Study on the inverse problem of diffuse optical tomography based on improved stacked auto-encoder_Journal of Biomedical Engineering

Authors：

TIAN Wenxu ^1,2 ,  YANG Dan ^1,2,3 , WEI Zhulin ^1,3 , WANG Jiao ¹

1. School of Information Science & Engineering, Northeastern University, Shenyang 110819, P.R.China;
2. Key Laboratory of Infrared Optoelectric Materials and Micro-Nano Devices, Shenyang 110819, P.R.China;
3. Key Laboratory of Data Analytics and Optimization for Smart Industry, Northeastern University, Shenyang 110819, P.R.China;

Corresponding author：

YANG Dan, Email: yangdan@mail.neu.edu.cn

Keywords：

diffuse optical tomography; machine learning; stacked autoencoder; inverse problem

DOI：

10.7507/1001-5515.202010041

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The inverse problem of diffuse optical tomography (DOT) is ill-posed. Traditional method cannot achieve high imaging accuracy and the calculation process is time-consuming, which restricts the clinical application of DOT. Therefore, a method based on stacked auto-encoder (SAE) was proposed and used for the DOT inverse problem. Firstly, a traditional SAE method is used to solved the inverse problem. Then, the output structure of SAE neural network is improved to a single output SAE, which reduce the burden on the neural network. Finally, the improved SAE method is used to compare with traditional SAE method and traditional levenberg-marquardt (LM) iterative method. The result shows that the average time to solve the inverse problem of the method proposed in this paper is only 1.67% of the LM method. The mean square error (MSE) value is 46.21% lower than the traditional iterative method, 61.53% lower than the traditional SAE method, and the image correlation coefficient(ICC) value is 4.03% higher than the traditional iterative method, 18.7% higher than the traditional SAE method and has good noise immunity under 3% noise conditions. The research results in this article prove that the improved SAE method has higher image quality and noise resistance than the traditional SAE method, and at the same time has a faster calculation speed than the traditional iterative method, which is conducive to the application of neural networks in DOT inverse problem calculation.

Citation： TIAN Wenxu, YANG Dan, WEI Zhulin, WANG Jiao. Study on the inverse problem of diffuse optical tomography based on improved stacked auto-encoder. Journal of Biomedical Engineering, 2021, 38(4): 774-782. doi: 10.7507/1001-5515.202010041 Copy

1.	Uddin K S, Zhang M, Anastasio M, et al. Optimal breast cancer diagnostic strategy using combined ultrasound and diffuse optical tomography. Biomed Opt Express, 2020, 11(5): 2722-2737.
2.	Hernandez-Martin E, Gonzalez-Mora J L. Diffuse optical tomography using bayesian filtering in the human brain. Applied Sciences, 2020, 10(10): 3399.
3.	李玉, 熊馨, 李昭阳, 等. 基于功能性近红外光谱识别右脚三种想象动作研究. 生物医学工程学杂志, 2020, 37(2): 262-270.
4.	Boas D A, Brooks D H, Miller E L, et al. Imaging the body with diffuse optical tomography. IEEE Signal Process Mag, 2001, 18(6): 57-75.
5.	Arridge S R, Schweiger M. Inverse methods for optical tomography//Biennial International Conference on Information Processing in Medical Imaging. Heidelberg: Springer Berlin, 1993: 259-277.
6.	Arridge S R. Photon-measurement density functions. part I: analytical forms. Appl Opt, 1995, 34(31): 7395-7409.
7.	佟珊珊. 基于稳态辐射传输方程的扩散光学层析成像的方法研究. 哈尔滨: 哈尔滨工业大学, 2018.
8.	唐锦萍. 基于辐射传输方程的扩散光学层析成像理论与算法研究. 哈尔滨: 哈尔滨工业大学, 2016.
9.	Vidal-Rosas E E, Billings S A, Zheng Y, et al. Reduced-order modeling of light transport in tissue for real-time monitoring of brain hemodynamics using diffuse optical tomography. J Biomed Opt, 2014, 19(2): 026008.
10.	Vidal-Rosas E E, Billings S A, Zheng Ying, et al. Real-time diffuse optical tomography using reduced-order light propagation models//Proceedings of the 8th IASTED International Conference on Biomedical Engineering. Biomed, 2011: 378-385.
11.	Feng J, Sun Q, Li Z, et al. Back-propagation neural network-based reconstruction algorithm for diffuse optical tomography. J Biomed Opt, 2018, 24(5): 051407.
12.	Yoo J, Sabir S, Heo D, et al. Deep learning diffuse optical tomography. IEEE Trans Med Imaging, 2020, 39(4): 877-887.
13.	Yedder H B, BenTaieb A, Shokoufi M, et al. Deep learning based image reconstruction for diffuse optical tomography//International Workshop on Machine Learning for Medical Image Reconstruction. Springer Cham, 2018: 112-119.
14.	Li W, Fu H, Yu L, et al. Stacked autoencoder-based deep learning for remote-sensing image classification: a case study of African land-cover mapping. Int J Remote Sens, 2016, 37(23): 5632-5646.
15.	Li Sheng, Kawale J, Fu Yun. Deep collaborative filtering via marginalized denoising auto-encoder//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. New York: Association for Computing Machinery, 2015: 811-820.
16.	戴逸翔, 王雪, 戴鹏, 等. 面向可穿戴多模生物信息传感网络的栈式自编码器优化情绪识别. 计算机学报, 2017, 40(8): 1750-1763.
17.	Jermyn M, Ghadyani H, Mastanduno M A, et al. Fast segmentation and high-quality three-dimensional volume mesh creation from medical images for diffuse optical tomography. J Biomed Opt, 2013, 18(8): 86007.
18.	Dehghani H, Eames M E, Yalavarthy P K, et al. Near infrared optical tomography using NIRFAST: algorithm for numerical model and image reconstruction. Commun Numer Methods Eng, 2009, 25(6): 711-732.
19.	马小雅. 扩散光学层析成像系统优化及其与PET融合成像的研究. 西安: 西安电子科技大学, 2019.

1. Uddin K S, Zhang M, Anastasio M, et al. Optimal breast cancer diagnostic strategy using combined ultrasound and diffuse optical tomography. Biomed Opt Express, 2020, 11(5): 2722-2737.
2. Hernandez-Martin E, Gonzalez-Mora J L. Diffuse optical tomography using bayesian filtering in the human brain. Applied Sciences, 2020, 10(10): 3399.
3. 李玉, 熊馨, 李昭阳, 等. 基于功能性近红外光谱识别右脚三种想象动作研究. 生物医学工程学杂志, 2020, 37(2): 262-270.
4. Boas D A, Brooks D H, Miller E L, et al. Imaging the body with diffuse optical tomography. IEEE Signal Process Mag, 2001, 18(6): 57-75.
5. Arridge S R, Schweiger M. Inverse methods for optical tomography//Biennial International Conference on Information Processing in Medical Imaging. Heidelberg: Springer Berlin, 1993: 259-277.
6. Arridge S R. Photon-measurement density functions. part I: analytical forms. Appl Opt, 1995, 34(31): 7395-7409.
7. 佟珊珊. 基于稳态辐射传输方程的扩散光学层析成像的方法研究. 哈尔滨: 哈尔滨工业大学, 2018.
8. 唐锦萍. 基于辐射传输方程的扩散光学层析成像理论与算法研究. 哈尔滨: 哈尔滨工业大学, 2016.
9. Vidal-Rosas E E, Billings S A, Zheng Y, et al. Reduced-order modeling of light transport in tissue for real-time monitoring of brain hemodynamics using diffuse optical tomography. J Biomed Opt, 2014, 19(2): 026008.
10. Vidal-Rosas E E, Billings S A, Zheng Ying, et al. Real-time diffuse optical tomography using reduced-order light propagation models//Proceedings of the 8th IASTED International Conference on Biomedical Engineering. Biomed, 2011: 378-385.
11. Feng J, Sun Q, Li Z, et al. Back-propagation neural network-based reconstruction algorithm for diffuse optical tomography. J Biomed Opt, 2018, 24(5): 051407.
12. Yoo J, Sabir S, Heo D, et al. Deep learning diffuse optical tomography. IEEE Trans Med Imaging, 2020, 39(4): 877-887.
13. Yedder H B, BenTaieb A, Shokoufi M, et al. Deep learning based image reconstruction for diffuse optical tomography//International Workshop on Machine Learning for Medical Image Reconstruction. Springer Cham, 2018: 112-119.
14. Li W, Fu H, Yu L, et al. Stacked autoencoder-based deep learning for remote-sensing image classification: a case study of African land-cover mapping. Int J Remote Sens, 2016, 37(23): 5632-5646.
15. Li Sheng, Kawale J, Fu Yun. Deep collaborative filtering via marginalized denoising auto-encoder//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. New York: Association for Computing Machinery, 2015: 811-820.
16. 戴逸翔, 王雪, 戴鹏, 等. 面向可穿戴多模生物信息传感网络的栈式自编码器优化情绪识别. 计算机学报, 2017, 40(8): 1750-1763.
17. Jermyn M, Ghadyani H, Mastanduno M A, et al. Fast segmentation and high-quality three-dimensional volume mesh creation from medical images for diffuse optical tomography. J Biomed Opt, 2013, 18(8): 86007.
18. Dehghani H, Eames M E, Yalavarthy P K, et al. Near infrared optical tomography using NIRFAST: algorithm for numerical model and image reconstruction. Commun Numer Methods Eng, 2009, 25(6): 711-732.
19. 马小雅. 扩散光学层析成像系统优化及其与PET融合成像的研究. 西安: 西安电子科技大学, 2019.

Journal of Biomedical Engineering

Study on the inverse problem of diffuse optical tomography based on improved stacked auto-encoder

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content