CAJ | 학술논문

本文针对海量医学影像信息的计算机辅助诊断技术中特征提取的难题,以脑CT图像为研究对象,提出了一种基于小波分解的纹理特征提取方法.首先通过对预处理后的子图像分别进行的分层处理与分层提取,构成纹理特征向量;然后采用创建数字化统计图谱的方法,对实验数据集进行了计算机辅助诊断实验.实验结果表明此方法可以标记出可能存在病变的区域,为医师的诊断提供辅助信息.
본문침대해량의학영상신식적계산궤보조진단기술중특정제취적난제,이뇌CT도상위연구대상,제출료일충기우소파분해적문리특정제취방법.수선통과대예처리후적자도상분별진행적분층처리여분층제취,구성문리특정향량;연후채용창건수자화통계도보적방법,대실험수거집진행료계산궤보조진단실험.실험결과표명차방법가이표기출가능존재병변적구역,위의사적진단제공보조신식.
In this paper we propose and validate a method for feature extraction of brain CT images,which is a difficult problem in CAD technology for mass medical imaging information.Firstly,the preprocessed sub-images were divided into different layers to construct texture feature vectors.Secondly,CAD experiment was performed by constructing digital statistical atlas.Experiment results show that the method could mark the region where pathological changes may exist and provide information to physicians.