摘要
目的:探讨基于神经网络的31PMR波谱在辨别肝细胞癌,正常肝和肝硬化中的价值。方法:运用自组织特征映射神经网络(SOM)分析66个31PMRS数据,其中包括肝细胞癌(13个样本),正常肝脏(16个样本)和肝硬化(37个样本)。结果:31PMRS可以用于肝细胞癌与肝硬化结节的诊断和鉴别诊断,经四个实验证明,基于神经网络模型的31PMR波谱数据分析可以将肝细胞癌的诊断正确率从85.4%提高到92.31%。结论:基于神经网络模型的31PMRS波谱数据分析为活体肝细胞癌的诊断提供了一种有价值的诊断手段。
Objective：To investigate the ^31 p MR spectroscopy based on neural networks so as to distinguish hepatocellular carcinoma,normal liver and cirrhosis in value.Methods：Using self-organlzing map neural network （SOM）, we analysed 66 data of^31P MRS, including hepatocellular carcinoma （13 samples）, normal liver （16 samples） and liver cirrhosis （37 samples）. Results：alP MRS can be used to diagnose and distinguish hepatocellular carcinoma and liver cirrhosis nodules. The four experiments showed that neural network model based on the ^31 p MR spectroscopy data analysis may be increased diagnostic accuracy rate of hepatooellular carcinoma from 85.4% to 92.31%. Conclusion： ^31p MRS data analysis based on neural network model provides a valuable diagnostic tool of hepatooellular carcinoma in vivo.
出处
《医学影像学杂志》
2009年第7期860-863,共4页
Journal of Medical Imaging
基金
山东省自然科学基金项目资助
项目编号Y2006C96
关键词
磷-31
磁共振波谱
肝细胞癌
神经网络
31-P hosphorus
Magnetic resonance spectroscopy
Hepatocellular carcinoma
Neural network
