摘要
为了探讨人工神经网络和图像纹理特征提取在肿瘤鉴别诊断中的应用;采用了收集病例资料并对其进行处理,以及提取相关医学图像纹理特征指标的方法;根据整理的病人相关临床检查指标、CT图像有特征性的指标、利用灰度共生矩阵提取的肿瘤CT图像纹理特征指标,得出了建立应用于肿瘤鉴别诊断的人工神经网络模型的结果;进一步得出结论:人工神经网络和图像纹理特征提取可以应用于肿瘤的鉴别诊断.
To explore the application of artificial neural network and impge texture feature extraction in tumor diagnosis, this paper uses case data collection and data processing, and extracts indexes of related medical image texture features. Based on the acquired patients＂ clinical examination indexes, distinctive inde- xes of CT image and indexes of CT image texture features extracted from gray level co-occurrence matrix, artificial neural network model is built to apply to tumor diagnosis. Further,it comes to the conclusion that artificial neural network and image textural features extraction can be used in diagnosis of tumor.
出处
《湖南工程学院学报（自然科学版）》
2013年第3期28-33,共6页
Journal of Hunan Institute of Engineering(Natural Science Edition)
关键词
人工神经网络
图像纹理特征
灰度共生矩阵
肿瘤
artificial neural network
image texture feature
gray level co-occurrence matrix
tumor
