scholarly journals Machine learning estimation of tissue optical properties

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Brett H. Hokr ◽  
Joel N. Bixler
Keyword(s):  
Neural Network ◽  
Optical Properties ◽  
Biological Tissues ◽  
Homogeneous Layer ◽  
In Vivo Measurement ◽  
Tissue Optical Properties ◽  
The Neural Network ◽  
Spatio Temporal ◽  
Fully Connected

AbstractDynamic, in vivo measurement of the optical properties of biological tissues is still an elusive and critically important problem. Here we develop a technique for inverting a Monte Carlo simulation to extract tissue optical properties from the statistical moments of the spatio-temporal response of the tissue by training a 5-layer fully connected neural network. We demonstrate the accuracy of the method across a very wide parameter space on a single homogeneous layer tissue model and demonstrate that the method is insensitive to parameter selection of the neural network model itself. Finally, we propose an experimental setup capable of measuring the required information in real time in an in vivo environment and demonstrate proof-of-concept level experimental results.

Measurement of the Optical Properties of Muscle Tissue In Vivo

2000 ◽  
Author(s):  
P. L. Kopsombut ◽  
D. Willis ◽  
A. E. Schen ◽  
L. X. Xu ◽  
X. Xu
Keyword(s):  
Optical Properties ◽  
Transport Theory ◽  
Rapid Development ◽  
Ccd Camera ◽  
High Sensitivity ◽  
Biological Tissues ◽  
In Vivo Measurement ◽  
Living Tissues

Abstract Along with rapid development of diagnostic and therapeutic applications of lasers in medicine, optical properties of various biological tissues have been extensively studied [1]. Most of the studies were performed in vitro owing to the complexity involved in in vivo measurement. To date, it is well understood that living tissue is an absorbing and scattering heterogeneous medium because of its complex structures including blood network. The transport theory cannot be readily used due to the heterogeneity and the absence of the optical properties of living tissues [2]. In this research, we have developed a procedure for measuring the total attenuation coefficient (μ1) of the exteriorized rat 2-D spinotrapezius muscle in the wavelength ranged from 480–560 nm using the collimated light from a Nitrogen-pumped dye laser and a high-sensitivity CCD camera.

Charge-coupled device and neural-network-based instrument for the noninvasive determination of tissue optical properties in vivo

1994 ◽  
Author(s):  
Thomas J. Farrell ◽  
Michael S. Patterson ◽  
Joseph E. Hayward ◽  
Brian C. Wilson ◽  
Elsa R. Beck
Keyword(s):  
Neural Network ◽  
Optical Properties ◽  
Charge Coupled Device ◽  
Tissue Optical Properties

Estimation of Site Amplification from Geotechnical Array Data Using Neural Networks

2021 ◽  
Author(s):  
Daniel Roten ◽  
Kim B. Olsen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Site Response ◽  
Site Amplification ◽  
Data Driven ◽  
Vertical Array ◽  
The Neural Network ◽  
Simplifying Assumptions ◽  
The Mean ◽  
Fully Connected

ABSTRACT We use deep learning to predict surface-to-borehole Fourier amplification functions (AFs) from discretized shear-wave velocity profiles. Specifically, we train a fully connected neural network and a convolutional neural network using mean AFs observed at ∼600 KiK-net vertical array sites. Compared with predictions based on theoretical SH 1D amplifications, the neural network (NN) results in up to 50% reduction of the mean squared log error between predictions and observations at sites not used for training. In the future, NNs may lead to a purely data-driven prediction of site response that is independent of proxies or simplifying assumptions.

scholarly journals A THREE-PHASE INDUCTIVE SENSOR FOR IN VIVO MEASUREMENT OF ELECTRICAL ANISOTROPY OF BIOLOGICAL TISSUES

2014 ◽  
Vol 5 (1) ◽  
Author(s):  
Yukio Kosugi ◽  
Tadashi Takemae ◽  
Hiroki Takeshima ◽  
Atsushi Kudo ◽  
Kazuyuki Kojima ◽  
...  
Keyword(s):  
Magnetic Field ◽  
Electrical Conductivity ◽  
High Frequency ◽  
Reference Signal ◽  
Biological Tissues ◽  
Electrical Anisotropy ◽  
Conductivity Anisotropy ◽  
In Vivo Measurement ◽  
Surgical Operations

Biological tissue will have anisotropy in electrical conductivity, due to the orientation of muscular fibers or neural axons as well as the distribution of large size blood vessels. Thus, the in vivo measurement of electrical conductivity anisotropy can be used to detect deep-seated vessels in large organs such as the liver during surgeries. For diagnostic applications, decrease of anisotropy may indicate the existence of cancer in anisotropic tissues such as the white matter of the brain or the mammary gland in the breast. In this paper, we will introduce a new tri-phase induction method to drive rotating high-frequency electrical current in the tissue for the measurement of electrical conductivity anisotropy. In the measurement, three electromagnets are symmetrically placed on the tissue surface and driven by high-frequency alternative currents of 0 kHz, modulated with 1 kHz 3-phase signals. In the center area of three magnets, magnetic fields are superimposed to produce a rotating induction current. This current produces electrical potentials among circularly arranged electrodes to be used to find the conductivity in each direction determined by the electrode pairs. To find the horizontal and vertical signal components, the measured potentials are amplified by a 2ch lock-in amplifier phase-locked with the 1 kHz reference signal. The superimposed current in the tissue was typically 45 micro Amperes when we applied 150 micro Tesla of magnetic field. We showed the validity of our method by conducting in vitro measurements with respect to artificially formed anisotropic materials and preliminary in vivo measurements on the pig’s liver. Compared to diffusion tensor MRI method, our anisotropy sensor is compact and advantageous for use during surgical operations because our method does not require strong magnetic field that may disturb ongoing surgical operations.

A fiber optic approach for in vivo minimally invasive study of tissue optical properties

2004 ◽  
Author(s):  
Ilko K. Ilev ◽  
Ronald W. Waynant ◽  
Kimberly R. Byrnes ◽  
Juanita Anders
Keyword(s):  
Optical Properties ◽  
Minimally Invasive ◽  
Fiber Optic ◽  
Tissue Optical Properties

scholarly journals In-vivo tissue optical properties derived by linear perturbation theory for edge-corrected time-domain mammograms

2005 ◽  
Vol 13 (21) ◽  
pp. 8571 ◽  
Author(s):  
B. Wassermann ◽  
A. Kummrow ◽  
K. T. Moesta ◽  
D. Grosenick ◽  
J. Mucke ◽  
...  
Keyword(s):  
Optical Properties ◽  
Perturbation Theory ◽  
Time Domain ◽  
Linear Perturbation ◽  
Tissue Optical Properties ◽  
Linear Perturbation Theory

scholarly journals Optical investigation of bovine grey and white matters in visible and near-infrared ranges

2021 ◽  
Vol 27 (1) ◽  
pp. 99-107
Author(s):  
Ali Shahin ◽  
Wesam Bachir ◽  
Moustafa Sayem El-Daher
Keyword(s):  
Optical Properties ◽  
Absorption Coefficient ◽  
Wavelength Range ◽  
Grey Matter ◽  
Near Infrared ◽  
Biological Tissues ◽  
Integrating Sphere ◽  
Visible Range ◽  
Optical Investigation

Abstract Introduction: Due to enormous interests for laser in medicine and biology, optical properties characterization of different tissue have be affecting in development processes. In addition, the optical properties of biological tissues could be influenced by storage methods. Thus, optical properties of bovine white and grey tissues preserved by formalin have been characterized over a wide wavelength spectrum varied between 440 nm and 1000 nm. Materials and Methods: To that end, a single integrating sphere system was assembled for spectroscopic characterization and an inverse adding-doubling algorithm was used to retrieve optical coefficients, i.e. reduced scattering and absorption coefficients. Results: White matter has shown a strong scattering property in comparison to grey matter. On the other hand, the grey matter has absorbed light extensively. In comparison, the reduced scattering profile for both tissue types turned out to be consistent with prior works that characterized optical coefficients in vivo. On the contrary, absorption coefficient behavior has a different feature. Conclusion: Formalin could change the tissue’s optical properties because of the alteration of tissue’s structure and components. The absence of hemoglobin that seeps out due to the use of a formalin could reduce the absorption coefficient over the visible range. Both the water replacement by formalin could reduce the refractive index of a stored tissue and the absence of hemoglobin that scatters light over the presented wavelength range should diminish the reduced scattering coefficients over that wavelength range.

scholarly journals ForkDec: Accurate Detection for Selfish Mining Attacks

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Zhaojie Wang ◽  
Qingzhe Lv ◽  
Zhaobo Lu ◽  
Yilei Wang ◽  
Shengjie Yue
Keyword(s):  
Neural Network ◽  
Incentive Mechanism ◽  
Attack Detection ◽  
Detection Accuracy ◽  
Data Set ◽  
Incentive Compatible ◽  
The Neural Network ◽  
Security Challenges ◽  
Excellent Research ◽  
Fully Connected

Incentive mechanism is the key to the success of the Bitcoin system as a permissionless blockchain. It encourages participants to contribute their computing resources to ensure the correctness and consistency of user transaction records. Selfish mining attacks, however, prove that Bitcoin’s incentive mechanism is not incentive-compatible, which is contrary to traditional views. Selfish mining attacks may cause the loss of mining power, especially those of honest participants, which brings great security challenges to the Bitcoin system. Although there are a series of studies against selfish mining behaviors, these works have certain limitations: either the existing protocol needs to be modified or the detection effect for attacks is not satisfactory. We propose the ForkDec, a high-accuracy system for selfish mining detection based on the fully connected neural network, for the purpose of effectively deterring selfish attackers. The neural network contains a total of 100 neurons (10 hidden layers and 10 neurons per layer), learned on a training set containing about 200,000 fork samples. The data set, used to train the model, is generated by a Bitcoin mining simulator that we preconstructed. We also applied ForkDec to the test set to evaluate the attack detection and achieved a detection accuracy of 99.03%. The evaluation experiment demonstrates that ForkDec has certain application value and excellent research prospects.

Sign in / Sign up

Export Citation Format

Share Document