Reducing instability of inter-subject covariance of FDG uptake networks using structure-weighted sparse estimation approach.

PURPOSE: Sparse inverse covariance estimation (SICE) is increasingly utilized to estimate inter-subject covariance of FDG uptake (FDGcov) as proxy of metabolic brain connectivity. However, this statistical method suffers from the lack of robustness in the connectivity estimation. Patterns of FDGcov were observed to be spatially similar with patterns of structural connectivity as obtained from DTI imaging. Based on this similarity, we propose to regularize the sparse estimation of FDGcov using the structural connectivity. METHODS: We retrospectively analyzed the FDG-PET and DTI data of 26 healthy controls, 41 patients with Alzheimer's disease (AD), and 30 patients with frontotemporal lobar degeneration (FTLD). Structural connectivity matrix derived from DTI data was introduced as a regularization parameter to assign individual penalties to each potential metabolic connectivity. Leave-one-out cross validation experiments were performed to assess the differential diagnosis ability of structure weighted SICE approach. A few approaches of structure weighted were compared with the standard SICE. RESULTS: Compared to the standard SICE, structural weighting has shown more stable performance in the supervised classification, especially in the differentiation AD vs. FTLD (accuracy of 89-90%, while unweighted SICE only 85%). There was a significant positive relationship between the minimum number of metabolic connection and the robustness of the classification accuracy (r = 0.57, P < 0.001). Shuffling experiments showed significant differences between classification score derived with true structural weighting and those obtained by randomized structure (P < 0.05). CONCLUSION: The structure-weighted sparse estimation can enhance the robustness of metabolic connectivity, which may consequently improve the differentiation of pathological phenotypes.

Classification of microcalcification clusters in digital breast tomosynthesis using ensemble convolutional neural network.

BACKGROUND: The classification of benign and malignant microcalcification clusters (MCs) is an important task for computer-aided diagnosis (CAD) of digital breast tomosynthesis (DBT) images. Influenced by imaging method, DBT has the characteristic of anisotropic resolution, in which the resolution of intra-slice and inter-slice is quite different. In addition, the sharpness of MCs in different slices of DBT is quite different, among which the clearest slice is called focus slice. These characteristics limit the performance of CAD algorithms based on standard 3D convolution neural network (CNN). METHODS: To make full use of the characteristics of the DBT, we proposed a new ensemble CNN, which consists of the 2D ResNet34 and the anisotropic 3D ResNet to extract the 2D focus slice features and 3D contextual features of MCs, respectively. Moreover, the anisotropic 3D convolution is used to build 3D ResNet to avoid the influence of DBT anisotropy. RESULTS: The proposed method was evaluated on 495 MCs in DBT images of 275 patients, which are collected from our collaborative hospital. The area under the curve (AUC) of receiver operating characteristic (ROC) and accuracy of classifying benign and malignant MCs using decision-level ensemble strategy were 0.8837 and 82.00%, which were significantly higher than the experimental results of 2D ResNet34 (AUC: 0.8264, ACC: 76.00%) and anisotropic 3D ResNet (AUC: 0.8455, ACC: 76.00%). Compared with the results of 3D features classification in the radiomics, the AUC of the deep learning method with decision-level ensemble strategy was improved by 0.0435, and the F1 score was improved from 79.37 to 85.71%. More importantly, the sensitivity increased from 78.13 to 84.38%, and the specificity increased from 66.67 to 77.78%, which effectively reduced the false positives of diagnosis CONCLUSION: The results fully prove that the ensemble CNN can effectively integrate 2D features and 3D features, improve the classification performance of benign and malignant MCs in DBT, and reduce the false positives.

Individual brain metabolic connectome indicator based on Kullback-Leibler Divergence Similarity Estimation predicts progression from mild cognitive impairment to Alzheimer's dementia.

PURPOSE: Positron emission tomography (PET) with 18F-fluorodeoxyglucose (FDG) reveals altered cerebral metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's dementia (AD). Previous metabolic connectome analyses derive from groups of patients but do not support the prediction of an individual's risk of conversion from present MCI to AD. We now present an individual metabolic connectome method, namely the Kullback-Leibler Divergence Similarity Estimation (KLSE), to characterize brain-wide metabolic networks that predict an individual's risk of conversion from MCI to AD. METHODS: FDG-PET data consisting of 50 healthy controls, 332 patients with stable MCI, 178 MCI patients progressing to AD, and 50 AD patients were recruited from ADNI database. Each individual's metabolic brain network was ascertained using the KLSE method. We compared intra- and intergroup similarity and difference between the KLSE matrix and group-level matrix, and then evaluated the network stability and inter-individual variation of KLSE. The multivariate Cox proportional hazards model and Harrell's concordance index (C-index) were employed to assess the prediction performance of KLSE and other clinical characteristics. RESULTS: The KLSE method captures more pathological connectivity in the parietal and temporal lobes relative to the typical group-level method, and yields detailed individual information, while possessing greater stability of network organization (within-group similarity coefficient, 0.789 for sMCI and 0.731 for pMCI). Metabolic connectome expression was a superior predictor of conversion than were other clinical assessments (hazard ratio (HR) = 3.55; 95% CI, 2.77-4.55; P < 0.001). The predictive performance improved further upon combining clinical variables in the Cox model, i.e., C-indices 0.728 (clinical), 0.730 (group-level pattern model), 0.750 (imaging connectome), and 0.794 (the combined model). CONCLUSION: The KLSE indicator identifies abnormal brain networks predicting an individual's risk of conversion from MCI to AD, thus potentially constituting a clinically applicable imaging biomarker.

A Combined Deep-Learning and Lattice Boltzmann Model for Segmentation of the Hippocampus in MRI.

Segmentation of the hippocampus (HC) in magnetic resonance imaging (MRI) is an essential step for diagnosis and monitoring of several clinical situations such as Alzheimer's disease (AD), schizophrenia and epilepsy. Automatic segmentation of HC structures is challenging due to their small volume, complex shape, low contrast and discontinuous boundaries. The active contour model (ACM) with a statistical shape prior is robust. However, it is difficult to build a shape prior that is general enough to cover all possible shapes of the HC and that suffers the problems of complicated registration of the shape prior and the target object and of low efficiency. In this paper, we propose a semi-automatic model that combines a deep belief network (DBN) and the lattice Boltzmann (LB) method for the segmentation of HC. The training process of DBN consists of unsupervised bottom-up training and supervised training of a top restricted Boltzmann machine (RBM). Given an input image, the trained DBN is utilized to infer the patient-specific shape prior of the HC. The specific shape prior is not only used to determine the initial contour, but is also introduced into the LB model as part of the external force to refine the segmentation. We used a subset of OASIS-1 as the training set and the preliminary release of EADC-ADNI as the testing set. The segmentation results of our method have good correlation and consistency with the manual segmentation results.

[A Method for Fluorescent Diffuse Optical Tomography Based on Lattice Boltzmann Forward Model on GPU Parallelization].

Fluorescent Diffuse Optical Tomography (FDOT) is an emerging imaging method with great prospects in fields of biology and medicine. However, the current solutions to the forward problem in FDOT are time consuming, which greatly limit the application. We proposed a method for FDOT based on Lattice Boltzmann forward model on GPU to greatly improve the computational efficiency. The Lattice Boltzmann Method (LBM) was used to construct the optical transmission model. This method separated the LBM into collision, streaming and boundary processing processes on GPUs to perform the LBM efficiently, which were local computational and inefficient on CPU. The feasibility of the proposed method was verified by the numerical phantom and the physical phantom experiments. The experimental results showed that the proposed method achieved the best performance of a 118-fold speed up under the precondition of simulation accuracy, comparing to the diffusion equation implemented by Finite Element Method (FEM) on CPU. Thus, the LBM on the GPU may efficiently solve the forward problem in FDOT.

[A Fluorescence Diffusion Optical Tomography System Based on Lattice Boltzmann Forward Model].

Fluorescence Diffuse Optical Tomography (FDOT) is significant for biomedical applications, such as medical diagnostics, drug research. The fluorescence probe distribution in biological tissues can be quantitatively and non-invasively obtained via FDOT, achieving targets positioning and detection. In order to reduce the cost of FDOT, this study designs a FDOT system based on Lattice Boltzmann forward model. The system is used to realize two functions of light propagation simulation and FDOT reconstruction, and is composed of a parameter module, an algorithm module, a result display module and a data interaction module. In order to verify the effectiveness of the platform, this study carries out the light propagation simulation experiment and the FDOT reconstruction experiment, respectively comparing the Monte Carlo (MC) light propagation simulation results and the real position of the light source to be reconstructed. Experiments show that the proposed FDOT system has good reliability and has a high promotion value.

Predicting Alzheimer Disease From Mild Cognitive Impairment With a Deep Belief Network Based on 18F-FDG-PET Images.

OBJECTIVE: Accurate diagnosis of early Alzheimer disease (AD) plays a critical role in preventing the progression of memory impairment. We aimed to develop a new deep belief network (DBN) framework using 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) metabolic imaging to identify patients at the mild cognitive impairment (MCI) stage with presymptomatic AD and to discriminate them from other patients with MCI. METHODS: 18F-fluorodeoxyglucose-PET images of 109 patients recruited in the ongoing longitudinal Alzheimer's Disease Neuroimaging Initiative study were included in this analysis. Patients were grouped into 2 classes: (1) stable mild cognitive impairment (n = 62) or (2) progressive mild cognitive impairment (n = 47). Our framework is composed of 4 steps: (1) image preprocessing: normalization and smoothing; (2) identification of regions of interest (ROIs); (3) feature learning using deep neural networks; and (4) classification by support vector machine with 3 kernels. All classification experiments were performed with a 5-fold cross-validation. Accuracy, sensitivity, and specificity were used to validate the results. RESULT: A total of 1103 ROIs were obtained. One hundred features were learned from ROIs using the DBN. The classification accuracy using linear, polynomial, and RBF kernels was 83.9%, 79.2%, and 86.6%, respectively. This method may be a powerful tool for personalized precision medicine in the population with prediction of early AD progression.

[A Lattice Boltzmann Forward Model for Fast Fluorescence Diffuse Optical Tomography].

Fluorescent Diffuse Optical Tomography (FDOT), as a new imaging technology, can achieve three-dimensional quantitative functional imaging of probe in biological tissues, and has wide application value in biomedicine. Forward model which describes the photon propagation within a biological tissue is a prerequisite for implementing FDOT and determines the performance of FDOT. To further improve the efficiency of FDOT, this paper proposes a new forward model based on the Lattice Boltzmann (LB) method derived from the discretization of radiation transfer equation and applies it to FDOT. The experimental results of numerical simulation and physical phantom show that the LB-based forward model proposed in this paper can increase the imaging speed of FDOT by about 5 times compared with the traditional diffusion equation method, without reducing its imaging quality.

[Simulation Platform of Photoacoustic Imaging Based on Finite Element and k-space Pseudospectral Method].

Numerical simulation is a powerful technology for photoacoustic imaging (PAI) in both theory studies and practical applications. In this paper, a simulation platform for PAI was designed and implemented based on Matlab. The simulation platform utilized finite element method (FEM) and k-space pseudospectral method to calculate the forward and inverse problem of PAI. And a graphical user interface (GUI) was realized. Structural design, work process and other operating details of the platform was also provided. By compared with theoretical temporal waveform of photoacoustic signal and reconstruction results of COMSOL, the validity and reliability was verified. And a reliable simulation tool was proposed for PAI.

[Hippocampus MRI Parallel Segmentation Using Three Dimensions Lattice Boltzmann Model with Prior Information].

Getting volume change of hippocampus by segmenting on brain MRI is an important step in the diagnose of Alzheimer's disease and other brain disease. Three dimensional segmentation can make use of the correlation of image in gray and spatial position, so it has high accuracy. This paper proposes a novel three-dimensional lattice Boltzmann model combined with the surface evolution of deformable model and taking the prior information as an external force term to constrain the evolution of three dimensional surfaces. In order to solve the problem of high computational cost caused by 3D segmentation, the parallelization of the method is programmed on single GPU platform and dual GPU platform. Comparison experiments were set to test the accuracy of segmentation and computational efficiency between the novel LB method and another method by using 20 real AD patient's MRI from ADNI. In ensuring the accuracy of the segmentation, the time can be reduced to 12.76 s on single GPU platform, and 17.32 s on dual GPU platform, contrasting 132.43 s on CPU platform. It fully validates the characteristics of lattice Boltzmann method which can be highly parallelized.

[Design of Intelligent Nursing Bed Based on Internet of Things + Technology].

With the advent of social aging, the development of intelligent multifunctional nursing beds that are suitable for hospitals, nursing homes, homes and the like has a wide range of applications, this paper presents an intelligent nursing bed design based on Internet of Things technology. The design uses STM32F103 as the central processor. The design is divided into nursing bed module based on tri-fold structure, central control module based on data processing, weight scale module based on weight detection, power supply module based on system power supply and host computer module based on user operation. The design uses a closed control mode, greatly improving the bed control accuracy. Experimental tests showed that under the action of the intelligent control bed control system, the error rate of bed position information driven bedboard can be less than 2%, which has high accuracy and stability.

[Wearable Device for Non-Invasive Continuously Blood Pressure Monitoring].

In aging society the development of non-invasive continuously blood pressure monitors which are suitable for homes, communities and nursing homes has a wide range of applications. This paper proposes a non-invasive continuously blood pressure monitoring based on wearable device which uses MSP430F5529 as the central processor. The design is divided into signal acquisition module, central control module, display module, power supply module and host computer module. The experimental results showed that DBP (375/390, 96.15%) and SBP estimation values (377/390, 96.67%) are in 95% confidence interval, which means our design passes Bland-Altman test with high accuracy and stability.

[Design and Implementation of the Glasses-free Three Dimensional Laparoscopy System].

Minimally invasive surgery (MIS) has the advantages of small trauma, quick recovery and lower risk of the surgery. Compared with the traditional two-dimension laparoscopic technique, three-dimension laparoscopic system uses the double beam imaging system as well as the three-dimensional imaging display device so as to compensate for the lack of depth information in two-dimension laparoscopic imaging technique, reduce the surgeon's difficulty in using surgical instruments and enhance the accuracy of the surgery. For those reasons, the author designed a glassesfree three dimensional wide-field electronic laparoscopic system, which consists of dual CMOS camera module, image processing module and glasses-free display module that can offer depth information. The active shape model is applied to eye tracking, for the purpose of getting the wide-field to help doctor obtain 3D display in more places. Primary experimental results of the simulation using the system show that operators with the aid of proposed system spend less time finishing the task than those using traditional system without depth perception during operation.

[Evaluation of Axillary Lymph Node Metastasis by Using Radiomics of Dual-modal Ultrasound Composed of Elastography and B-mode].

OBJECTIVES: To explore the diagnostic value of quantitative radiomics features from dual-modal ultrasound composed of elastography and B-mode for axillary lymph node metastasis in breast cancer patients. METHODS: We retrospectively analyzed 161 axillary lymph nodes (69 benign and 92 metastatic) undergoing real-time elastography and B-mode ultrasound from 158 patients with breast cancer. We extracted a total of 428 features, consisting of morphologic features from B-mode, and intensity features and gray-level co-occurrence matrix features from the dual modalities, and the optimal subsut of features was selected through least absolute shrinkage and selection operator (Lasso) under the condition of leave-one-out cross validation. We used SVM for the classification of benign and metastatic nodes. RESULTS: The sensitivity, specificity, accuracy and Youden's index of the 35 radiomics features selected with Lasso were 86.96%, 85.51%, 86.34% and 72.46%, respectively. CONCLUSIONS: The radiomics features from dual-modal ultrasound (elastography and B-mode) have demonstrated good performance for classification and have potential to be applied to clinical diagnosis of axillary lymph node metastasis.

[The Standardization Study of Data Communication and Storage for Rehabilitation Devices].

Currently, lacking standards of data communication and storage has been becoming a huge problem in tertiary medical rehabilitation networks. Several rehabilitation management requirements need be met, such as integrating rehabilitation resources, sharing patient data, and augmenting efficiency of rehabilitation therapies. By summarizing existing standards within medical devices and data management, this paper proposed a novel standardized protocol for rehabilitation, which is composed of standards in data format, communication signaling and processing. To demonstrate it, an application in current tertiary medical rehabilitation networks was also proposed in this paper. As a result, the outcomes of this paper are expected to solve the 'information isolated island' problem in current rehabilitation medical rehabilitation networks.

[Multifunctional Nursing Beds Based on Intelligent Detection and Recovery].

With the advent of the aging society, there will be a wide range of applications if novel intelligent multifunctional nursing beds can be developed for hospitals, bead houses and families at the same time. By listing and analyzing existing products, this paper summarized four function categories for multifunctional nursing beds, including security assurance, treatment aid, comfortability optimization, and human-machine interaction and communication. Finally, by comparing existing functions and potential user requirements, this paper proposed four function development trends, including physiological parameter monitoring, sleep aid, intelligent temperature control, and video communication.

[Design and Implementation of Image Interpolation and Color Correction for Ultra-thin Electronic Endoscope on FPGA].

This paper proposed an image interpolation algorithm based on bilinear interpolation and a color correction algorithm based on polynomial regression on FPGA, which focused on the limited number of imaging pixels and color distortion of the ultra-thin electronic endoscope. Simulation experiment results showed that the proposed algorithm realized the real-time display of 1280 x 720@60Hz HD video, and using the X-rite color checker as standard colors, the average color difference was reduced about 30% comparing with that before color correction.

[Design and Implementation of a Novel Networked Sleep Monitoring System].

To meet the need of cost-effective multi-biosignal monitoring devices nowadays, we designed a system based on super low power MCU. It can collect, record and transfer several signals including ECG, Oxygen saturation, thoracic and abdominal wall expansion, oronasal airflow signal. The data files can be stored on a flash chip and transferred to a computer by a USB module. In addition, the sensing data can be sent wirelessly in real time. Considering that long term work of wireless module consumes much energy, we present a low-power optimization method based on delay constraint. Lower energy consumption comes at the cost of little delay. Experimental results show that it can effectively decrease the energy consumption without changing wireless module and transfer protocol. Besides, our system is powered by two dry batteries and can work at least 8 hours throughout a whole night.

[Design of ENT endoscopic HD video image system].

Endoscopes have been widely used in ENT (Ear-Nose-Throat) disease diagnosis. This paper mainly designs a high-definition (HD) endoscopic video image system, as a subsystem of digital HD ENT head and neck surgery comprehensive diagnostic workstation, permit to display, record, store and transport of HD video or image, which are needed in clinical examination, diagnosis, treatment and teaching. The system is mainly composed of camera control module, video processing module, video display and storage module, human interactive module and picture & text workstation interactive interface module, etc.

An effective and robust lattice Boltzmann model guided by atlas for hippocampal subregions segmentation.

BACKGROUND: Given the varying vulnerability of the rostral and caudal regions of the hippocampus to neuropathology in the Alzheimer's disease (AD) continuum, accurately assessing structural changes in these subregions is crucial for early AD detection. The development of reliable and robust automatic segmentation methods for hippocampal subregions (HS) is of utmost importance. OBJECTIVE: Our aim is to propose and validate a HS segmentation model that is both training-free and highly generalizable. This method should exhibit comparable accuracy and efficiency to state-of-the-art techniques. The segmented HS can serve as a biomarker for studying the progression of AD. METHODS: We utilized the functional magnetic resonance imaging of the Brain's Integrated Registration and Segmentation Tool (FIRST) to segment the entire hippocampus. By intersecting the segmentation results with the Brainnetome (BN) atlas, we obtained coarse segmentation of the four HS regions. This coarse segmentation was then employed as a shape prior term in the lattice Boltzmann (LB) model, as well as for initializing contours. Additionally, image gradients and local gray levels were integrated into the external force terms of the LB model to refine the coarse segmentation results. We assessed the segmentation accuracy of the model using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and evaluated the potential of the segmentation results as AD biomarkers on both the ADNI and Xuanwu datasets. RESULTS: The median Dice similarity coefficients (DSC) for the left caudal, right caudal, left rostral, and right rostral hippocampus were 0.87, 0.88, 0.88, and 0.89, respectively. The proportion of segmentation results with a DSC exceeding 0.8 was 77%, 78%, 77%, and 94% for the respective regions. In terms of volume, the correlation coefficients between the segmentation results of the four HS regions and the gold standard were 0.95, 0.93, 0.96, and 0.96, respectively. Regarding asymmetry, the correlation coefficient between the segmentation result's right caudal minus left caudal and the corresponding gold standard was 0.91, while for right rostral minus left rostral, it was 0.93. Over time, we observed a decline in the volumes of the four HS regions and the total hippocampal volume of mild cognitive impairment (MCI) converters. Analysis of inter-group differences revealed that, except for the right rostral region in the ADNI dataset, the p-values for the four HS regions in the normal controls (NC), MCI, and AD groups from both datasets were all below 0.05. The right caudal hippocampal volume demonstrated correlation coefficients of 0.47 and 0.43 with the mini-mental state examination (MMSE) and Montreal cognitive assessment (MoCA), respectively. Similarly, the left rostral hippocampal volume showed correlation coefficients of 0.50 and 0.58 with MMSE and MoCA, respectively. CONCLUSIONS: Our framework allows for direct application to different brain magnetic resonance (MR) datasets without the need for training. It eliminates the requirement for complex image preprocessing steps while achieving segmentation accuracy comparable to deep learning (DL) methods even with small sample sizes. Compared to traditional active contour models (ACM) and atlas-based methods, our approach exhibits significant speed advantages. The segmented HS regions hold promise as potential biomarkers for studying the progression of AD.