KEYWORDS: Image restoration, Feature extraction, Associative arrays, Data modeling, Brain tissue, Image processing, Magnetic resonance imaging, 3D modeling, Signal to noise ratio, Tissue optics
Diffuse optical tomography (DOT) guided by medical images can be used to achieve real-time reconstruction of subdural hematoma images for monitoring purposes. However, when the hematoma is irregular and the signal to noise ratio(SNR) of input signal is low, the reconstruction effect of this method is not ideal. In order to alleviate this situation and improve the reconstruction effect of cerebral hematoma images, we proposed a optical image mapping feature extraction method in the paper. The result of experiment shows that the mean relative volume error (VRE) of the hematoma reconstruction model optimized by the optical image mapping feature extraction method is only 0.79%, and the mean value of the average Manhattan distance (AMD) between the reconstructed absorption coefficient and the true absorption coefficient is 0.0062mm-1. Compared with the model directly inputting optical information, the optical image mapping feature extraction method reduces the average VRE of the model by 93.3%, and the average AMD by 27.1%. This method provides a promising method for non-invasive continuous monitoring of clinical cerebral hematoma.
To overcome the ill-conditioning of the NIR fluorescence molecular tomography (FMT) inverse problem, neural networks are commonly used for reconstruction to improve the accuracy and reliability of imaging. This paper aims to investigate the impact of different neural network structures on the reconstruction performance of FMT for improved effect. In this study, the finite element solution of the Laplace-transformed time-domain coupled diffusion equation serves as the forward model for FMT, an improved stacked autoencoder (SAE) network is used and applied to FMT reconstruction. In the study, the SAE was set as a four layers network model structure, of which two layers were used for the hidden layer of the network. When the number of neurons in hidden layer 1 is smaller than hidden layer 2, the network is referred to as a decreasing network structure, and vice versa for an increasing network structure. The input data to the network consists of surface fluorescence intensity values collected by detectors around the heterogeneity. The output data of the network consists of fluorescence intensity values on partitioned nodes obtained through finite element method (FEM) partitioning. The experimental results demonstrate that the increasing network structure exhibits better imaging accuracy, fewer artifacts, and a more stable network model in FMT reconstruction. Through this study of the impact of SAE network architecture on FMT reconstruction, we have identified the optimal network model, which holds significant guidance for the application of neural networks in the field of FMT.
Laser speckle contrast imaging (LSCI) is a non-scanning full-field hemodynamic imaging technology, which has the advantages of real-time, non-invasive, and high spatiotemporal resolution. It has become a widely used optical imaging technology for vascular visualization and dynamic blood flow monitoring. The Reflect-LSCI (R-LSCI) system is mostly used for the imaging of superficial blood vessels, exhibiting poor image quality when it comes to deep vascular visualization. Some studies have shown that Transmissive-LSCI (T-LSCI) has advantages in deep tissue imaging. At the same time, adaptive window space direction (awsdK) method has better imaging quality for deep blood vessels in R-LSCI. In this study, we used several LSCI methods processed in the spatial domain to compare the speckle images acquired by the R-LSCI system and the T-LSCI system. The results of comparative experiments show that in the T-LSCI, the awsdK also has the ability to improve the visualization of deep blood vessels without changing the relative velocity information. At the same time, the reflection speckle images and transmission speckle images were compared. The results showed that the T-LSCI was better than the R-LSCI in deep tissue imaging for a certain thickness of tissue
Cerebral blood flow (CBF) is the main basis for clinical diagnosis of cerebrovascular diseases such as cerebral infarction and cerebral hemorrhage. The local cerebral blood flow (rCBF) detection method based on optical heterodyne detection (OHD) is expected to achieve high-precision detection of rCBF. The purpose of this study is to study the polarization state distribution characteristics of polarized light in the scattering medium by Monte Carlo simulation method, and to guide the optimization of measurement position and source-detector separation when OHD method is used to detect rCBF, and improve the measurement sensitivity. The Monte Carlo simulation result shows that the proportion of photons maintaining polarization state in the weak scattering medium is greater than in the strong scattering medium, and the proportion of photons maintaining polarization state is inversely proportional to the source-detector separation. Among them, The photon ratio that maintains the polarization state is best when the scattering angle is 0 or π. This study is of great significance for optimizing the source-detector separation and improving the sensitivity of OHD method for detecting rCBF.
The location of the source-detector relative to the anomaly whose optical properties is different from normal tissue has an important influence on the detection effect based on near - infrared spectroscopy for intracranial anomaly detection. In this study we propose a distribution structure of Single-Source Multi-Detectors (SS-MD) in order to realize the rapid localization of intracranial anomaly. A novel approach we use differential optical density difference to determine the location of anomaly, since the shape of the differential optical density curve of the two adjacent detectors is significantly related to the position of the anomaly.The finite element optical simulations were performed on anomaly with different sizes, horizontal positions and depths using SS-MD distribution structure. The distribution structure of SS-MD and the differential optical density difference curve can be used to quickly and accurately realize the localization of the anomaly, which plays an important role in optimizing the location of the source-detectors in the near infrared spectroscopy and improving the accuracy of the clinical detection of anomaly.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.