出了一种血管结构参数化算法，该算法在保证不同节段血管表面的空间连续性的基础上，对血管分支分叉不为进行自动识别和连接；2）建立了一种基于投影数据匹配的血管半径估计方法，用于设定血管初始半径；3）在参数优化过程中引入了包含利用血管结构先验知识和弹性先验进行约束，保证了血管结构的的平滑性和弹性先验以此来并排除降低噪声的干扰和，增大对初始坐标位置误差的容许度，并利用算法利用梯度下降法进行迭代优化。实验表明该重建方法对冠状动脉X射线造影重建能够收敛并具有较精确的重建结果。
关键字：三维重建；冠状动脉；X射线；旋转造影；模型
中图分类号：R318.0文献标识码：A


Object-Based 3-D Reconstruction of Arterial Trees from Coronary Angiograms
LI Ze-wen1,HU Yi-ning2
1(School of Bio-Medical Engineering, Southeast University, Nanjing, 210096，China）
2(Department of Computer Science and Engineering,Southeast University, Nanjing210096, China)
【Abstract】This paper describes an object-based approach to the problem of reconstructing three-dimensional descriptions of arterial trees from a few noisy angiographic projections. The stages of the method are: 1) an easy to implement parameter model are designed to represent bifurcations accurately, and ensure that the spatial continuity of the vascular surface; 2) an automatic algorithms for the initialization of parameter model; 3) The method incorporates a priori knowledge of the structure of the arteries into a natural optimality criterion that encompasses the entire arterial tree. We present an efficient optimization algorithm for object estimation, and demonstrate its performance by the experimental results.
【Key words】reconstruction; Coronary artery; X-ray; rotational angiography; parameter model
 

利用支持向量机对癌细胞的识别
唐思源，柳原，崔媛
(包头医学院计算机科学与技术系，内蒙古包头014040)
摘要：癌细胞识别是数字图像处理和模式识别领域的一个研究热点，在临床上也是一个比较有意义的研究课题，本文利用支持向量机的方法，通过提取细胞的特征来分类和识别癌细胞。首先收集彩色图像，对图像进行预处理，之后是进行分割及对单细胞和多细胞的特征提取，最后实现对癌变细胞的识别和分类。
关键字：数字图像处理；模式识别；支持向量机；特征提取
中图分类号：R734.2;TP391.41 文献标识码：A

SVM identification of cancer
TANG Si-yuan,LIUYuan,CUI Yuan
(Department of Computer Science and Technology, Baotou, Inner Mongolia Medical College, Baotou 014040,China)
【Abstract】Identification of cancer cells is a digital image processing and pattern recognition research focus areas, but also in a more clinically meaningful research, we use SVM method, feature extraction and classification of cells to identify cancer cells. First collect color images, image preprocessing, segmentation, and after a single-cell and multi-cell feature extraction, and finally achieve the identification and classification of cancerous cells. 
【Keywords】 digital image processing; pattern recognition; support vector machine; Feature Extraction
 

 

 

小训练样本的人脸识别研究

黄宏博1,穆志纯1
（1．北京科技大学 自动化学院，北京 100083 2.北京信息科技大学 计算中心,北京 100192）
摘要:人脸识别问题在很多情况下都会面临小训练样本的问题，在训练样本数量远小于数据维数的情形下许多人脸识别方法都会遇到困难。本文分析了造成小样本问题的原因，从虚拟样本扩充、数据降维以及算法优化等不同方面总结了解决方法，并对不同方法进行了简要评价，对解决小样本问题的未来发展方向进行了展望。
关键字：人脸识别；小样本问题；虚拟样本；数据降维
中图分类号：TP391.41 文献标识码：A

Review of Face Recognition on Small Sample Size Problem
HUANG Hong-bo1,2,MU Zhi-chun1
1(School of Automation & Electrical Engineering,University of Science&Technology Beijing,Beijing 10083)
2( Computing Center,Beijing Information Science&Technology University, Beijing 100192)
【Abstract】Small Sample Size Problem is a general problem in face recognition. Most methods of face recognition will encounter difficulties when the number of samples is much smaller than the dimension of face data. This paper analyzed the the origin of the problem, and then defferent solutions were presented includeing virtual sample expansion,data reduction and algorithm optimization. A brief evaluation of different methods was given. Future directions of solving the problem were prospected .
【Key words】Face Recognition; Small Sample Size Problem;Virtual Sample;Data Reduction
 

 

中医肺病科电子病历系统设计与实现

董国华，朱习军
（青岛科技大学信息科学技术学院，山东青岛 266061）
摘要：中医肺病科电子病历系统的设计是为了将中医院肺病科的纸质病历转化为电子病历，从而更好的保存、使用中医肺病科病历，并为以后进行中医肺病数据的分析研究做前期准备。系统用Java Web技术进行开发，采用MVC设计模式，并用struts框架简化开发步骤。最终开发出的中医肺病科电子病历系统拥有快捷简单的操作界面，图文并茂的病历显示功能和方便的病历打印功能。
关键词：中医肺病科电子病历系统；电子病历；模块化
中图分类号：TP273   文献标识码：A

Design and Implementation of Electronic Medical Records System of Traditional Chinese Medicine Lung Disease 
DONG Guo-hua,ZHU Xi-jun
(Department of Information Science and Technology ,QingDao University of Science&Technology ,Qingdao 266061,China) 
【Abstract】The design of electronic medical records (EMR)system of Traditional Chinese Medicine(TCM) lung disease is to transform TCM lung disease paper-based medical records to EMR(electronic medical records).This system can better save and use the medical records .It provides convenience to analysis the TCM lung disease medical records.This system was designed by Java Web technology,using MVC design model,and applying struts frame to simplify its developing procedure.The system designed own fast and simple operation interface and abundant medical records showing function,and it also has convenient medical records printing function.
【Key Words】EMR system of TCM lung disease diagnosis; EMR;modularization