Deep learning neural network estimation of tissue oxygenation based on diffuse optical spectroscopy

被引:5
|
作者
Kleshnin, Mikhail S. [1 ]
机构
[1] Russian Acad Sci, Inst Appl Phys, Nizhnii Novgorod, Russia
基金
俄罗斯基础研究基金会;
关键词
diffuse optical spectroscopy; tissue oxygenation; optimisation problem; neural network; NONINVASIVE DETERMINATION; T-TEST; REFLECTANCE; SCATTERING;
D O I
10.1088/1555-6611/ab2acc
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Diffuse optical spectroscopy (DOS) is an effective technique for diagnosing the component composition of biological tissues. It is based on the analysis of optical radiation transmitted through the tissue at different wavelengths. Tissues are optically inhomogeneous media, so real spectroscopic measurements contain random and systematic errors, and the DOS inverse problem is ill-conditioned, therefore traditional optimization techniques for reconstructing the optical characteristics of the investigated object have a rather high error rate. In this paper we have proposed a predictive method for calculating the tissue oxygenation, based on a deep direct neural network for solving the DOS error problem. The proposed neural network consists of 6 layers and has 141987 parameters. 214220 simulated spectroscopic measurements for various component compositions of tissue were used to train the neural network. Statistical analysis of the calculating accuracy for tissue oxygenation has showed a significant advantage of the developed technique over the traditional optimization approach to solving the DOS problem.
引用
收藏
页数:5
相关论文
共 50 条
  • [11] Deep Learning Based Image Reconstruction for Diffuse Optical Tomography
    Ben Yedder, Hanene
    BenTaieb, Aicha
    Shokoufi, Majid
    Zahiremami, Amir
    Golnaraghi, Farid
    Hamarneh, Ghassan
    MACHINE LEARNING FOR MEDICAL IMAGE RECONSTRUCTION, MLMIR 2018, 2018, 11074 : 112 - 119
  • [12] Phase function estimation from a diffuse optical image via deep learning
    Liang, Yuxuan
    Niu, Chuang
    Wei, Chen
    Ren, Shenghan
    Cong, Wenxiang
    Wang, Ge
    PHYSICS IN MEDICINE AND BIOLOGY, 2022, 67 (07):
  • [13] Deep Learning Diffuse Optical Tomography
    Yoo, Jaejun
    Sabir, Sohail
    Heo, Duchang
    Kim, Kee Hyun
    Wahab, Abdul
    Choi, Yoonseok
    Lee, Seul-, I
    Chae, Eun Young
    Kim, Hak Hee
    Bae, Young Min
    Choi, Young-Wook
    Cho, Seungryong
    Ye, Jong Chul
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2020, 39 (04) : 877 - 887
  • [14] Portable optical tissue flow oximeter based on diffuse correlation spectroscopy
    Shang, Yu
    Zhao, Youquan
    Cheng, Ran
    Dong, Lixin
    Irwin, Daniel
    Yu, Guoqiang
    OPTICS LETTERS, 2009, 34 (22) : 3556 - 3558
  • [15] Near-infrared Diffuse Optical Spectroscopies for Measurement of Deep Tissue Blood Flow, Oxygenation and Metabolism
    Yu, Guoqiang
    Shang, Yu
    2011 FUTURE OF INSTRUMENTATION INTERNATIONAL WORKSHOP (FIIW), 2011,
  • [16] Neural network-based inverse model for diffuse reflectance spectroscopy
    Lan, Qing
    Mcclarren, Ryan G.
    Vishwanath, Karthik
    BIOMEDICAL OPTICS EXPRESS, 2023, 14 (09) : 4725 - 4738
  • [17] Physics-guided neural network for tissue optical properties estimation
    Chong, Kian Chee
    Pramanik, Manojit
    BIOMEDICAL OPTICS EXPRESS, 2023, 14 (06) : 2576 - 2590
  • [18] Convolutional Neural Network-based Deep Learning for Intelligent OSNR Estimation on Eye Diagrams
    Wang, Danshi
    Zhang, Min
    Li, Ze
    Li, Jin
    Song, Chuang
    Li, Jianqiang
    Wang, Mengyuan
    43RD EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION (ECOC 2017), 2017,
  • [19] Transfer learning in deep neural network-based receiver coil sensitivity map estimation
    Madiha Arshad
    Mahmood Qureshi
    Omair Inam
    Hammad Omer
    Magnetic Resonance Materials in Physics, Biology and Medicine, 2021, 34 : 717 - 728
  • [20] Transfer learning in deep neural network-based receiver coil sensitivity map estimation
    Arshad, Madiha
    Qureshi, Mahmood
    Inam, Omair
    Omer, Hammad
    MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE, 2021, 34 (05) : 717 - 728