基于并行BP神经网络的近红外光断层图像重建方法基础研究

J4 ›› 2009, Vol. 26 ›› Issue (3): 272-277.

基于并行BP神经网络的近红外光断层图像重建方法基础研究

李婷钱志余李韪韬汤飞飞

南京航空航天大学生物医学工程南京 210016

收稿日期:2008-05-30 修回日期:2008-07-31 出版日期:2009-05-28 发布日期:2009-05-07
通讯作者: 钱志余，教授，博导。 E-mail:zhiyu@nuaa.edu.cn
作者简介:李婷（1987－），江西人，研究方向为基于神经网络的光学CT图像重建技术。
基金资助:
国家自然科学基金资助项目（30671997）

An image reconstruction approach for near-infrared optical tomography based on parallel BP neural network

LI Ting, QIAN Zhi-Tu, LI Wei-Tao, TANG Fei-Fei

Department of Biomedical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Received:2008-05-30 Revised:2008-07-31 Published:2009-05-28 Online:2009-05-07

摘要/Abstract

摘要：

提出一种基于并行BP神经网络的NIR OT (Near-infrared Optical Tomography)图像重建算法，利用BP神经网络来表征生物组织内部光学参数的空间分布和边界光强之间的非线性映射关系。该方法将一个复杂的模型分解成简单的模型分别建立并行的神经网络。利用Femlab软件完成基于有限元的稳态扩散方程的两个简单模型的正向问题求解，根据提出的平均优化散射系数和正向问题训练的大量数据集合，建立并训练并行神经网络，通过对两个网络结果的分析，实现快速获得更复杂模型的光学参数的重构。算法能够快速识别特异组织的位置和准确反映热疗过程中生物组织的优化散射系数的变化趋势。

关键词: NIR OT, 逆向问题, 并行BP神经网络, 双支路, 平均光学参数, 快速重建

Abstract:

An image reconstruction approach for near-infrared optical tomography (NIR OT) based on a parallel neural network is presented. The parallel BP neural network is used to distinguish the nonlinear relationship between the spatial location of tumor and light intensity around the boundary of tissue. The method turns a complicated model into two simpler ones to build two parallel BP neural networks. The steady state diffusion equation of the two simple models is solved by Femlab software. The inverse problem is solved as optimization problem by Levenberg-Marquardt algorithm. The concept of the average optical coefficient is proposed, which is helpful to understand the distribution of the scattering photon from tumor. The reconstructive can be got by the trained network. The proposed algorithm realized the fast reconstruction of tissue optical properties and provided reconstruction of OT with a new method.

Key words: NIR OT, inverse problem, parallel BP neural network, double branches, average optical parameters, fast reconstruction

中图分类号:

O242.2

李婷钱志余李韪韬汤飞飞. 基于并行BP神经网络的近红外光断层图像重建方法基础研究[J]. J4, 2009, 26(3): 272-277.

LI Ting, QIAN Zhi-Tu, LI Wei-Tao, TANG Fei-Fei. An image reconstruction approach for near-infrared optical tomography based on parallel BP neural network[J]. J4, 2009, 26(3): 272-277.

参考文献

[1] Feng Gao, Huijuan Zhao, Hanbei Niu, et al. Review of Optical Imaging in Medicine I- Direct Method. Laser & Optoelectronics Progress[J]. 1999，10（1）：7～11 [高峰，赵会娟，牛憨笨等，光学医学成像实验技术综述——间接成像法，激光与光电子学进展[J]，1999，10（1）：7～11]
[2] Boas D A, Brooks D H, Miller E L, et al. Imaging the body with diffuse optical tomography. IEEE Signal Proc Mag [J], 2001, 186: 57-75.
[3] Arridge S R. Optical tomography in medical imaging: modeling and reconstruction [J], 1999, 15(2): R41-R93. [4] Huabei Jiang,Yong Xu, Nicusor Iftimia, et al. Three-Diminsional Optical Tomographic Imaging of Breast in a Human Subject. IEEE Transaction on Medical Imaging [J], 2001; 20(12):1334
[5] Joseph P. Culver, Andrew M. Siegel, Jonathan J. Stott, et al. Volumetric diffuse optical tomography of brain activity. Optics Letters [J],2003;28(21):2061
[6] Klose A D, Hielscher A H. Optical tomography using the time-independent equation of radiative transfer—Part 2: inverse model. JQSRT [J] 2002; 72: 715–32
[7] Arridge S R, Schweiger M. A gradient-based optimization scheme for optical tomography. Opt Express[J] 1998;2:213–26.
[8] Jing Meng Jiajun Wang, Xianwu Huang Renjin Liu. Optical tomography reconstruction based on gradient tree: Journal of Quantitative Spectroscopy & Radiative Transfer [J] 102 (2006) 181–189.
[9] Weitao Li, Zhiyu Qian, Huinan Wang. Image Reconstruction Algorithm of Near Infrared Optical Tomography. Chinese Optical Letters Supplement [Proc], 2005, 3: 237-238.
[10] Schweiger M, Arridge S R, Hiraoka M, et al. The finite element method for the propagation of light in scattering media: Boundary and source conditions[J]. Applied Phys, 1995, 22(11):1779-1792.
[11] Qiong Wu, Zhiyu Qian, Yueqing Gu. A New Image Reconstruction Approach to Optical Computed Tomography Based on BP Neural Network. 27th International Congress on High-Speed Photography and Photonics. SPIE.Xi an,China.September 17th~22nd,2006.
[12] Minqing Jing, Xiaoli Zhang. Research on Fault Diagnosis of Diesel Engine Based on ART-BP Neural Network: Mechanical Science and Technology[J]. April,2007:412-416; [景敏卿，张晓丽，基于ART—并行BP神经网络的柴油机故障诊断研究.机械科学与技术[J].2007年第26卷第4期412-416.]
[13] Weitao Li ，Zhiyu Qian, The Research on the Relationship Between the Reduced Scattering Coefficient and Temperature of the Tissue by NIRS Light Scattering. International Symposium on Biophotonics, Nanophotonics and Metamaterials, 2006,10, 16-18.