High-sensitivity dynamic diffuse fluorescence tomography system for fluorescence pharmacokinetics

Zhang, Limin; Cheng, Nan; Liu, Han; Pan, Yingxue; Zhang, Yanqi; Gao, Feng

doi:10.1117/1.jbo.27.4.046002

Cited by 7 publications

(4 citation statements)

References 26 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this system, lock-in photon-counting technique were employed to obtain high sensitivity, large dynamic range, and high ability to reject ambient light. The light sources are laser diodes (L785P25, Thorlabs) with a wavelength of 785 nm; the detectors are photomultiplier tubes (H8259-02e, Hamamatsu, Japan) having a limited dynamic range of 100 dB, and a complete measurement time for one frame image was 10.08 s. The technical details of the system can be referred to our previous work [ 25 ]. Figure 6(a) and (b) illustrate the sketch and the photo of the phantom, respectively.…”

Section: Experimental Methodsmentioning

confidence: 99%

Performance enhancement of diffuse fluorescence tomography based on an extended Kalman filtering-long short term memory neural network correction model

Xing,

Zhang,

Sun

et al. 2024

Biomed. Opt. Express

Self Cite

View full text Add to dashboard Cite

To alleviate the ill-posedness of diffuse fluorescence tomography (DFT) reconstruction and improve imaging quality and speed, a model-derived deep-learning method is proposed by combining extended Kalman filtering (EKF) with a long short term memory (LSTM) neural network, where the iterative process parameters acquired by implementing semi-iteration EKF (SEKF) served as inputs to the LSTM neural network correction model for predicting the optimal fluorescence distributions. To verify the effectiveness of the SEKF-LSTM algorithm, a series of numerical simulations, phantom and in vivo experiments are conducted, and the experimental results are quantitatively evaluated and compared with the traditional EKF algorithm. The simulation experimental results show that the proposed new algorithm can effectively improve the reconstructed image quality and reconstruction speed. Importantly, the LSTM correction model trained by the simulation data also obtains satisfactory results in the experimental data, suggesting that the SEKF-LSTM algorithm possesses strong generalization ability and great potential for practical applications.

show abstract

Section: Experimental Methodsmentioning

confidence: 99%

Performance enhancement of diffuse fluorescence tomography based on an extended Kalman filtering-long short term memory neural network correction model

Xing,

Zhang,

Sun

et al. 2024

Biomed. Opt. Express

Self Cite

View full text Add to dashboard Cite

show abstract

“…The results showed that the light intensity fluctuated within 1.5% during one‐hour period, and the channel‐to‐channel crosstalk ratio was better than 3%, suggesting the system demonstrated good performance. The assessment methods can be referred to our previous work [27].…”

Section: Methodsmentioning

confidence: 99%

Neural network‐based optimization of sub‐diffuse reflectance spectroscopy for improved parameter prediction and efficient data collection

Jingyi

Zhang

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

In this study, a general and systematical investigation of sub‐diffuse reflectance spectroscopy is implemented. A Gegenbauer‐kernel phase function‐based Monte Carlo is adopted to describe photon transport more efficiently. To improve the computational efficiency and accuracy, two neural network algorithms, namely, back propagation neural network and radial basis function neural network are utilized to predict the absorption coefficient μnormala, reduced scattering coefficient μnormals′ and sub‐diffusive quantifier γ, simultaneously, at multiple source‐detector separations (SDS). The predicted results show that the three parameters can be predicated accurately by selecting five SDSs or above. Based on the simulation results, a four wavelength (520, 650, 785 and 830 nm) measurement system using five SDSs is designed by adopting phase‐lock‐in technique. Furtherly, the trained neural‐network models are utilized to extract optical properties from the phantom and in vivo experimental data. The results verify the feasibility and effectiveness of our proposed system and methods in mucosal disease diagnosis.

show abstract

“…Based on the detection mode of D-DFT system in previous research, under the excitation of steady-state point light source, the forward model of DFT method in tissue can be approximated by a set of coupled diffusion equations, as shown in Equation (1) [13][14][15] .…”

Section: Nonuniform Photon Transport Model Modelingmentioning

confidence: 99%

Fluorescence pharmacokinetic parametric imaging method based on dynamic diffuse fluorescence tomography and deep learning

Zhang¹,

Zhang²,

Liu³

et al. 2022

Optics in Health Care and Biomedical Optics XII

View full text Add to dashboard Cite

At present, the imaging of fluorescence pharmacokinetic parameters based on dynamic diffuse fluorescence tomography (D-DFT) technology have limitations in some aspects including the accuracy of physical model and the quantification of method. In this work, we propose a fluorescence pharmacokinetic parametric imaging method of tumor tissues based on D-DFT and deep learning. It mainly includes: a more realistic training and test simulation data set can be established by combining non-uniform tissue photon transport model and biological tissue fluorescence kinetics method. A fluorescence pharmacokinetic parametric reconstruction algorithm that involves an improved U-Net architecture based on the fully convolutional neural network is developed to break through the complexity bottleneck of imaging physical model. The numerical simulation results show that the method can realize image reconstruction of pharmacokinetic parameters with high spatial resolution and high quantitative accuracy.

show abstract

High-sensitivity dynamic diffuse fluorescence tomography system for fluorescence pharmacokinetics

Cited by 7 publications

References 26 publications

Performance enhancement of diffuse fluorescence tomography based on an extended Kalman filtering-long short term memory neural network correction model

Performance enhancement of diffuse fluorescence tomography based on an extended Kalman filtering-long short term memory neural network correction model

Neural network‐based optimization of sub‐diffuse reflectance spectroscopy for improved parameter prediction and efficient data collection

Fluorescence pharmacokinetic parametric imaging method based on dynamic diffuse fluorescence tomography and deep learning

Contact Info

Product

Resources

About