Back-propagation neural network-based reconstruction algorithm for diffuse optical tomography

Automated pipeline for breast cancer diagnosis using US assisted diffuse optical tomography

Ultrasound (US)-guided diffuse optical tomography (DOT) is a portable and non-invasive imaging modality for breast cancer diagnosis and treatment response monitoring. However, DOT data pre-processing and imaging reconstruction often require labor intensive manual processing which hampers real-time diagnosis. In this study, we aim at providing an automated US-assisted DOT pre-processing, imaging and diagnosis pipeline to achieve near real-time diagnosis. We have developed an automated DOT pre-processing method including motion detection, mismatch classification using deep-learning approach, and outlier removal. US-lesion information needed for DOT reconstruction was extracted by a semi-automated lesion segmentation approach combined with a US reading algorithm. A deep learning model was used to evaluate the quality of the reconstructed DOT images and a two-step deep-learning model developed earlier is implemented to provide final diagnosis based on US imaging features and DOT measurements and imaging results. The presented US-assisted DOT pipeline accurately processed the DOT measurements and reconstruction and reduced the procedure time to 2 to 3 minutes while maintained a comparable classification result with manually processed dataset.

FDU-Net: Deep Learning-Based Three-Dimensional Diffuse Optical Image Reconstruction

Near-infrared diffuse optical tomography (DOT) is a promising functional modality for breast cancer imaging; however, the clinical translation of DOT is hampered by technical limitations. Specifically, conventional finite element method (FEM)-based optical image reconstruction approaches are time-consuming and ineffective in recovering full lesion contrast. To address this, we developed a deep learning-based reconstruction model (FDU-Net) comprised of a Fully connected subnet, followed by a convolutional encoder-Decoder subnet, and a U-Net for fast, end-to-end 3D DOT image reconstruction. The FDU-Net was trained on digital phantoms that include randomly located singular spherical inclusions of various sizes and contrasts. Reconstruction performance was evaluated in 400 simulated cases with realistic noise profiles for the FDU-Net and conventional FEM approaches. Our results show that the overall quality of images reconstructed by FDU-Net is significantly improved compared to FEM-based methods and a previously proposed deep-learning network. Importantly, once trained, FDU-Net demonstrates substantially better capability to recover true inclusion contrast and location without using any inclusion information during reconstruction. The model was also generalizable to multi-focal and irregularly shaped inclusions unseen during training. Finally, FDU-Net, trained on simulated data, could successfully reconstruct a breast tumor from a real patient measurement. Overall, our deep learning-based approach demonstrates marked superiority over the conventional DOT image reconstruction methods while also offering over four orders of magnitude acceleration in computational time. Once adapted to the clinical breast imaging workflow, FDU-Net has the potential to provide real-time accurate lesion characterization by DOT to assist the clinical diagnosis and management of breast cancer.

Two-stage classification strategy for breast cancer diagnosis using ultrasound-guided diffuse optical tomography and deep learning

Significance

Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated great potential for breast cancer diagnosis in which real-time or near real-time diagnosis with high accuracy is desired.

Aim

We aim to use US-guided DOT to achieve an automated, fast, and accurate classification of breast lesions.

Approach

We propose a two-stage classification strategy with deep learning. In the first stage, US images and histograms created from DOT perturbation measurements are combined to predict benign lesions. Then the non-benign suspicious lesions are passed through to the second stage, which combine US image features, DOT histogram features, and 3D DOT reconstructed images for final diagnosis.

Results

The first stage alone identified 73.0% of benign cases without image reconstruction. In distinguishing between benign and malignant breast lesions in patient data, the two-stage classification approach achieved an area under the receiver operating characteristic curve of 0.946, outperforming the diagnoses of all single-modality models and of a single-stage classification model that combines all US images, DOT histogram, and imaging features.

Conclusions

The proposed two-stage classification strategy achieves better classification accuracy than single-modality-only models and a single-stage classification model that combines all features. It can potentially distinguish breast cancers from benign lesions in near real-time.

An Optical Sensory System for Assessment of Residual Cancer Burden in Breast Cancer Patients Undergoing Neoadjuvant Chemotherapy

Breast cancer patients undergoing neoadjuvant chemotherapy (NAC) require precise and accurate evaluation of treatment response. Residual cancer burden (RCB) is a prognostic tool widely used to estimate survival outcomes in breast cancer. In this study, we introduced a machine-learning-based optical biosensor called the Opti-scan probe to assess residual cancer burden in breast cancer patients undergoing NAC. The Opti-scan probe data were acquired from 15 patients (mean age: 61.8 years) before and after each cycle of NAC. Using regression analysis with k-fold cross-validation, we calculated the optical properties of healthy and unhealthy breast tissues. The ML predictive model was trained on the optical parameter values and breast cancer imaging features obtained from the Opti-scan probe data to calculate RCB values. The results show that the ML model achieved a high accuracy of 0.98 in predicting RCB number/class based on the changes in optical properties measured by the Opti-scan probe. These findings suggest that our ML-based Opti-scan probe has considerable potential as a valuable tool for the assessment of breast cancer response after NAC and to guide treatment decisions. Therefore, it could be a promising, non-invasive, and accurate method for monitoring breast cancer patient's response to NAC.

Football players' strength training method using image processing based on machine learning

This work addresses the declining physical fitness levels observed in both football players and the general population. The objective is to investigate the impact of functional strength training on the physical capabilities of football players and to develop a machine learning-based approach for posture recognition. A total of 116 adolescents aged 8 to 13 participating in football training are randomly assigned to either an experimental group (n = 60) or a control group (n = 56). Both groups underwent 24 training sessions, with the experimental group engaging in 15-20 minutes of functional strength training after each session. Machine learning techniques, specifically the backpropagation neural network (BPNN) in deep learning, are utilized to analyze the kicking actions of football players. Movement speed, sensitivity, and strength are employed as input vectors for the BPNN to compare the images of players' movements, while the similarity between the kicking actions and standard movements served as the output result to enhance training efficiency. The experimental group's kicking scores are compared to their pre-experiment scores, demonstrating a statistically significant improvement. Moreover, statistically significant differences are observed in the 5*25m shuttle running, throwing, and set kicking between the control and experimental groups. These findings highlight the significant enhancement in strength and sensitivity achieved through functional strength training in football players. The results contribute to the development of training programs for football players and the overall improvement of training efficiency.

High-Speed Time-Domain Diffuse Optical Tomography with a Sensitivity Equation-based Neural Network

Steady progress in time-domain diffuse optical tomography (TD-DOT) technology is allowing for the first time the design of low-cost, compact, and high-performance systems, thus promising more widespread clinical TD-DOT use, such as for recording brain tissue hemodynamics. TD-DOT is known to provide more accurate values of optical properties and physiological parameters compared to its frequency-domain or steady-state counterparts. However, achieving high temporal resolution is still difficult, as solving the inverse problem is computationally demanding, leading to relatively long reconstruction times. The runtime is further compromised by processes that involve 'nontrivial' empirical tuning of reconstruction parameters, which increases complexity and inefficiency. To address these challenges, we present a new reconstruction algorithm that combines a deep-learning approach with our previously introduced sensitivity-equation-based, non-iterative sparse optical reconstruction (SENSOR) code. The new algorithm (called SENSOR-NET) unfolds the iterations of SENSOR into a deep neural network. In this way, we achieve high-resolution sparse reconstruction using only learned parameters, thus eliminating the need to tune parameters prior to reconstruction empirically. Furthermore, once trained, the reconstruction time is not dependent on the number of sources or wavelengths used. We validate our method with numerical and experimental data and show that accurate reconstructions with 1 mm spatial resolution can be obtained in under 20 milliseconds regardless of the number of sources used in the setup. This opens the door for real-time brain monitoring and other high-speed DOT applications.

Fusion deep learning approach combining diffuse optical tomography and ultrasound for improving breast cancer classification

Diffuse optical tomography (DOT) is a promising technique that provides functional information related to tumor angiogenesis. However, reconstructing the DOT function map of a breast lesion is an ill-posed and underdetermined inverse process. A co-registered ultrasound (US) system that provides structural information about the breast lesion can improve the localization and accuracy of DOT reconstruction. Additionally, the well-known US characteristics of benign and malignant breast lesions can further improve cancer diagnosis based on DOT alone. Inspired by a fusion model deep learning approach, we combined US features extracted by a modified VGG-11 network with images reconstructed from a DOT deep learning auto-encoder-based model to form a new neural network for breast cancer diagnosis. The combined neural network model was trained with simulation data and fine-tuned with clinical data: it achieved an AUC of 0.931 (95% CI: 0.919-0.943), superior to those achieved using US images alone (0.860) or DOT images alone (0.842).

Periodic-net: an end-to-end data driven framework for diffuse optical imaging of breast cancer from noisy boundary data

SIGNIFICANCE

The machine learning (ML) approach plays a critical role in assessing biomedical imaging processes especially optical imaging (OI) including segmentation, classification, and reconstruction, intending to achieve higher accuracy efficiently.

AIM

This research aims to develop an end-to-end deep learning framework for diffuse optical imaging (DOI) with multiple datasets to detect breast cancer and reconstruct its optical properties in the early stages.

APPROACH

The proposed Periodic-net is a nondestructive deep learning (DL) algorithm for the reconstruction and evaluation of inhomogeneities in an inverse model with high accuracy, while boundary measurements are calculated by solving a forward problem with sources/detectors arranged uniformly around a circular domain in various combinations, including 16 × 15 , 20 × 19 , and 36 × 35 boundary measurement setups.

RESULTS

The results of image reconstruction on numerical and phantom datasets demonstrate that the proposed network provides higher-quality images with a greater amount of small details, superior immunity to noise, and sharper edges with a reduction in image artifacts than other state-of-the-art competitors.

CONCLUSIONS

The network is highly effective at the simultaneous reconstruction of optical properties, i.e., absorption and reduced scattering coefficients, by optimizing the imaging time without degrading inclusions localization and image quality.

Sensor-to-Image Based Neural Networks: A Reliable Reconstruction Method for Diffuse Optical Imaging of High-Scattering Media

Imaging tasks today are being increasingly shifted toward deep learning-based solutions. Biomedical imaging problems are no exception toward this tendency. It is appealing to consider deep learning as an alternative to such a complex imaging task. Although research of deep learning-based solutions continues to thrive, challenges still remain that limits the availability of these solutions in clinical practice. Diffuse optical tomography is a particularly challenging field since the problem is both ill-posed and ill-conditioned. To get a reconstructed image, various regularization-based models and procedures have been developed in the last three decades. In this study, a sensor-to-image based neural network for diffuse optical imaging has been developed as an alternative to the existing Tikhonov regularization (TR) method. It also provides a different structure compared to previous neural network approaches. We focus on realizing a complete image reconstruction function approximation (from sensor to image) by combining multiple deep learning architectures known in imaging fields that gives more capability to learn than the fully connected neural networks (FCNN) and/or convolutional neural networks (CNN) architectures. We use the idea of transformation from sensor- to image-domain similarly with AUTOMAP, and use the concept of an encoder, which is to learn a compressed representation of the inputs. Further, a U-net with skip connections to extract features and obtain the contrast image, is proposed and implemented. We designed a branching-like structure of the network that fully supports the ring-scanning measurement system, which means it can deal with various types of experimental data. The output images are obtained by multiplying the contrast images with the background coefficients. Our network is capable of producing attainable performance in both simulation and experiment cases, and is proven to be reliable to reconstruct non-synthesized data. Its apparent superior performance was compared with the results of the TR method and FCNN models. The proposed and implemented model is feasible to localize the inclusions with various conditions. The strategy created in this paper can be a promising alternative solution for clinical breast tumor imaging applications.

High-density diffuse correlation tomography with enhanced depth localization and minimal surface artefacts

A spatially weighted filter applied to both the measurement and the Jacobian is proposed for high-density diffuse correlation tomography (DCT) to remove unwanted extracerebral interferences and artefacts along with better depth localization in the reconstructed blood flow images. High-density DCT is implemented by appropriate modification of recently introduced Multi-speckle Diffuse Correlation Spectroscopy (M-DCS) system. Additionally, we have used autocorrelation measurements at multiple delay-times in an iterative manner to improve the reconstruction results. The proposed scheme has been validated by simulations, phantom experiments and in-vivo human experiments.

Construction and Evaluation of Prognosis Prediction Model for Patients with Brain Contusion and Laceration Based on Machine Learning

Objective

Finding valuable risk factors for the prognosis of brain contusion and laceration can help patients understand the condition and improve the prognosis. This study is aimed at analyzing the risk factors of poor prognosis in patients with brain contusion after the operation.

Methods

A total of 136 patients with cerebral contusion and laceration combined with cerebral hernia treated by neurosurgical craniotomy in our hospital were retrospectively selected and divided into a training set (n = 95) and a test set (n = 41) by the 10-fold crossover method. Logistic regression and back-propagation neural network prediction models were established to predict poor prognosis factors. The receiver operating characteristic curve (ROC) and the calibration curve were used to verify the differentiation and consistency of the prediction model.

Results

Based on logistic regression and back-propagation neural network prediction models, GCS score ≤ 8 on admission, blood loss ≥ 30 ml, mannitol ≥ 2 weeks, anticoagulants before admission, and surgical treatment are the risk factors that affect the poor prognosis of patients with a cerebral contusion after the operation. The area under the ROC was 0.816 (95% CI 0.705~0.926) and 0.819 (95% CI 0.708~0.931), respectively.

Conclusion

The prediction model based on the risk factors that affect the poor prognosis of patients with brain contusion and laceration has good discrimination and accuracy.

A simple algorithm for diffuse optical tomography without Jacobian inversion

A computationally simpler algorithm to reconstruct the optical property distribution of turbid media using diffuse optical tomographic principles is presented. The proposed algorithm eliminates the requirement of large Jacobian matrix inversion which otherwise is essential for tomographic imaging. The most significant Jacobians are identified based on proper thresholding of the measurement and the intersection of these Jacobians gives the approximate spatial location of the inhomogeneity. The algorithm is tested and optimized using simulations and further validated using tissue-mimicking phantom-based experiments andin-vivosmall-animal experiments.

A Model-Based Iterative Learning Approach for Diffuse Optical Tomography

Diffuse optical tomography (DOT) utilises near-infrared light for imaging spatially distributed optical parameters, typically the absorption and scattering coefficients. The image reconstruction problem of DOT is an ill-posed inverse problem, due to the non-linear light propagation in tissues and limited boundary measurements. The ill-posedness means that the image reconstruction is sensitive to measurement and modelling errors. The Bayesian approach for the inverse problem of DOT offers the possibility of incorporating prior information about the unknowns, rendering the problem less ill-posed. It also allows marginalisation of modelling errors utilising the so-called Bayesian approximation error method. A more recent trend in image reconstruction techniques is the use of deep learning, which has shown promising results in various applications from image processing to tomographic reconstructions. In this work, we study the non-linear DOT inverse problem of estimating the (absolute) absorption and scattering coefficients utilising a 'model-based' learning approach, essentially intertwining learned components with the model equations of DOT. The proposed approach was validated with 2D simulations and 3D experimental data. We demonstrated improved absorption and scattering estimates for targets with a mix of smooth and sharp image features, implying that the proposed approach could learn image features that are difficult to model using standard Gaussian priors. Furthermore, it was shown that the approach can be utilised in compensating for modelling errors due to coarse discretisation enabling computationally efficient solutions. Overall, the approach provided improved computation times compared to a standard Gauss-Newton iteration.

Multitask Deep Learning Reconstruction and Localization of Lesions in Limited Angle Diffuse Optical Tomography

Diffuse optical tomography (DOT) leverages near-infrared light propagation through tissue to assess its optical properties and identify abnormalities. DOT image reconstruction is an ill-posed problem due to the highly scattered photons in the medium and the smaller number of measurements compared to the number of unknowns. Limited-angle DOT reduces probe complexity at the cost of increased reconstruction complexity. Reconstructions are thus commonly marred by artifacts and, as a result, it is difficult to obtain an accurate reconstruction of target objects, e.g., malignant lesions. Reconstruction does not always ensure good localization of small lesions. Furthermore, conventional optimization-based reconstruction methods are computationally expensive, rendering them too slow for real-time imaging applications. Our goal is to develop a fast and accurate image reconstruction method using deep learning, where multitask learning ensures accurate lesion localization in addition to improved reconstruction. We apply spatial-wise attention and a distance transform based loss function in a novel multitask learning formulation to improve localization and reconstruction compared to single-task optimized methods. Given the scarcity of real-world sensor-image pairs required for training supervised deep learning models, we leverage physics-based simulation to generate synthetic datasets and use a transfer learning module to align the sensor domain distribution between in silico and real-world data, while taking advantage of cross-domain learning. Applying our method, we find that we can reconstruct and localize lesions faithfully while allowing real-time reconstruction. We also demonstrate that the present algorithm can reconstruct multiple cancer lesions. The results demonstrate that multitask learning provides sharper and more accurate reconstruction.

A Data Self-Calibration Method Based on High-Density Parallel Plate Diffuse Optical Tomography for Breast Cancer Imaging

When performing the diffuse optical tomography (DOT) of the breast, the mismatch between the forward model and the experimental conditions will significantly hinder the reconstruction accuracy. Therefore, the reference measurement is commonly used to calibrate the measured data before the reconstruction. However, it is complicated to customize corresponding reference phantoms based on the breast shape and background optical parameters of different subjects in clinical trials. Furthermore, although high-density (HD) DOT configuration has been proven to improve imaging quality, a large number of source-detector (SD) pairs also increase the difficulty of multi-channel correction. To enhance the applicability of the breast DOT, a data self-calibration method based on an HD parallel-plate DOT system is proposed in this paper to replace the conventional relative measurement on a reference phantom. The reference predicted data can be constructed directly from the measurement data with the support of the HD-DOT system, which has nearly a hundred sets of measurements at each SD distance. The proposed scheme has been validated by Monte Carlo (MC) simulation, breast-size phantom experiments, and clinical trials, exhibiting the feasibility in ensuring the quality of the DOT reconstruction while effectively reducing the complexity associated with relative measurements on reference phantoms.

Detection of Tibiofemoral Joint Injury in High-Impact Motion Based on Neural Network Reconstruction Algorithm

In order to reduce the damage degree of joint bones, ligaments, and soft tissues caused by the high impact on the tibiofemoral joint during landing, a method for detecting the damage of tibiofemoral joint under high-impact action based on neural network reconstruction algorithm is proposed. Two dimensional X-ray images of knee joints from straightening to bending in 10 healthy volunteers were selected. CT scans were performed on the knee joint on the same side, and the 3D model from the acquired images was reconstructed. The kinematics data of the femur relative to the tibia with full degree of freedom were measured by registering the 3D model with 2D images. The results showed that in the extended position, the femur was rotated inward (5.5° ± 6.3°) relative to the tibia. The range of femoral external rotation is (18.7° ± 5.9°) from flexion to 90° in straight position. However, from 90° to 120°, a small amount of internal rotation occurred (1.4° ± 1.9°), so during the whole flexion process, the femur rotated (17.3° ± 6.9°), among which, from the straight position to 15°, the femur rotated (10.0° ± 5.6°). Damage in different areas is determined by the size of the interlayer displacement sample size method of sample space reduction. It is proved that the detection method of tibiofemoral joint injury in high-impact motion based on neural network reconstruction algorithm has high accuracy and consistency.

Safety Risk Assessment of Tourism Management System Based on PSO-BP Neural Network

With the development of science and technology, system management is gradually applied to tourism management. How to correctly assess the security risks of the tourism management system has become an important means to maintain passenger information. The security risk index of the travel management system is input into the PSO-BP network as a sample, and the corresponding risk value of the index is used as the network output. The results show that the error results, accuracy (96.53%), training time (216 s), number of iterations (275 times), and convergence speed are all better than traditional BP network. The relative error of PSO-BP network (0.32%) is better than that of BP network, with 300 iterations, and the error is close to 10–5. The average evaluation accuracy of S based on PSO-BP network is 99.72%, and the average time consumed is 2.512 s. It is superior to the evaluation model based on fuzzy set and entropy weight theory and the evaluation model based on gray correlation analysis and radial basis function neural network. In conclusion, the security risk assessment of the tourism management system based on PSO-BP network can effectively assess the security risk of the tourism management system.

Machine learning model with physical constraints for diffuse optical tomography

A machine learning model with physical constraints (ML-PC) is introduced to perform diffuse optical tomography (DOT) reconstruction. DOT reconstruction is an ill-posed and under-determined problem, and its quality suffers by model mismatches, complex boundary conditions, tissue-probe contact, noise etc. Here, for the first time, we combine ultrasound-guided DOT with ML to facilitate DOT reconstruction. Our method has two key components: (i) a neural network based on auto-encoder is adopted for DOT reconstruction, and (ii) physical constraints are implemented to achieve accurate reconstruction. Both qualitative and quantitative results demonstrate that the accuracy of the proposed method surpasses that of existing models. In a phantom study, compared with the Born conjugate gradient descent (Born-CGD) reconstruction method, the ML-PC method decreases the mean percentage error of the reconstructed maximum absorption coefficient from 16.41% to 13.4% for high contrast phantoms and from 23.42% to 9.06% for low contrast phantoms, with improved depth distribution of the target absorption maps. In a clinical study, better contrast was obtained between malignant and benign breast lesions, with the ratio of the medians of the maximum absorption coefficient improved from 1.63 to 2.22.

Application of a Generative Adversarial Network in Image Reconstruction of Magnetic Induction Tomography

Image reconstruction of Magnetic induction tomography (MIT) is an ill-posed problem. The non-linear characteristics lead many difficulties to its solution. In this paper, a method based on a Generative Adversarial Network (GAN) is presented to tackle these barriers. Firstly, the principle of MIT is analyzed. Then the process for finding the global optimum of conductivity distribution is described as a training process, and the GAN model is proposed. Finally, the image was reconstructed by a part of the model (the generator). All datasets are obtained from an eight-channel MIT model by COMSOL Multiphysics software. The voltage measurement samples are used as input to the trained network, and its output is an estimate for image reconstruction of the internal conductivity distribution. The results based on the proposed model and the traditional algorithms were compared, which have shown that average root mean squared error of reconstruction results obtained by the proposed method is 0.090, and the average correlation coefficient with original images is 0.940, better than corresponding indicators of BPNN and Tikhonov regularization algorithms. Accordingly, the GAN algorithm was able to fit the non-linear relationship between input and output, and visual images also show that it solved the usual problems of artifact in traditional algorithm and hot pixels in L2 regularization, which is of great significance for other ill-posed or non-linear problems.

Modeling and Synthesis of Breast Cancer Optical Property Signatures With Generative Models

Is it possible to find deterministic relationships between optical measurements and pathophysiology in an unsupervised manner and based on data alone? Optical property quantification is a rapidly growing biomedical imaging technique for characterizing biological tissues that shows promise in a range of clinical applications, such as intraoperative breast-conserving surgery margin assessment. However, translating tissue optical properties to clinical pathology information is still a cumbersome problem due to, amongst other things, inter- and intrapatient variability, calibration, and ultimately the nonlinear behavior of light in turbid media. These challenges limit the ability of standard statistical methods to generate a simple model of pathology, requiring more advanced algorithms. We present a data-driven, nonlinear model of breast cancer pathology for real-time margin assessment of resected samples using optical properties derived from spatial frequency domain imaging data. A series of deep neural network models are employed to obtain sets of latent embeddings that relate optical data signatures to the underlying tissue pathology in a tractable manner. These self-explanatory models can translate absorption and scattering properties measured from pathology, while also being able to synthesize new data. The method was tested on a total of 70 resected breast tissue samples containing 137 regions of interest, achieving rapid optical property modeling with errors only limited by current semi-empirical models, allowing for mass sample synthesis and providing a systematic understanding of dataset properties, paving the way for deep automated margin assessment algorithms using structured light imaging or, in principle, any other optical imaging technique seeking modeling. Code is available.

Optoacoustic Imaging of Glucagon-like Peptide-1 Receptor with a Near-Infrared Exendin-4 Analog

Limitations in current imaging tools have long challenged the imaging of small pancreatic islets in animal models. Here, we report the first development and in vivo validation testing of a broad-spectrum and high-absorbance near-infrared optoacoustic contrast agent, E4x12-Cy7. Our near-infrared tracer is based on the amino acid sequence of exendin-4 and targets the glucagon-like peptide-1 receptor (GLP-1R). Cell assays confirmed that E4x12-Cy7 has a high-binding affinity (dissociation constant, Kd, 4.6 ± 0.8 nM). Using the multispectral optoacoustic tomography, we imaged E4x12-Cy7 and optoacoustically visualized β-cell insulinoma xenografts in vivo for the first time. In the future, similar optoacoustic tracers that are specific for β-cells and combines optoacoustic and fluorescence imaging modalities could prove to be important tools for monitoring the pancreas for the progression of diabetes.

Exploring the relationship between the dielectric properties and viability of human normal hepatic tissues from 10 Hz to 100 MHz based on grey relational analysis and BP neural network

Liver is an important parenchyma organ, and its tissue viability plays an important role in liver transplantation and liver ischemic injury assessment. Dielectric property is a useful biophysical feature that provides insights into the structure and composition of biological tissues. This work aims to establish the relationship between the dielectric properties and viability of human normal hepatic tissues and explore the possibility of evaluating tissue viability by using dielectric properties. First, data on dielectric properties and tissue viability (including cell morphology and enzyme indicators) were collected from human liver tissues at 0.25-24 h after isolation. Grey relational analysis was conducted to select dielectric property and tissue viability indices that were highly correlated with prolonged ex vivo time as the inputs and outputs, respectively, of back-propagation (BP) neural network analysis. Finally, a BP neural network was developed with the Levenberg-Marquardt algorithm to explore the possibility of using dielectric properties as the basis for tissue viability evaluation. Results showed that the mean relative error for prediction was 2.40%, indicating that the model showed potential in forecasting liver tissue viability by applying dielectric properties.

Multi-sensor information fusion detection system for fire robot through back propagation neural network

Objective

To reduce the danger for firefighters and ensure the safety of firefighters as much as possible, based on the back propagation neural network (BPNN) the fire sensor multi-sensor information fusion detection system is investigated.

Method

According to previous studies, the information sources and information processing methods for the design of this study are first explained. Then, the basic structure and flowchart of the research object in this study are designed. Based on the structure diagram and flowchart, the BPNN is selected to fuse the feature layers in this study, and the fuzzy control is selected to fuse the decision layers in this study. The multi-sensor information fusion detection system collects information for the sensors first, processes the collected information, and sends it to the processor of the robot. The processor analyzes and processes the received signal, and transmits the obtained information to the control terminal through the wireless communication system.

Results

Through the tests in this study, it is found that when the number of hidden layer nodes of the BPNN is 7, the optimal training result is obtained. On this basis, the test of BPNN in this study is performed. The test results show that after 127 iterations, the error of the BPNN reaches the lowest target value, indicating that the BPNN achieves an excellent level of accuracy. The trained BPNN has a running time of 0.0276 s and a mean square error of 0.0013. The smaller the mean square error value is, the higher the accuracy of the BPNN is, which shows that the BPNN meets the high precision requirements of this study.

Conclusion

The research on the multi-sensor information fusion detection system of fire robots in this study can provide theoretical support for the research on forest fire detection in China. Since the proposed BPNN-based robot is applied to the inspection and processing of forest remaining fire, the results are applicable to the forests of various countries, with a wide range of applications.

Soft Sensors in the Primary Aluminum Production Process Based on Neural Networks Using Clustering Methods

Primary aluminum production is an uninterrupted and complex process that must operate in a closed loop, hindering possibilities for experiments to improve production. In this sense, it is important to have ways to simulate this process computationally without acting directly on the plant, since such direct intervention could be dangerous, expensive, and time-consuming. This problem is addressed in this paper by combining real data, the artificial neural network technique, and clustering methods to create soft sensors to estimate the temperature, the aluminum fluoride percentage in the electrolytic bath, and the level of metal of aluminum reduction cells (pots). An innovative strategy is used to split the entire dataset by section and lifespan of pots with automatic clustering for soft sensors. The soft sensors created by this methodology have small estimation mean squared error with high generalization power. Results demonstrate the effectiveness and feasibility of the proposed approach to soft sensors in the aluminum industry that may improve process control and save resources.

Elastographic Tomosynthesis From X-Ray Strain Imaging of Breast Cancer

Noncancerous breast tissue and cancerous breast tissue have different elastic properties. In particular, cancerous breast tumors are stiff when compared to the noncancerous surrounding tissue. This difference in elasticity can be used as a means for detection through the method of elastographic tomosynthesis by means of physical modulation. This paper deals with a method to visualize elasticity of soft tissues, particularly breast tissues, via x-ray tomosynthesis. X-ray tomosynthesis is now used to visualize breast tissues with better resolution than the conventional single-shot mammography. The advantage of X-ray tomosynthesis over X-ray CT is that fewer projections are needed than CT to perform the reconstruction, thus radiation exposure and cost are both reduced. Two phantoms were used for the testing of this method, a physical phantom and an in silico phantom. The standard root mean square error in the tomosynthesis for the physical phantom was 2.093 and the error in the in silico phantom was negligible. The elastographs were created through the use of displacement and strain graphing. A Gaussian Mixture Model with an expectation–maximization clustering algorithm was applied in three dimensions with an error of 16.667%. The results of this paper have been substantial when using phantom data. There are no equivalent comparisons yet in 3D x-ray elastographic tomosynthesis. Tomosynthesis with and without physical modulation in the 3D elastograph can identify feature groupings used for biopsy. The studies have potential to be applied to human test data used as a guide for biopsy to improve accuracy of diagnosis results. Further research on this topic could prove to yield new techniques for human patient diagnosis purposes.

Special Section Guest Editorial: Celebration of the Britton Chance Legacy

This guest editorial introduces the Special Section on Metabolic Imaging and Spectroscopy: Britton Chance 105th Birthday Commemorative.