摘要
高强度聚焦超声(HIFU)治疗肿瘤过程中,根据组织损伤程度调整HIFU治疗剂量非常重要.本文从信号处理的角度出发,提出基于超声散射回波能量和声衰减系数并结合BP神经网络监测生物组织损伤程度的方法.将高强度聚焦超声打击新鲜猪肉组织前后获得的散射回波通过A/D转换输入到计算机,对接收到的组织散射回波信号进行预处理,再从中提取出超声散射回波能量和声衰减系数参量信息,比较不同参量对损伤程度的辨识效果.实验结果表明:综合超声散射回波能量和声衰减系数特征并输入BP神经网络,相对于仅使用某种特征参数而言能更好地监测HIFU治疗中生物组织的损伤程度,尤其在组织损伤严重时优势更加明显.
In the process of High Intensity Focused Ultrasound（HIFU）treatment of tumor,it is very important to adjust HIFU treatment dosage according to the tissue damage degree.From the view of signal processing,a method using BP neural network was presented to check biological tissue damage degree based on the ultrasonic backscattered energy and attenuation coefficient.The scattering echo signal was detected before and after the fresh pork tissue was hit by HIFU,and the signal was inputted to the computer through A/D conversion.After some pretreatment to the signal,the echo energy and attenuation coefficient of the signal were analyzed.The effects of different parameters on the recognition of tissue damage degree were compared.The results showed that combining the ultrasonic backscattered energy with the attenuation coefficient to construct BP neural network can better monitor the biological tissue damage degree compared to use a single characteristic parameter,and it showed obvious advantages when the tissue is seriously damaged.
出处
《测试技术学报》
2014年第3期209-213,共5页
Journal of Test and Measurement Technology
基金
国家自然科学基金资助项目(No.11174077)
湖南省自然科学基金资助项目(No.11JJ3079)
湖南省教育厅资助科研项目(No.11C0844)
关键词
高强度聚焦超声
组织损伤
回波能量
声衰减系数
神经网络
High Intensity Focused Ultrasound（HIFU）
tissue damage
echo energy
attenuation coefficient
neural network
