Novel Pulmonary Nodule Position Detection Method Based on Multiscale Convolution / 中国医疗器械杂志

OBJECTIVE@#In order to improve the accuracy of the current pulmonary nodule location detection method based on CT images, reduce the problem of missed detection or false detection, and effectively assist imaging doctors in the diagnosis of pulmonary nodules.@*METHODS@#Propose a novel method for detecting the location of pulmonary nodules based on multiscale convolution. First, image preprocessing methods are used to eliminate the noise and artifacts in lung CT images. Second, multiple adjacent single-frame CT images are selected to be concatenate into multi-frame images, and the feature extraction is carried out through the artificial neural network model U-Net improved by multi-scale convolution to enhanced feature extraction capability for pulmonary nodules of different sizes and shapes, so as to improve the accuracy of feature extraction of pulmonary nodules. Finally, using point detection to improve the loss function of U-Net training process, the accuracy of pulmonary nodule location detection is improved.@*RESULTS@#The accuracy of detecting pulmonary nodules equal or larger than 3 mm and smaller than 3 mm are 98.02% and 96.94% respectively.@*CONCLUSIONS@#This method can effectively improve the detection accuracy of pulmonary nodules on CT image sequence, and can better meet the diagnostic needs of pulmonary nodules.

Automatic segmentation of organs at risk in head and neck carcinoma from radiation therapy using multi-scale fusion and attention based mechanisms / 中华放射肿瘤学杂志

Objective:To develop a multi-scale fusion and attention mechanism based image automatic segmentation method of organs at risk (OAR) from head and neck carcinoma radiotherapy.Methods:We proposed a new OAR segmentation method for medical images of heads and necks based on the U-Net convolution neural network. Spatial and channel squeeze excitation (csSE) attention block were combined with the U-Net, aiming to enhance the feature expression ability. We also proposed a multi-scale block in the U-Net encoding stage to supplement characteristic information. Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD) were used as evaluation criteria for deep learning performance.Results:The segmentation of 22 OAR in the head and neck was performed according to the medical image computing computer assisted intervention (MICCAI) StructSeg2019 dataset. The proposed method improved the average segmentation accuracy by 3%-6% compared with existing methods. The average DSC in the segmentation of 22 OAR in the head and neck was 78.90% and the average 95%HD was 6.23 mm.Conclusion:Automatic segmentation of OAR from the head and neck CT using multi-scale fusion and attention mechanism achieves high segmentation accuracy, which is promising for enhancing the accuracy and efficiency of radiotherapy in clinical practice.

A method for photoplethysmography signal quality assessment fusing multi-class features with multi-scale series information / 生物医学工程学杂志

Photoplethysmography (PPG) is often affected by interference, which could lead to incorrect judgment of physiological information. Therefore, performing a quality assessment before extracting physiological information is crucial. This paper proposed a new PPG signal quality assessment by fusing multi-class features with multi-scale series information to address the problems of traditional machine learning methods with low accuracy and deep learning methods requiring a large number of samples for training. The multi-class features were extracted to reduce the dependence on the number of samples, and the multi-scale series information was extracted by a multi-scale convolutional neural network and bidirectional long short-term memory to improve the accuracy. The proposed method obtained the highest accuracy of 94.21%. It showed the best performance in all sensitivity, specificity, precision, and F1-score metrics, compared with 6 quality assessment methods on 14 700 samples from 7 experiments. This paper provides a new method for quality assessment in small samples of PPG signals and quality information mining, which is expected to be used for accurate extraction and monitoring of clinical and daily PPG physiological information.

Non-rigid registration for medical images based on deformable convolution and multi-scale feature focusing modules / 生物医学工程学杂志

Non-rigid registration plays an important role in medical image analysis. U-Net has been proven to be a hot research topic in medical image analysis and is widely used in medical image registration. However, existing registration models based on U-Net and its variants lack sufficient learning ability when dealing with complex deformations, and do not fully utilize multi-scale contextual information, resulting insufficient registration accuracy. To address this issue, a non-rigid registration algorithm for X-ray images based on deformable convolution and multi-scale feature focusing module was proposed. First, it used residual deformable convolution to replace the standard convolution of the original U-Net to enhance the expression ability of registration network for image geometric deformations. Then, stride convolution was used to replace the pooling operation of the downsampling operation to alleviate feature loss caused by continuous pooling. In addition, a multi-scale feature focusing module was introduced to the bridging layer in the encoding and decoding structure to improve the network model's ability of integrating global contextual information. Theoretical analysis and experimental results both showed that the proposed registration algorithm could focus on multi-scale contextual information, handle medical images with complex deformations, and improve the registration accuracy. It is suitable for non-rigid registration of chest X-ray images.

Decreasing complexity of glucose time series derived from continuous glucose monitoring is correlated with deteriorating glucose regulation / 医学前沿

Most information used to evaluate diabetic statuses is collected at a special time-point, such as taking fasting plasma glucose test and providing a limited view of individual's health and disease risk. As a new parameter for continuously evaluating personal clinical statuses, the newly developed technique "continuous glucose monitoring" (CGM) can characterize glucose dynamics. By calculating the complexity of glucose time series index (CGI) with refined composite multi-scale entropy analysis of the CGM data, the study showed for the first time that the complexity of glucose time series in subjects decreased gradually from normal glucose tolerance to impaired glucose regulation and then to type 2 diabetes (P for trend < 0.01). Furthermore, CGI was significantly associated with various parameters such as insulin sensitivity/secretion (all P < 0.01), and multiple linear stepwise regression showed that the disposition index, which reflects β-cell function after adjusting for insulin sensitivity, was the only independent factor correlated with CGI (P < 0.01). Our findings indicate that the CGI derived from the CGM data may serve as a novel marker to evaluate glucose homeostasis.

Automated detection of sleep-arousal using multi-scale convolution and self-attention mechanism / 生物医学工程学杂志

In clinical, manually scoring by technician is the major method for sleep arousal detection. This method is time-consuming and subjective. This study aimed to achieve an end-to-end sleep-arousal events detection by constructing a convolutional neural network based on multi-scale convolutional layers and self-attention mechanism, and using 1 min single-channel electroencephalogram (EEG) signals as its input. Compared with the performance of the baseline model, the results of the proposed method showed that the mean area under the precision-recall curve and area under the receiver operating characteristic were both improved by 7%. Furthermore, we also compared the effects of single modality and multi-modality on the performance of the proposed model. The results revealed the power of single-channel EEG signals in automatic sleep arousal detection. However, the simple combination of multi-modality signals may be counterproductive to the improvement of model performance. Finally, we also explored the scalability of the proposed model and transferred the model into the automated sleep staging task in the same dataset. The average accuracy of 73% also suggested the power of the proposed method in task transferring. This study provides a potential solution for the development of portable sleep monitoring and paves a way for the automatic sleep data analysis using the transfer learning method.

Advances in methods and applications of single-cell Hi-C data analysis / 生物医学工程学杂志

Chromatin three-dimensional genome structure plays a key role in cell function and gene regulation. Single-cell Hi-C techniques can capture genomic structure information at the cellular level, which provides an opportunity to study changes in genomic structure between different cell types. Recently, some excellent computational methods have been developed for single-cell Hi-C data analysis. In this paper, the available methods for single-cell Hi-C data analysis were first reviewed, including preprocessing of single-cell Hi-C data, multi-scale structure recognition based on single-cell Hi-C data, bulk-like Hi-C contact matrix generation based on single-cell Hi-C data sets, pseudo-time series analysis, and cell classification. Then the application of single-cell Hi-C data in cell differentiation and structural variation was described. Finally, the future development direction of single-cell Hi-C data analysis was also prospected.

Multi-classification prediction model of lung cancer tumor mutation burden based on residual network / 生物医学工程学杂志

Medical studies have found that tumor mutation burden (TMB) is positively correlated with the efficacy of immunotherapy for non-small cell lung cancer (NSCLC), and TMB value can be used to predict the efficacy of targeted therapy and chemotherapy. However, the calculation of TMB value mainly depends on the whole exon sequencing (WES) technology, which usually costs too much time and expenses. To deal with above problem, this paper studies the correlation between TMB and slice images by taking advantage of digital pathological slices commonly used in clinic and then predicts the patient TMB level accordingly. This paper proposes a deep learning model (RCA-MSAG) based on residual coordinate attention (RCA) structure and combined with multi-scale attention guidance (MSAG) module. The model takes ResNet-50 as the basic model and integrates coordinate attention (CA) into bottleneck module to capture the direction-aware and position-sensitive information, which makes the model able to locate and identify the interesting positions more accurately. And then, MSAG module is embedded into the network, which makes the model able to extract the deep features of lung cancer pathological sections and the interactive information between channels. The cancer genome map (TCGA) open dataset is adopted in the experiment, which consists of 200 pathological sections of lung adenocarcinoma, including 80 data samples with high TMB value, 77 data samples with medium TMB value and 43 data samples with low TMB value. Experimental results demonstrate that the accuracy, precision, recall and F1 score of the proposed model are 96.2%, 96.4%, 96.2% and 96.3%, respectively, which are superior to the existing mainstream deep learning models. The model proposed in this paper can promote clinical auxiliary diagnosis and has certain theoretical guiding significance for TMB prediction.

Multimodal high-grade glioma semantic segmentation network with multi-scale and multi-attention fusion mechanism / 生物医学工程学杂志

Glioma is a primary brain tumor with high incidence rate. High-grade gliomas (HGG) are those with the highest degree of malignancy and the lowest degree of survival. Surgical resection and postoperative adjuvant chemoradiotherapy are often used in clinical treatment, so accurate segmentation of tumor-related areas is of great significance for the treatment of patients. In order to improve the segmentation accuracy of HGG, this paper proposes a multi-modal glioma semantic segmentation network with multi-scale feature extraction and multi-attention fusion mechanism. The main contributions are, (1) Multi-scale residual structures were used to extract features from multi-modal gliomas magnetic resonance imaging (MRI); (2) Two types of attention modules were used for features aggregating in channel and spatial; (3) In order to improve the segmentation performance of the whole network, the branch classifier was constructed using ensemble learning strategy to adjust and correct the classification results of the backbone classifier. The experimental results showed that the Dice coefficient values of the proposed segmentation method in this article were 0.909 7, 0.877 3 and 0.839 6 for whole tumor, tumor core and enhanced tumor respectively, and the segmentation results had good boundary continuity in the three-dimensional direction. Therefore, the proposed semantic segmentation network has good segmentation performance for high-grade gliomas lesions.

A three dimensional convolutional neural network pulmonary nodule detection algorithm based on the multi-scale attention mechanism / 生物医学工程学杂志

Early screening based on computed tomography (CT) pulmonary nodule detection is an important means to reduce lung cancer mortality, and in recent years three dimensional convolutional neural network (3D CNN) has achieved success and continuous development in the field of lung nodule detection. We proposed a pulmonary nodule detection algorithm by using 3D CNN based on a multi-scale attention mechanism. Aiming at the characteristics of different sizes and shapes of lung nodules, we designed a multi-scale feature extraction module to extract the corresponding features of different scales. Through the attention module, the correlation information between the features was mined from both spatial and channel perspectives to strengthen the features. The extracted features entered into a pyramid-similar fusion mechanism, so that the features would contain both deep semantic information and shallow location information, which is more conducive to target positioning and bounding box regression. On representative LUNA16 datasets, compared with other advanced methods, this method significantly improved the detection sensitivity, which can provide theoretical reference for clinical medicine.

Automatic segmentation of kidney tumor based on cascaded multiscale convolutional neural networks / 生物医学工程学杂志

The background of abdominal computed tomography (CT) images is complex, and kidney tumors have different shapes, sizes and unclear edges. Consequently, the segmentation methods applying to the whole CT images are often unable to effectively segment the kidney tumors. To solve these problems, this paper proposes a multi-scale network based on cascaded 3D U-Net and DeepLabV3+ for kidney tumor segmentation, which uses atrous convolution feature pyramid to adaptively control receptive field. Through the fusion of high-level and low-level features, the segmented edges of large tumors and the segmentation accuracies of small tumors are effectively improved. A total of 210 CT data published by Kits2019 were used for five-fold cross validation, and 30 CT volume data collected from Suzhou Science and Technology Town Hospital were independently tested by trained segmentation models. The results of five-fold cross validation experiments showed that the Dice coefficient, sensitivity and precision were 0.796 2 ± 0.274 1, 0.824 5 ± 0.276 3, and 0.805 1 ± 0.284 0, respectively. On the external test set, the Dice coefficient, sensitivity and precision were 0.817 2 ± 0.110 0, 0.829 6 ± 0.150 7, and 0.831 8 ± 0.116 8, respectively. The results show a great improvement in the segmentation accuracy compared with other semantic segmentation methods.

Optimized multi-scale entropy to localize epileptogenic hemisphere of temporal lobe epilepsy based on resting-state functional magnetic resonance imaging / 生物医学工程学杂志

Entropy model is widely used in epileptic electroencephalogram (EEG) analysis, but there are few reports on how to objectively select the parameters to compute the entropy model in the analysis of resting-state functional magnetic resonance imaging (rfMRI). Therefore, an optimization algorithm to confirm the parameters in multi-scale entropy (MSE) model was proposed, and the location of epileptogenic hemisphere was taken as an example to test the optimization effect by supervised machine learning. The rfMRI data of 20 temporal lobe epilepsy (TLE) patients with hippocampal sclerosis, positive on structural magnetic resonance imaging, were divided into left and right groups. Then, the parameters in MSE model were optimized by the receiver operating characteristic curves (ROC) and area under ROC curve (AUC) values in sensitivity analysis, and the entropy value of the brain regions with statistically significant difference between the groups were taken as sensitive features to epileptogenic hemisphere lateral. The optimized entropy values of these bio-marker brain areas were considered as feature vectors input into the support vector machine (SVM). Finally, combining optimized MSE model with SVM could accurately distinguish epileptogenic hemisphere in TLE at an average accuracy rate of 95%, which was higher than the current level. The results show that the MSE model parameter optimization algorithm can accurately extract the functional imaging markers sensitive to the epileptogenic hemisphere, and achieve the purpose of objectively selecting the parameters for MSE in rfMRI, which provides the basis for the application of entropy in advanced technology detection.

Research progress on multiscale entropy algorithm and its application in neural signal analysis / 生物医学工程学杂志

Changes in the intrinsic characteristics of brain neural activities can reflect the normality of brain functions. Therefore, reliable and effective signal feature analysis methods play an important role in brain dysfunction and relative diseases early stage diagnosis. Recently, studies have shown that neural signals have nonlinear and multi-scale characteristics. Based on this, researchers have developed the multi-scale entropy (MSE) algorithm, which is considered more effective when analyzing multi-scale nonlinear signals, and is generally used in neuroinformatics. The principles and characteristics of MSE and several improved algorithms base on disadvantages of MSE were introduced in the article. Then, the applications of the MSE algorithm in disease diagnosis, brain function analysis and brain-computer interface were introduced. Finally, the challenges of these algorithms in neural signal analysis will face to and the possible further investigation interests were discussed.

The Trans-Scale Conduction Behavior of Fluid Stimulation in Loaded Bone / 医用生物力学

Objective To investigate the conduction behavior of fluid flow induced by physiological loads at different scales of bone. Method sThe multiscale bone models were established by using the COMSOL Multiphysics software, and the fluid behaviors were investigated at macro-, meso- and micro-scale. Results At macro-meso scale，the distribution of pore pressure and fluid velocity of osteon near the periosteum and endoosteum were different from that in other parts. Due to the different structure and material parameters at different layers, the loading and fluid pressure caused different biomechanical responses in the process of transferring from macro-scale to micro-scale. Conclusions The multi-scale layered modeling of bone structure-osteon-lacunae-bone canaliculi was established, which provided the theoretical reference for deeper understanding of fluid stimulation and mechanotransduction.

Exploratory research into theories and system for membrane technology based on green manufacturing of Chinese materia medica-An emerging concept construction based on material-chemical engineering / 中草药

The implementation of membrane technology in the manufacturing of Chinese materia medica (CMM) plays a critical role in the strategic plan and demand from the perspective of national science and technology, and it is a new and high technology that needs to be popularized in Chinese medicine pharmaceutical industry. The manufacturing technology of CMM is primarily based on the theory and practices of chemical engineering in which the upgrade of its separation technology mainly relies on the advancement in chemical engineering. Our authors have been exploring and implementing membrane technology in the green manufacturing process of CMM in the past decade. Recently, we were granted funding in the topic of "The Modernization of Traditional Chinese Medicine" from The National Key Research and Development Program of China. In the research proposal, we introduced the emerging concept of "material-chemistry engineering", and suggested the concept of theoretical framework for "the process design and engineering of membrane-based green manufacturing of CMM". The framework included the establishment of analytical testing approach for precise analysis in aqueous CMM environment, a systematic testing and inspection method for the membrane and membrane process to guarantee the safety and effectiveness of the CMM products, as well as the integrated membrane process design and optimization for the CMM manufacturing process. The ultimate goal of the proposal is to achieve high flux and decent separation efficiency for CMM production in multi-scale range, in particular to understand the correlation between the aqueous CMM environment and the structure, property and preparation of the membrane. Furthermore, with the aid of computational modeling in process design and manufacturing, the theoretical foundation of membrane-based CMM green manufacturing can be assured. The innovation in the interdisciplinary of CMM production and material-chemistry engineering will help overcoming the current bottleneck encountered in the CMM manufacturing industry in China, resolving the urgent issues of energy, resources and environment, and providing a feasible solution to sustainable development.

Methodology and applications for multimodal identification of active constituents of traditional Chinese medicine / 中国中药杂志

The discovery of active constituents of traditional Chinese medicine(TCM) faces multiple challenges, such as limited approaches to evaluate poly-pharmacological effects, and the lack of systematic methods to identify active constituents. Aimed at these bottleneck problems in the field, the present study intensively discussed the key scientific problems in the identification of active constituents of TCM, based on scientific methodologies including systematology, information theory, and synergetics. A comprehensive strategy is herein proposed to investigate the correlations between the chemical composition and biological activities of TCM, from macro-, meso-, and micro-scales. Moreover, in this study, we systematically proposed the methodology of the multimodal identification of TCM active constituents, and thoroughly constructed its core technologies. Its technical framework is suggested to be assessed by multimodal information acquisition, centered on multisource information fusion, and focused on interaction evaluation. Furthermore, the core technologies for the multimodal identification of active constituents of TCM were developed in this study, which is according to the characteristics of the exchanges of between TCM and biological organisms, in the aspects of material, energy and information. Finally, two examples of the application of the proposed method were briefly introduced. The proposed methodology provides a novel way to solve the bottlenecks in the study of active constituents of TCM, and lays the foundation for the multimodal study of TCM.

Estimation by Inverse Approach of a Transmissivity Field over the Entire Continental Terminal Aquifer of Abidjan

Hydraulic characterization of aquifer systems is important for the development of exploitation scenarios and groundwater management strategies. Especially in lithologically heterogeneous aquifers, local scale variations in transmissivity (T) may not be neglected. Field scale transmissivity values are usually derived from pumping tests, but in most cases their number and availability are rather limited. Thus, direct measurement of transmissivity over an entire aquifer is expensive and technically almost impossible. In such situations, inverse hydrodynamic modelling is the appropriate solution. In this article, the real transmissivity field of the aquifer of the Continental Terminal of Abidjan is investigated by a multi-scale parametrization that allows to bypass the problem of scale change and to determine this hydrodynamic parameter over the entire aquifer. This hydrogeological modelling of the Continental Terminal aquifer identified a structure of 153 nodes in size as the closest structure to that of the Continental Terminal aquifer. The transmissivity field associated with this optimal size, ranging from 5.4.10-5 to 1 m2s-1, has been compared with values published in other studies in Africa and the world. These identified values are plausible and have a good overall structure. The success of this modeling is strongly linked to the quantity, quality and spatial distribution of authentic informations on the parameters sought.

A novel lesion detection algorithm based on multi-scale input convolutional neural network model for diabetic retinopathy / 中华实验眼科杂志

Objective To propose a multi-scale convolutional neural network ( CNN) based lesions detection method of fundus image,and evaluate its application in diabetic retinopathy ( DR) assisted diagnosis. Methods A multi-scale CNN based on lesions detection method of fundus image was proposed. Compared with the existing detection methods,the problem of poor robustness based on threshold segmentation and morphological segmentation was overcome. The idea of multi-scale grids detection without relying on manual pixel-by-pixel labeling was adopted in this algorithm,and the detection performance of small lesions was significantly improved. In addition, multiple DR lesions with high accuracy could be detected by the proposed loss function under the condition of weak labels and small data sets. Results At the level of lesions,the sensitivity and specificity of hard exudation lesions detection were 92. 17％ and 97. 17％,respectively. Compared with single-scale method,the sensitivity and accuracy of multi-scale method proposed in this paper increased by 7. 41％ and 5. 02％,respectively,and compared with other algorithm using the same public dataset IDRiD, the specificity of this algorithm increased by 55. 82％. This method could effectively detect the lesions in fundus images,and could give the basic range of the lesions. The average detection time of fundus images with a large number of lesions was 1. 59 seconds. Conclusions The DR lesions in the fundus image can be quickly and reliably identified,the location information of the lesions can be marked,and the influence of subjective factors can be reduced by using this algorithm, and it can be used to assist the clinician to conduct more effectively.

Hemodynamics Study of Internal Carotid Artery：A Comparison Between Unidirectional and Bidirectional Coupled Multi-Scale Model / 医用生物力学

Objective To compare the hemodynamic characteristics in internal carotid artery models, which were obtained by multi-scale unidirectional and bidirectional coupling models, so as to provide references for selecting models in further studies. Methods Based on the nuclear magnetic resonance image of one patient with mild stenosis of internal carotid artery, the lumped parameter model of the circle of Willis and the three-dimensional model of internal carotid artery were constructed. Those two different multi-scale models were constructed by unidirectional and bidirectional coupling. Results With the increase of stenosis degree, the inlet and outlet blood pressure and the outlet blood flow of internal carotid artery all decreased under two kinds of coupling method. The distribution of low time average wall shear stress (TAWSS) and high oscillatory shear index (OSI) of the internal carotid artery both increased with the increase of stenosis degree under two kinds of coupling method in general. The anterior cerebral artery segment showed lower shear stress and higher OSI with bidirectional coupling in 70% stenosis, and the blood flow direction of posterior communicating artery was changed, which was significantly different from unidirectional coupling results. Conclusions At a low degree of stenosis, the result of those two kinds of coupling method were consistent in general, but there was a significant difference in 70% stenosis, and the result of bidirectional coupling was closer to physiological parameters. The research findings can be better applied to the hemodynamic study of cerebrovascular diseases.

High quality reconstruction algorithm for cardiac magnetic resonance images based on multiscale low rank modeling / 生物医学工程学杂志

Taking advantages of the sparsity or compressibility inherent in real world signals, compressed sensing (CS) can collect compressed data at the sampling rate much lower than that needed in Shannon's theorem. The combination of CS and low rank modeling is used to medical imaging techniques to increase the scanning speed of cardiac magnetic resonance (CMR), alleviate the patients' suffering and improve the images quality. The alternating direction method of multipliers (ADMM) algorithm is proposed for multiscale low rank matrix decomposition of CMR images. The algorithm performance is evaluated quantitatively by the peak signal to noise ratio (PSNR) and relative norm error (RLNE), with the human visual system and the local region magnification as the qualitative comparison. Compared to L + S, kt FOCUSS, k-t SPARSE SENSE algorithms, experimental results demonstrate that the proposed algorithm can achieve the best performance indices, and maintain the most detail features and edge contours. The proposed algorithm can encourage the development of fast imaging techniques, and improve the diagnoses values of CMR in clinical applications.