1
|
Xiong C, Ren Z, Liu T. Quantitative blood glucose detection influenced by various factors based on the fusion of photoacoustic temporal spectroscopy with deep convolutional neural networks. BIOMEDICAL OPTICS EXPRESS 2024; 15:2719-2740. [PMID: 38855672 PMCID: PMC11161381 DOI: 10.1364/boe.521059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/06/2024] [Revised: 03/19/2024] [Accepted: 03/20/2024] [Indexed: 06/11/2024]
Abstract
In order to efficiently and accurately monitor blood glucose concentration (BGC) synthetically influenced by various factors, quantitative blood glucose in vitro detection was studied using photoacoustic temporal spectroscopy (PTS) combined with a fusion deep neural network (fDNN). Meanwhile, a photoacoustic detection system influenced by five factors was set up, and 625 time-resolved photoacoustic signals of rabbit blood were collected under different influencing factors.In view of the sequence property for temporal signals, a dimension convolutional neural network (1DCNN) was established to extract features containing BGC. Through the parameters optimization and adjusting, the mean square error (MSE) of BGC was 0.51001 mmol/L for 125 testing sets. Then, due to the long-term dependence on temporal signals, a long short-term memory (LSTM) module was connected to enhance the prediction accuracy of BGC. With the optimal LSTM layers, the MSE of BGC decreased to 0.32104 mmol/L. To further improve prediction accuracy, a self-attention mechanism (SAM) module was coupled into and formed an fDNN model, i.e., 1DCNN-SAM-LSTM. The fDNN model not only combines the advantages of temporal expansion of 1DCNN and data long-term memory of LSTM, but also focuses on the learning of more important features of BGC. Comparison results show that the fDNN model outperforms the other six models. The determination coefficient of BGC for the testing set was 0.990, and the MSE reached 0.1432 mmol/L. Results demonstrate that PTS combined with 1DCNN-SAM-LSTM ensures higher accuracy of BGC under the synthetical influence of various factors, as well as greatly enhances the detection efficiency.
Collapse
Affiliation(s)
- Chengxin Xiong
- Key Laboratory of Optic-electronic and Communication, Jiangxi Science and Technology Normal University, Nanchang 330038, China
| | - Zhong Ren
- Key Laboratory of Optic-electronic and Communication, Jiangxi Science and Technology Normal University, Nanchang 330038, China
- Key Laboratory of Optic-electronic Detection and Information Processing of Nanchang City, Jiangxi Science and Technology Normal University, Nanchang 330038, China
| | - Tao Liu
- Key Laboratory of Optic-electronic and Communication, Jiangxi Science and Technology Normal University, Nanchang 330038, China
| |
Collapse
|
2
|
Mi J, Liu C, Chen H, Qian Y, Zhu J, Zhang Y, Liang Y, Wang L, Ta D. Light on Alzheimer's disease: from basic insights to preclinical studies. Front Aging Neurosci 2024; 16:1363458. [PMID: 38566826 PMCID: PMC10986738 DOI: 10.3389/fnagi.2024.1363458] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2023] [Accepted: 03/04/2024] [Indexed: 04/04/2024] Open
Abstract
Alzheimer's disease (AD), referring to a gradual deterioration in cognitive function, including memory loss and impaired thinking skills, has emerged as a substantial worldwide challenge with profound social and economic implications. As the prevalence of AD continues to rise and the population ages, there is an imperative demand for innovative imaging techniques to help improve our understanding of these complex conditions. Photoacoustic (PA) imaging forms a hybrid imaging modality by integrating the high-contrast of optical imaging and deep-penetration of ultrasound imaging. PA imaging enables the visualization and characterization of tissue structures and multifunctional information at high resolution and, has demonstrated promising preliminary results in the study and diagnosis of AD. This review endeavors to offer a thorough overview of the current applications and potential of PA imaging on AD diagnosis and treatment. Firstly, the structural, functional, molecular parameter changes associated with AD-related brain imaging captured by PA imaging will be summarized, shaping the diagnostic standpoint of this review. Then, the therapeutic methods aimed at AD is discussed further. Lastly, the potential solutions and clinical applications to expand the extent of PA imaging into deeper AD scenarios is proposed. While certain aspects might not be fully covered, this mini-review provides valuable insights into AD diagnosis and treatment through the utilization of innovative tissue photothermal effects. We hope that it will spark further exploration in this field, fostering improved and earlier theranostics for AD.
Collapse
Affiliation(s)
- Jie Mi
- Yiwu Research Institute, Fudan University, Yiwu, China
| | - Chao Liu
- Yiwu Research Institute, Fudan University, Yiwu, China
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, China
- Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai, China
| | - Honglei Chen
- Yiwu Research Institute, Fudan University, Yiwu, China
| | - Yan Qian
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, China
- Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai, China
| | - Jingyi Zhu
- Department of Biomedical Engineering, City University of Hong Kong, Kowloon, Hong Kong SAR, China
| | - Yachao Zhang
- Medical Ultrasound Department, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China
| | - Yizhi Liang
- Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Institute of Photonics Technology, Jinan University, Guangzhou, China
| | - Lidai Wang
- Department of Biomedical Engineering, City University of Hong Kong, Kowloon, Hong Kong SAR, China
| | - Dean Ta
- Yiwu Research Institute, Fudan University, Yiwu, China
- Department of Electronic Engineering, Fudan University, Shanghai, China
| |
Collapse
|
3
|
Functional photoacoustic microscopy of hemodynamics: a review. Biomed Eng Lett 2022; 12:97-124. [PMID: 35529339 PMCID: PMC9046529 DOI: 10.1007/s13534-022-00220-4] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Revised: 01/24/2022] [Accepted: 01/30/2022] [Indexed: 12/19/2022] Open
Abstract
Functional blood imaging can reflect tissue metabolism and organ viability, which is important for life science and biomedical studies. However, conventional imaging modalities either cannot provide sufficient contrast or cannot support simultaneous multi-functional imaging for hemodynamics. Photoacoustic imaging, as a hybrid imaging modality, can provide sufficient optical contrast and high spatial resolution, making it a powerful tool for in vivo vascular imaging. By using the optical-acoustic confocal alignment, photoacoustic imaging can even provide subcellular insight, referred as optical-resolution photoacoustic microscopy (OR-PAM). Based on a multi-wavelength laser source and developed the calculation methods, OR-PAM can provide multi-functional hemodynamic microscopic imaging of the total hemoglobin concentration (CHb), oxygen saturation (sO2), blood flow (BF), partial oxygen pressure (pO2), oxygen extraction fraction, and metabolic rate of oxygen (MRO2). This concise review aims to systematically introduce the principles and methods to acquire various functional parameters for hemodynamics by photoacoustic microscopy in recent studies, with characteristics and advantages comparison, typical biomedical applications introduction, and future outlook discussion.
Collapse
|
4
|
Jang Y, Wee H, Oh J, Jung J. Single Microdroplet Breakup-Assisted Viscosity Measurement. MICROMACHINES 2022; 13:mi13040558. [PMID: 35457863 PMCID: PMC9032506 DOI: 10.3390/mi13040558] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Revised: 03/25/2022] [Accepted: 03/29/2022] [Indexed: 12/04/2022]
Abstract
Recently, with the development of biomedical fields, the viscosity of prepolymer fluids, such as hydrogels, has played an important role in determining the mechanical properties of the extracellular matrix (ECM) or being closely related to cell viability in ECM. The technology for measuring viscosity is also developing. Here, we describe a method that can measure the viscosity of a fluid with trace amounts of prepolymers based on a simple flow-focused microdroplet generator. We also propose an equation that could predict the viscosity of a fluid. The viscosity of the prepolymer was predicted by measuring and calculating various lengths of the disperse phase at the cross junction of two continuous-phase channels and one disperse-phase channel. Bioprepolymer alginates and gelatin methacryloyl (GelMA) were used to measure the viscosity at different concentrations in a microdroplet generator. The break-up length of the dispersed phase at the cross junction of the channel gradually increased with increasing flow rate and viscosity. Additional viscosity analysis was performed to validate the standard viscosity calculation formula depending on the measured length. The viscosity formula derived based on the length of the alginate prepolymer was applied to GelMA. At a continuous phase flow rate of 400 uL/h, the empirical formula of alginate showed an error within about 2%, which was shown to predict the viscosity very well in the viscometer. Results of this study are expected to be very useful for hydrogel tuning in biomedical and tissue regeneration fields by providing a technology that can measure the dynamic viscosity of various prepolymers in a microchannel with small amounts of sample.
Collapse
Affiliation(s)
- Yeongseok Jang
- Department of Mechanical Design Engineering, Jeonbuk National University, Jeonju 54896, Korea;
| | - Hwabok Wee
- Department of Orthopaedics & Rehabilitation, College of Medicine, Pennsylvania State University, Hershey, PA 17033, USA;
| | - Jonghyun Oh
- Department of Nano-Bio Mechanical System Engineering, Jeonbuk National University, Jeonju 54896, Korea
- Correspondence: (J.O.); (J.J.)
| | - Jinmu Jung
- Department of Nano-Bio Mechanical System Engineering, Jeonbuk National University, Jeonju 54896, Korea
- Correspondence: (J.O.); (J.J.)
| |
Collapse
|
5
|
Cheng S, Zhou Y, Chen J, Li H, Wang L, Lai P. High-resolution photoacoustic microscopy with deep penetration through learning. PHOTOACOUSTICS 2022; 25:100314. [PMID: 34824976 PMCID: PMC8604673 DOI: 10.1016/j.pacs.2021.100314] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/04/2021] [Revised: 11/01/2021] [Accepted: 11/01/2021] [Indexed: 05/18/2023]
Abstract
Optical-resolution photoacoustic microscopy (OR-PAM) enjoys superior spatial resolution and has received intense attention in recent years. The application, however, has been limited to shallow depths because of strong scattering of light in biological tissues. In this work, we propose to achieve deep-penetrating OR-PAM performance by using deep learning enabled image transformation on blurry living mouse vascular images that were acquired with an acoustic-resolution photoacoustic microscopy (AR-PAM) setup. A generative adversarial network (GAN) was trained in this study and improved the imaging lateral resolution of AR-PAM from 54.0 µm to 5.1 µm, comparable to that of a typical OR-PAM (4.7 µm). The feasibility of the network was evaluated with living mouse ear data, producing superior microvasculature images that outperforms blind deconvolution. The generalization of the network was validated with in vivo mouse brain data. Moreover, it was shown experimentally that the deep-learning method can retain high resolution at tissue depths beyond one optical transport mean free path. Whilst it can be further improved, the proposed method provides new horizons to expand the scope of OR-PAM towards deep-tissue imaging and wide applications in biomedicine.
Collapse
Affiliation(s)
- Shengfu Cheng
- Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, China
- The Hong Kong Polytechnic University Shenzhen Research Institute, Shenzhen, China
| | - Yingying Zhou
- Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, China
- Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China
- The Hong Kong Polytechnic University Shenzhen Research Institute, Shenzhen, China
| | - Jiangbo Chen
- Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China
- City University of Hong Kong Shenzhen Research Institute, Shenzhen, China
| | - Huanhao Li
- Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, China
- The Hong Kong Polytechnic University Shenzhen Research Institute, Shenzhen, China
| | - Lidai Wang
- Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China
- City University of Hong Kong Shenzhen Research Institute, Shenzhen, China
| | - Puxiang Lai
- Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong, China
- The Hong Kong Polytechnic University Shenzhen Research Institute, Shenzhen, China
| |
Collapse
|