一种基于上下文信息的乳腺肿块ROI检测方法

J4 ›› 2010, Vol. 45 ›› Issue (7): 70-75.

一种基于上下文信息的乳腺肿块ROI检测方法

郭乔进,丁轶,李宁

南京大学计算机科学与技术系计算机软件新技术国家重点实验室, 江苏南京 210093

收稿日期:2010-04-02 出版日期:2010-07-16 发布日期:2010-09-06
作者简介:郭乔进(1986-),男,博士研究生,研究方向为机器学习和模式识别.Emai:guoqiaojin@gmail.com
基金资助:
国家自然科学基金资助项目(60875011)

A context based method for ROI detection in digitized mammograms

GUO Qiao-jin, DING Yi, LI Ning

National Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing 210093, Jiangsu, China

Received:2010-04-02 Online:2010-07-16 Published:2010-09-06

摘要/Abstract

摘要：

传统的ROI(region of interest)检测方法忽略了图像中的上下文信息,为了解决这个问题,本文利用概率潜在语义分析(probability latent semantic analysis,PLSA)来对图像中的每块区域周围的图像特征进行分析,并利用其作为上下文特征来辅助ROI的检测。实验表明,该方法与直接进行分类相比,能够取得更好的分类效果。

关键词: 乳房X光检查;ROI检测;概率潜在语义分析

Abstract:

In order to solve the problem that context information was often missed in ROI (region of interest)detection. probability latent semantic analysis(PLSA) was employed to extract the context information from surrounding regions,and the context information was used as context features to aid ROI detection. Experimental results showed that the context information can effectively improve the accuracy of ROI detection.

Key words: mammogram; ROI-detection; probability latent semantic analysis

郭乔进,丁轶,李宁. 一种基于上下文信息的乳腺肿块ROI检测方法[J]. J4, 2010, 45(7): 70-75.

GUO Qiao-jin, DING Yi, LI Ning. A context based method for ROI detection in digitized mammograms[J]. J4, 2010, 45(7): 70-75.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed