|
|||||
|
|
| 基于B超图像多重分形谱的脂肪肝严重程度识别 | |
| 引用本文： | 张建炜,汪天富,殷杰,查晓霞,罗燕.基于B超图像多重分形谱的脂肪肝严重程度识别[J].中国医学影像技术,2009,25(7):1289-1292. |
| 作者姓名： | 张建炜 汪天富 殷杰 查晓霞 罗燕 |
| 作者单位： | 1. 成都医学院医学物理教研室,四川,成都,610083 2. 深圳大学信息工程学院,广东,深圳,518060 3. 四川理工学院生物医学工程教研室,四川,自贡,643000 4. 成都医学院第一附属医院超声科,四川,成都,610500 5. 四川大学华西医院超声科,四川,成都,610041 |
| 摘 要： | 目的 采用多重分形谱纹理分析法以及模式识别技术,建立一种识别正常肝脏和不同程度脂肪肝B超图像的计算机辅助诊断方法.方法 通过提取每幅B超图像多重分形谱曲线的奇异标度差和多重谱面积两个特征量,再结合近远场灰度比特征量,组成三维特征矢量输入BP人工神经网络进行分类识别.结果 正常肝脏正确识别率96.00%,轻度脂肪肝识别率80.00%,中度脂肪肝识别率88.00%,重度脂肪肝识别率92.00%.结论 特征矢量结合BP网络的识别方法在B超图像上能较好地识别肝脏脂肪化程度,可作为一种辅助诊断方法. |
| 关 键 词： | 超声检查 脂肪肝 多重分形谱法 计算机辅助诊断 人工神经网络 |
| 收稿时间： | 1/3/2009 12:00:00 AM |
| 修稿时间： | 2009/3/23 0:00:00 |
Recognition of liver steatosis degree based on multi-fractal spectrum of type-B ultrasonic image |
|
| ZHANG Jian-wei,WANG Tian-fu,YIN Jie,ZHA Xiao-xia and LUO Yan.Recognition of liver steatosis degree based on multi-fractal spectrum of type-B ultrasonic image[J].Chinese Journal of Medical Imaging Technology,2009,25(7):1289-1292. | |
| Authors: | ZHANG Jian-wei WANG Tian-fu YIN Jie ZHA Xiao-xia and LUO Yan |
| Institution: | Department of Medical Physics, Chengdu Medical College, Chengdu 610083, China;Information Engineering College, Shenzhen University, Shenzhen 518060, China;Department of Biomedical Engineering, Sichuan Science & Engineering College, Zigong 643000, China;Department of Ultrasound, First Hospital of Chengdu Medical College, Chengdu 610500, China;Department of Ultrasound,West China Hospital of Sichuan University, Chengdu 610041, China |
| Abstract: | Objective To develop a recognition method of liver steatosis degree on type-B ultrasonic images based on multi-fractal spectrum texture analysis method and pattern recognition. Methods Features of singularity strength width and multi-spectrum area were extracted from the curve of multi-fractal spectrum of each liver ultrasonic images. These two features and the feature of mean intensity ratio comprised a three-dimensional feature vector, which would be classified by BP neural network. Results The classification accuracy was 96.00% for normal liver, 80.00% for mild fatty liver, 88.00% for moderate fatty liver and 92.00% for severe fatty liver. Conclusion Feature vector combined with BP neural network can identify the steatosis degree of liver on the ultrasonic images and can be used as an assistant diagnostic method. |
| Keywords: | Ultrasonography Fatty liver Multi-fractal spectrum Computer-aided diagnosis Artificial neural network |
| 本文献已被 万方数据 等数据库收录！ | |
| 点击此处可从《中国医学影像技术》浏览原始摘要信息 | |
| 点击此处可从《中国医学影像技术》下载免费的PDF全文 | |