A Multi-Scale Matched Filter for Nodule Detection in Chest X-Ray Radiography

您当前的位置：

首页 >

文章列表页 >

A Multi-Scale Matched Filter for Nodule Detection in Chest X-Ray Radiography

更新时间：2025-07-09

- A Multi-Scale Matched Filter for Nodule Detection in Chest X-Ray Radiography
- Vol. 45, Issue 4, Pages: 30-35(2011)
- 作者机构：
  
  西安交通大学图像处理与模式识别研究所,西安,710049
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.41
- Online First：10 April 2011，
  
  Published：2011
- 稿件说明：
移动端阅览
A Multi-Scale Matched Filter for Nodule Detection in Chest X-Ray Radiography[J]. 2011, 45(4): 30-35.
DOI：

A Multi-Scale Matched Filter for Nodule Detection in Chest X-Ray Radiography[J]. 2011, 45(4): 30-35. DOI：

摘要

为了提高胸部X射线摄影图像中肺结节的正确检测率

提出一种基于通道化Hotelling模型的多尺度匹配滤波算法.以X射线胸片中的正样本和负样本图像作为训练集合

用Hotelling分类器训练出不同尺度的匹配滤波器组

并与待检测的胸片图像做滤波.计算滤波输出图像的视觉检测差异

以最大差异为约束条件寻找最优尺度的滤波器

计算待检测图像中的结节尺寸和检测能力.实验结果表明

基于通道化Hotelling的匹配滤波算法的病灶检测能力与主观评价结果取得了较好的一致性

并具有较高的病灶检测准确率

滤波处理后的图像中仅含少量的假阳性区域

计算出的病灶的相对半径误差主要位于-0.21和0.18之间

该误差范围的图像占实验数据库图像的比例为86%.

Abstract

A multi-scale matched filter based on Hotelling classifier is presented to improve the accuracy of nodule detection in chest X-ray radiography. The positive and negative radiography samples are used to train multi-dimension matched filters by Hotelling model. The visual detection difference is calculated using the filter outputs of radiography

and the optimal dimension filter is searched subject to the maximum detection difference. Then the nodule size and detection capability are calculated based on the optimal filter. Experimental results show that there is good accordance of the detection performances between the presented method and subjective observers. The method improves the detection accuracy and reduces the false-positive regions in the processed images. Errors of the calculated relative nodule sizes mainly distribute between -0.21 and 0.18 and the proportion of the images in this range is 86%.

关键词

Keywords

references

SCHNEIDER C, AMJADI A, RICHTER A, et al. Automated lung nodule detection and segmentation [EB/OL]. [2010-08-16]. http:∥spie.org/x648.html?product_id=811985.

TSENG L Y, HUANG L C. An adaptive thresholding method for automatic lung segmentation in CT images [C]∥Proceedings of the 9th IEEE AFRICON. Piscataway, NJ, USA: IEEE, 2009: 1-5.

曹蕾, 占杰, 余晓锷,等. 基于自动阈值的CT图像快速肺实质分割算法 [J]. 计算机工程与应用,2008,12(44): 178-181.

CAO Lei, ZHAN Jie, YU Xiaoe, et al. Fast lung segmentation algorithm for thoracic CT based on automated thresholding[J]. Journal of Computer Engineering and Applications, 2008, 12(44): 178-181.

孙海林,张晓鹏,唐磊,等. 阈值法三维体积测量肺结节的64排CT实验研究[J]. 中国医学影像技术,2008, 24(8): 1157-1161.

SUN Hailin, ZHANG Xiaopeng, TANG Lei, et al. Three-dimensional volumetric measurement of pulmonary nodules by 64-MSCT with segmentation threshold algorithm: experimental study [J]. Chin J Med Imaging Technol, 2008, 24(8): 1157-1161.

DEHMESHKI J, AMIN H. Segmentation of pulmonary nodules in thoracic CT scans: a region growing approach [J]. IEEE Transactions on Medical Imaging, 2008, 27(4): 467-480.

杨润玲,高新波. 基于加权模糊c均值聚类的快速图像自动分割算法[J]. 中国图像图形学报,2007,12(12): 2105-2112.

YANG Runling, GAO Xinbo. A fast automatic image segmentation algorithm based on weighting fuzzy c-means clustering [J]. Journal of Image and Graphics, 2007, 12(12): 2105-2112.

SHIRAISHI J, LI Qiang, DOI K. Development of a computerized scheme for detection of very subtle lung nodules located in opaque areas on chest radiographs [EB/OL]. [2010-08-16]. http:∥spie.org/x648.html?product_id=652456.

束洲. 肺结节计算机辅助诊断算法研究[D]. 浙江:浙江大学理学院,2007.

KUPINSKI M A, CLARKSON E, HESTERMAN J Y. Bias in Hotelling observer performance computed from finite data [EB/OL]. [2010-08-16]. http:∥spie.org/x648.html? product_id=707800.

YAO Jie, BARRETT H H. Predicting human performance by a channelized Hotelling observer model [C]∥Proceedings of SPIE Conference in Mathematical Methods in Medical Imaging. San Diego, CA, USA: SPIE, 1992: 161-168.

PARK S, BARRETT H H, CLARKSON E, et al. Channelized-ideal observer using Laguerre-Gauss channels in detection tasks involving non-Gaussian distributed lumpy backgrounds and a Gaussian signal [J]. J Opt Soc Am: A, 2007, 24(12): 136-150.

一种多尺度X射线胸片图像增强算法. 西安交通大学学报,2010,44(6):83-87.

图像分割的谱聚类集成算法. 西安交通大学学报,2010,44(6):93-98.

利用粒子群优化的人脸特征提取识别算法. 西安交通大学学报,2010,44(4):48-51.

一维子空间的三维重建方法. 西安交通大学学报,2009,43(12):31-34.

人眼视觉特性与粗糙集结合的X射线图像增强算法. 西安交通大学学报,2009,43(6):48-51.

一种八叉树编码加速的3D纹理体绘制算法. 西安交通大学学报,2008,42(12):1490-1494.

一种医学X射线图像动态范围扩展方法. 西安交通大学学报,2008,42(12):1468-1471.

锥束X射线CT投影的蒙特卡罗仿真. 西安交通大学学报,2008,42(4):414-417.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Structure-Semantics-Residual Collaborative Image Compression Framework：Towards Privacy Protection and High-Fidelity Reconstruction

Integrated and Joint Design Optimization of Centrifugal Compressor Impeller and Casing Treatment at Multiple Working Points

Numerical Simulation of Heat-Moisture Barrier Performance of a Horizontal Air Curtain in Cold Storage

Effects of Steam Addition on the Swirl Combustion and Emission Characteristics of Cracked Ammonia

Effects of Expansion Angle Crater Film Hole on the Film Cooling Characteristics of a Double-Wall Structure

Related Author

No data

Related Institution

No data

⁰