| 王娇,罗燕,李德玉,林江莉,汪天富,彭玉兰.B超图像复杂性特征分析方法诊断脂肪肝[J].中国医学影像技术,2006,22(1):135~138 |
| B超图像复杂性特征分析方法诊断脂肪肝 |
| Fatty liver diagnosed by B-mode ultrasonography based on the complexity analysis |
| 投稿时间：2005-07-28 修订日期：2005-10-31 |
| DOI： |
| 中文关键词: 脂肪肝 复杂性分析 图像识别 反向传播人工神经网络 |
| 英文关键词:Fatty liver Complexity analysis Image recognition Back-propagation artificial neural network |
| 基金项目: |
|
| 摘要点击次数: 2668 |
| 全文下载次数: 72 |
| 中文摘要: |
| 目的 利用复杂性分析研究脂肪肝患者B 超图像纹理改变,进而诊断脂肪肝。方法 通过分析正常肝脏与脂肪肝B 超图像的复杂度,近似熵和近远场灰度比特征,组成特征矢量,利用反向传播人工神经网络对脂肪肝进行计算机辅助诊断。结果 用80 例样本建立识别模型,用50 例样本进行验证,对正常肝的识别率达到100 % ,脂肪肝识别率达到100 %。结论 复杂性分析能较好地描述脂肪肝超声图像的特征,对脂肪肝的识别有着较好的性能。 |
| 英文摘要: |
| Objective To diagnose fatty liver by analyzing the complexity of B2mode ult rasonic images. Methods The complexity , approximate ent ropy and mean intensity ratio of images were studied. Feature vector of each liver image were created with the three features. Then use back2propagation artificial neural network to classify these vectors. Results The accuracy rates were 100 % for normal liver and 100 % for fatty liver. Conclusion Complexity analysis could indicate the tex-ture feature of B2mode ult rasonic images of normal liver and fatty liver successfully and it could improve the diagnosis of fatty liver. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
