Chinese Journal of Biomedical Engineering

Home

Editorial Board

Download

Quick Search

Office Online

Current Issue

Download Articles

Download

Links

2019 Vol. 38, No. 4 Published: 2019-08-20

Reviews Communications Regular Papers

Regular Papers

	385	The Comparative Study of Resting State EEG’s Power Spectral Entropy Between Schizophrenic and Depressive Patients
		Feng Jingwen, Lai Hongyu, Deng Wei, Zeng Jinkun, Zhang Junpeng, Li Tao
		DOI: 10.3969/j.issn.0258-8021.2019.04.1
		The aims of this paper were to investigate the power spectral entropy of the resting state EGG of schizophrenic (SC) and depressive (DP) patients and compare the performance of this index in these two kinds of diseases and to explore the reflection of this index on brain abnormalities of the two diseases. The subjects included 100 schizophrenia patients and 100 depression patients whose sex and age were matched (male: 50, female: 50). EEG was recorded under two conditions: (i) resting with eyes closed, and (ii) resting with eyes open. The signal preprocessing and the artifact correction were performed first. Power spectrum analysis was based on Welch transform, and the entropy of power spectrum was calculated by using relative power after normalization. At last, statistical analysis of the index was done by t-test and analysis of variance (ANOVA) through Matlab and SPSS. In any of the same states, the group average power spectral entropy of patients with schizophrenia was lower than that of patients with depression (lead average power spectrum entropy: closed-eye state: SC:1.26; DP:1.32; open eyes state: SC:1.33; DP:1.37), and the difference was significant on most leads (P<0.05). For all the subjects, the power spectral entropy in the closed-eye state was lower than that in the open eyes state. The decrease of the entropy from closed-eye state to open eyes state showed significant difference between the two groups in Fp1 and Fp2 leads (P<0.05) (Fp1:SC:0.08; DP:0.02;Fp2:SC:0.09; DP:0.02). In the closed-eye state, there was a difference in the asymmetry of power spectrum entropy between the left and right hemispheres of patients with schizophrenia and depression, and the schizophrenic group showed wider asymmetry (the pairs of electrodes with significant asymmetry: SC: 4 pairs, including F3-F4, O1-O2, F7-F8, T5-T6; DP: 2 pairs, including P3-P4, F7-F8). In the open eyes state, both of the two groups only showed significant asymmetry in the F7-F8, T5-T6 leads (P<0.05). In conclusion, the power spectrum entropy can sensitively and intuitively describe the distribution and irregularity of the power spectrum, and thus reflect the complexity of the EEG signal and the individual brain activity. The index could be used as an effective reference to distinguish between schizophrenia and depression, reflecting the difference in brain activity between the two diseases in the resting state.
		2019 Vol. 38 (4): 385-391 [Abstract] ( 373 ) HTML (0 KB) PDF (2531 KB) ( 560 )

	392	Quality Assessment of Fetal Head Ultrasound Images Based on Faster R-CNN
		Lin Zehui, Lei Baiying, Jiang Feng, Ni Dong, Chen Siping, Li Shengli, Wang Tianfu
		DOI: 10.3969/j.issn.0258-8021.2019.04.2
		The transthalamic plane of fetal is used to measure the biparietal diameter and head circumference of the fetus, and these two measurement parameters play an important role in predicting the fetal weight. Clinically, the plane has always been manually acquired by the ultrasound doctor, and the quality of the manually obtained plane is highly dependent on the clinical work experience of the doctor, which is time consuming, and the poor image quality for plane often happen. In order to overcome the problem of manual acquisition, we proposed a novel method for the quality assessment of fetal head ultrasound images based onfaster region-based convolutional neural networks (faster R-CNN), aiming to help doctors automatically, quickly and accurately obtain the standard transthalamic plane. Frist, we set up an evaluation protocol with the team of ultrasound experts and build a database of fetal head ultrasound images through data-enhanced methods. Second, faster R-CNN could learn from the training data to extract useful features, and through the use of joint training and alternative optimization, so that the regional proposal networks (RPN) module and fast R-CNN module shared the convolution layer features and built a complete end-to-end CNN object detection model to detect the key anatomical structures. Finally, the transthalamic plane was automatically scored by the results of the detected anatomical structure, and according to the score results, it was automatically determined whether the plane was a standard one. We collected 513 ultrasound planes, 80% was used as a training dataset and 20% as a test dataset. Our method could accurately locate the five anatomical structures of the transthalamic plane with an average accuracy of 80.7% and the examination time of each ultrasound image was approximately 0.27 s, which indicated that it was feasible to perform automated quality control of fetal head ultrasound images by the proposed method.
		2019 Vol. 38 (4): 392-400 [Abstract] ( 419 ) HTML (0 KB) PDF (12751 KB) ( 49 )

	401	YOLO V2 Network with Asymmetric ConvolutionKernel for Lung Nodule Detection of CT Image
		Li Xinzheng, Jin Wei, Li Gang, Yin Caoqian
		DOI: 10.3969/j.issn.0258-8021.2019.04.3
		Lung cancer has always been one of the serious threats to human health. As an important sign of early lung cancer, pulmonary nodules are of great significance in the early diagnosis and treatment of lung cancer. The traditional CT image lung nodule detection method is not only cumbersome, but also slow in processing speed, and the detection rate and positioning accuracy of the nodules need to be improved. This paper proposed a CT image lung nodule detection method based on the asymmetric convolution kernel YOLO V2 network. First, the continuous CT sequence was superimposed to construct a pseudo-color data set to enhance the difference between lesion and healthy tissue, which contained asymmetric volume. The inception V3 module of the accumulation was introduced into the YOLO V2 network to construct a deep network suitable for lung nodule detection. This aspect was drawn on the advantages of the YOLO V2 network in target detection, and on the other hand through the inception V3 module. The width and depth of the network were amplified to extract more abundant features; in order to further improve the positioning accuracy of the nodules, the design and calculation method of the loss function had also been improved. In order to verify the performance of the proposed test model, CT images of 1010 cases were selected from the LIDC-IDRI data set for training and testing. In lung nodules larger than 3 mm, the detection sensitivity was 94.25%, and the false positive rate was 8.50%. Experimental results showed that the lung nodule detection method proposed in this paper not only simplified the processing of lung CT images, but also was superior to traditional methods in nodule detection rate and positioning accuracy, providing a new way for lung nodule detection.
		2019 Vol. 38 (4): 401-408 [Abstract] ( 413 ) HTML (0 KB) PDF (6571 KB) ( 475 )

	409	Dynamic Large-Scale Functional Network Connectivity in Motor Imagery
		Zhang Tao, Jiang Chenyang, Li Mengchen, Yao Dezhong, Xu Peng
		DOI: 10.3969/j.issn.0258-8021.2019.04.4
		Motor imagery (MI) is a multidimensional high-level cognitive ability that is widely applied to brain-computer interface control and clinical rehabilitation. However, the underlying neural mechanisms behind the application of MI are still unclear. To further understand the underlying neural mechanisms of MI, we explored the dynamic large-scale brain network functional connectivity patterns of MI. Twenty-six healthy subjects were recruited for MI functional magnetic resonance scanning experiments. Based on the task fMRI data, first, the independent component analysis was used to obtain eleven large-scale functional sub-networks, and the time series corresponding to the sub-network was extracted. Then, we evaluated the dynamic network connectivity matrixes using the sliding window analysis method. Based on these connectivity matrices, we performed the cluster analysis resulting in state-dependent dynamic connectivity. Finally, the network statistical analysis method was used to evaluate the dynamic network difference in left-hand MI and right-hand MI. Results showed that the machine learning method could obtain data features more effectively, and the optimal window length based on data-driven was 31 time points, and the classification accuracy rate for left/right hand MI was 75.6%. The large-scale network connectivity pattern of MI was a state-dependent dynamic change process, resulting in 4 dynamic reconfiguration patterns. The specificity of large-scale dynamic network connectivity pattern during left-hand/right-hand MI mainly reflected by the interactions between the frontal-parietal network (FPN) and the dorsal attention network (DAN) and other sub-networks. Our findings provided new insights into the underlying neural mechanisms of MI.
		2019 Vol. 38 (4): 409-416 [Abstract] ( 376 ) HTML (0 KB) PDF (4605 KB) ( 266 )

	417	Digital Character Image Reconstruction on the Basis of Local Field Potential Signals of Pigeons
		Chen Shuli, Jiao Xingyang, Wang Zhizhong, Wang Songwei
		DOI: 10.3969/j.issn.0258-8021.2019.04.5
		The digital character image was reconstructed by the pigeon optic tectum neurons using local field potential signal (LFP) generated by visual image stimulation. The microelectrode array was used to record the LFP signal of the neuron under the stimulus of the digital image scanning screen. The Fourier transform was performed to extract the amplitude and phase characteristics. Then the reconstruction model was constructed by using the inverse filter algorithm, and the digital image was reconstructed. The cross-correlation coefficient was used to evaluate the reconstruct digital image. This study found out that with the optimal channel combination, according to the single-factor reconstruction test, the response delay time of neurons to visual stimuli under the reconstructed model was 0.01 s, the response duration was 0.55 s, and the frequency band range was 1 Hz< f₁<30 Hz、140 Hz< f₂<240 Hz. Under the optimal conditions of each single factor, the cross-correlation coefficient of the ten-digital characters images (0～9) reconstructed from 8 sets of data of 4 pigeons by reconstruction model exceed 0.90 compared with the original image, and the overall cross-correlation coefficient was 0.935±0.013.In short, the neuron response induced by the scanning visual stimulation pattern of digital images can reconstruct the visual stimulation image by means of information accumulation. It also showed that the amplitude and phase characteristics of the LFP signal represented the visual stimulation image better.
		2019 Vol. 38 (4): 417-423 [Abstract] ( 249 ) HTML (0 KB) PDF (3965 KB) ( 255 )

	424	Analysis of Crosstalk Pathways of Renal Clear Cell Carcinoma Based on Contribution Ranking
		Deng Jin, Kong Wei, Wang Shuaiqun, Mou Xiaoyang
		DOI: 10.3969/j.issn.0258-8021.2019.04.6
		Understanding biological processes based on gene signaling pathways exerts a significant function on exploring the pathogenesis of diseases. Current methods to measure the contribution of pathways to diseases usually rely on the number of differential expression genes in a single pathway, ignoring the effects of upstream and downstream perturbations in the pathway or crosstalk between the pathways. In this paper, a novel crosstalk analysis method based on pathway contribution ranking was proposed to analyze the influence of crosstalk between pathways on the pathogenesis of kidney renal clear cell carcinoma (KIRC). Firstly, the signal pathway impact analysis (SPIA) method was used to rank the KIRC-related pathways. Secondly, the distance correlation (DC) algorithm was applied to calculate the crosstalk between the high-contribution signal pathways in the diseased samples and control samples. Finally, those crosstalk pathways with a crosstalk change value higher than 0.1 were selected. Results showed that in 21 pathways with a crosstalk change value higher than 0.1, the difference of crosstalk relationship between the Epstein-Barr virus pathway and the ErbB signaling pathway was -0.12, the difference between the signal pathway of renal cell carcinoma and ErbB signal pathway was -0.20, the difference between Parkinson′s disease pathway and the pathway of protein processing in endoplasmic reticulum was -0.14. Also, there was a significant change among from 0.1 to 0.3 of crosstalk relationship between the signal pathway of Staphylococcus aureus infection and 11 signaling pathway. At the same time, molecular biological analysis verified that the significant changes of crosstalk between these pathways had an important effect on the occurrence and development of KIRC. This method could effectively explore the known and potential dysregulation-signaling pathway.
		2019 Vol. 38 (4): 424-430 [Abstract] ( 396 ) HTML (0 KB) PDF (3230 KB) ( 229 )

	431	Design and Application of the Wireless Remote Control System of Carp Robots
		Peng Yong, Wang Tingting, Yan Yanhong, Chen Zhiwang, Wen Shuhuan, Han Xiaoxiao, Zhao Yang, Liu Jianing, Zhang Qian
		DOI: 10.3969/j.issn.0258-8021.2019.04.7
		To overcome the obstacle of wire winding and motion restraint of aquatic animal robots, a wireless remote control system for carp robot′s brain electric stimulation was designed in this study. The system hardware included the wireless communication module, the electric stimulation signal generation module and the power supply module. The system software included the serial port communication setting and the motion mode selection. In this study, the brain electrode was implanted and sealed on the surface of the skull cavity, and the radio stimulator was placed in the waterproof package, and the underwater wireless stimulator mounted on the carp robot was remotely controlled by the upper computer for electrical stimulation. The electric stimulator was used to send signals through the electrodes to stimulate the brain motion area and control the movement of carp robots. Then the carp robots (n=10) were placed in the water maze for underwater experiments. The results showed that the forward, left and right steering movements of carp robots could be controlled by this system, with success rates of 60%, 70%, and 80% respectively. Our study indicated that this system and application methods were effective and feasible for the underwater wireless control of carp robots.
		2019 Vol. 38 (4): 431-437 [Abstract] ( 317 ) HTML (0 KB) PDF (5663 KB) ( 330 )

	438	Bone Healing Analysis of Transverse and Oblique Fracture Under Different Internal Fixation Parameters
		Fang Runxin, Ji Aimin, Chen Changsheng, Long Dengyan, Zhao Zhonghang
		DOI: 10.3969/j.issn.0258-8021.2019.04.8
		The aim of this work was to study the influences of internal fixation parameters on the fracture healing between transverse and oblique fracture. The second-development of Abaqus based on Python was used for the simulation of healing process. During the simulating process, the mechanical modulation and cell differentiation were integrated. The method of orthogonal experiment was used for studying the effects of parameters on the healing process, and different parameter combinations were constructed based on the orthogonal table of L₉(3⁴). Finally, an optimal combination was selected after the analysis. Results showed that the working length of the plate was the most influential parameter, a great divergence of healing pattern between transverse and oblique fracture was found under the low level of working length, the time of healing reached 1 000 MPa for transverse fracture was shorter than that for oblique fracture. Increased working length will drive the two fracture modes to show a similar healing pattern, their healing results finally reached or over 1400 MPa at the end of 16 weeks, which meant that a suitable mechanical environment for healing process could be ensured by omitting one or two screws that were proximal to the fracture gap. The healing efficiency of both the transverse and oblique fracture was highly correlated with the choice of internal fixation parameters. Compared with transverse fracture, oblique fracture required higher standard of stability for fracture healing, therefore, more screws were needed for the oblique fracture to ensure the stability.
		2019 Vol. 38 (4): 438-446 [Abstract] ( 312 ) HTML (0 KB) PDF (2817 KB) ( 236 )

	447	Fabrication and Characterization of Three-Dimensional Porous Electromagnetic Composite Scaffolds
		Xu Xuegai, Wu Fengxin, Gao Aijun, Meng Jie,Wen Tao, Liu Jian, Xu Lianghua, Xu Haiyan
		DOI: 10.3969/j.issn.0258-8021.2019.04.9
		Objective: To mimic the tissue structure and physiological function of extracellular matrix (ECM) to fabricate electromagnetic nanofibrous scaffolds that are favorable for cell adhesion, proliferation and differentiation.Nanofibrous films were fabricated by coaxial electrospinning with gelatin as shell layer and polylactic acid (PLA) as core layer; meanwhile, magnetic nanoparticles (MNP) were added into the gelatin and PLA. The obtained nanofibrous films were pulverized and blended with carbon fiber (CF), followed by freeze-drying and crosslinking treatment to obtain three-dimensional (3D) porous scaffolds. The morphology and structure of the scaffolds were observed by scanning electron microscope (SEM) and transmission electron microscope (TEM). The hysteresis loop was measured by vibrating sample magnetometer, the conductivity was measured using four point probe, and compression tests were carried out by universal material testing machine. The density and water absorption were also measured. CCK-8 and Western Blot were used to analyze the viability and function of the cells on the scaffolds. The scaffolds showed porous honeycomb microstructure, the pores were perforated with eachother. When CF content was 0, 1, 3 and 5 mg/mL, the density of scaffolds was 73.07, 72.56, 65.88 and 63.34 mg/cm³, the water absorption was 1164.60%, 1186.48%, 1284.835% and 1323.66%, the conductivity was 0, 0.0088, 0.2467 and 2.6625 s/m, and the saturated magnetization strength was 3.68, 3.15, 2.45 and 2.90 emu/g, respectively. The scaffolds up-regulated the expression of Cx43 and RhoA, as well as supported the growth of cardiomyocytes. The 3D porous electromagnetic composite scaffolds had both superparamagnetism and conductivity, the mechanical property was significantly improved by CF. The scaffolds supported growth and promoted the maturation of cardiomyocytes.
		2019 Vol. 38 (4): 447-454 [Abstract] ( 239 ) HTML (0 KB) PDF (5675 KB) ( 213 )

	455	The Preparation and Biological Study of Amphiphilic Glycopolypeptides as Liver-Targeted Theranostic Nanoparticles
		Lai Shengsheng, Liu Qiancheng, Jin Haoyu, Liu Wenping, Zhu Huier
		DOI: 10.3969/j.issn.0258-8021.2019.04.10
		In this work, amphiphilic glycopolypeptides were synthesized by a sequential ring opening polymerization of ε-carbobenzyloxy-L-lysine N-carboxyanhydride and glutamic acid based N-carboxyanhydride monomer. Galactosyl sugar units as targeting ligands were conjugated to the polypeptides block via an efficient click reaction. The chemical structures of the obtained glycopolypeptides were characterized by Fourier transform infrared spectroscopy and nuclear magnetic resonance analysis. Glycopolypeptides base nanoparticles were prepared by dialysis method in aqueous solution, followed by characterized with fluorometry, transmission electron microscopy and dynamic light scattering. The biological activity was demonstrated by selective lectin binding experiments. The cytotoxicity of the glycopolypeptides was investigated by MTT test. Furthermore, liver targeted theranostic nanoparticles were prepared by using glycopolypeptides acted as nano-cargo to load near infrared dyes IR780. The cellular uptake, photothermal therapy effect and in vivo tumor imaging were investigated by using fluorescence imaging, quantitative flow cytometry and in vivo imaging system. Results indicated that the amphiphilic glycopolypeptides were obtained via the combination of ring open polymerization and “click” reaction. Own to their amphiphilic property, glycopolypeptides self-assembled into spherical nanoparticles with about 85 nm in diameter in an aqueous medium once the concentration was over 0.015 μg/mL. MTT results revealed that the glycopolypeptides nanoparticles was nontoxic to HepG2 cells and HUVECs even the concentration was up to 500 μg/mL. Fluorescence microscope revealed the specific recognition between glycopolypeptides and ricin agglutinin. According to the flow cytometry results, glycopolypeptides nanoparticles could deliver IR780 into the HepG2 cells effectively. Photothermal therapy study revealed that higher doses of IR-780 killed more tumor cells after laser irradiation at 808 nm. In vivo NIRF imaging shown that the theranostics nanoparticles were mainly accumulated in the tumor mass, even after 24 h, strong flourescence signals were still detected from the tumor mass. The glycopolypeptides were demonstrated promising tumor targeting theranostic nanocarriers.
		2019 Vol. 38 (4): 455-463 [Abstract] ( 278 ) HTML (0 KB) PDF (6019 KB) ( 221 )

Reviews

	464	Deep Learning in EEG Decoding: A Review
		Wei Mengying, Li Linling, Huang Gan, Tang Fei, Zhang Zhiguo
		DOI: 10.3969/j.issn.0258-8021.2019.04.11
		In recent years, deep learning algorithms have been developed rapidly, and they are becoming a powerful tool in biomedical engineering. Especially, there has been an increasing focus on the use of deep learning algorithms for decoding physiological, psychological or pathological states of the brain from EEG. This paper overviews current applications of deep learning algorithms in various EEG decoding tasks, and introduces commonly used algorithms, typical application scenarios, important progresses and existing problems. Firstly, we briefly describe the basic principles of deep learning algorithms used in EEG decoding, including convolutional neural network, deep belief network, auto-encoder and recurrent neural network. Then this paper discusses existing applications of deep learning on EEG, including brain-computer interfaces, cognitive neuroscience and diagnosis of brain disorders. Finally, this paper outlines some key issues that need to be addressed in future applications of deep learning for EEG decoding, such as parameter selection, computational complexity, and the capability of generalization.
		2019 Vol. 38 (4): 464-472 [Abstract] ( 422 ) HTML (0 KB) PDF (1092 KB) ( 1167 )

	473	Application of Low-Temperature Atmospheric-Pressure Plasma in Oncology
		Qi Ying, Yu Mengjie, Hou Zhongyu, Yao Yu
		DOI: 10.3969/j.issn.0258-8021.2019.04.12
		Plasma medicine is an emerging field focusing on the application of plasma in medicine. In this review, we provided a brief overview of the low-temperature atmospheric-pressure plasma (LT-APP) first, and then focused on the application of LT-APP in oncology. In oncological application, direct plasma treatment to tumor cells can induce the apoptosis, necrosis and autophagy by generating large amounts of reactive agents; Plasma can also kill the cancer cells indirectly via the cytotoxicity of plasma activated liquids. On the other hand, plasma also has several non-fatal effects on tumors as well. In addition, plasma plays an important role in the field of anti-cancer drugs by participating in the construction of sustained-release systems of chemotherapeutic drugs, assisting drug transportation, and having a synergistic anti-tumor effect with traditional chemotherapeutic drugs.
		2019 Vol. 38 (4): 473-480 [Abstract] ( 314 ) HTML (0 KB) PDF (851 KB) ( 372 )

	481	Progress of Separation and Enrichment of Rare Cells from Blood
		Song Wanyun, Wang Huiyu, Wang Mingming, Zhang Tao
		DOI: 10.3969/j.issn.0258-8021.2019.04.13
		In recent years, high-efficiency, high-purity enrichment or capture of rare cells that containing less than 100 per milliliter of blood, and non-destructive release of captured target cells are hot research topics in the field of precise tumor treatment and early disease diagnosis. Among them, the enrichment of rare cells such as circulating tumor cells (CTCs) and fetal nucleated red blood cells (NRBCs) are the most extensive. Aiming at these two kinds of rare cells, we summarized the research progress in the field from the perspectives of separation and enrichment principle, experimental methods and separation efficiency, and analyzed the advantages and disadvantages of various methods. On the whole, the separation principle and methods of rare cells can be roughly divided into physical sorting method and immunoaffinity method. The former utilizes the physical characteristics of rare cells such as size and hydrodynamics. While in the later method, rare cells are isolated and enriched by utilizing the differences caused by the immunoaffinity reactions of specific receptors and antibodies, as well as the nucleic acid aptamers on the cell surfaces. In addition, we further introduced the physical properties of rare cells and the application of emerging technologies such as nanotechnology, microfluidics and single cell manipulation in the field of separation and enrichment of rare cells, and briefly compared various separation methods.
		2019 Vol. 38 (4): 481-489 [Abstract] ( 321 ) HTML (0 KB) PDF (5660 KB) ( 300 )

	490	Progress on Applications of Poly(Vinyl Amine) and its Derivativesin Biomedical Engineering
		Zhu Wenxian, Yuan Ming, Tang Huadong,
		DOI: 10.3969/j.issn.0258-8021.2019.04.14
		Poly(vinyl amine) (PVAm) is a water soluble macromolecule containing the highest primary amine groups among all amino polymers. PVAm is featured by its polycation property, pH-responsive behaviour and high reactive activity, and has various applications in biomedical science, petrochemical engineering, paper manufacturing, textile printing, and wastewater treatment. In this work, the research progress on the applications of PVAm and its derivatives in biomedical engineering was reviewed and the research results produced in recent ten years in the fields of gene transfection, drug therapy and tissue engineering were summarized. The advantages and disadvantages of PVAm and its derivatives in these fields were comparatively analyzed and the development tendency in these technology areas was presented, which could provide forward guidance for the design and synthesis of PVAm derivatives and the exploration of their applications in biomedical engineering.
		2019 Vol. 38 (4): 490-497 [Abstract] ( 492 ) HTML (0 KB) PDF (4316 KB) ( 362 )

	498	The Effect of Calcium Phosphate Scaffold on Angiogenesis
		Tan Yanlin, Luo Chunyuan, Chen Kairui, Zhang Qiang, Xiong Bokai,Liu Xiupiao, Yang Peipei, Yang Yuchen
		DOI: 10.3969/j.issn.0258-8021.2019.04.15
		Angiogenesis in scaffold materials can increase the volume of osteogenesis and the success rate of bone product transplantation, therefore is one crucial condition for bone tissue formation. Researches of vascular networks in scaffold materials or induce angiogenesis in osteogenesis by scaffold materials have been intensively conducted woldwide. Calcium phosphate is the most commonly used scaffold material in bone tissue engineering research. Studies have demonstrated that it can be given good bone conduction and osteoinductivity through structural optimization, but the application research of calcium phosphate scaffold has not fully realized its angiogenesis meaning. This article reviewed the effects of calcium phosphate scaffolds on angiogenesis and addressed the importance of angiogenesis in bone tissue engineering.
		2019 Vol. 38 (4): 498-502 [Abstract] ( 283 ) HTML (1 KB) PDF (755 KB) ( 184 )

Communications

	503	Prostate Cancer Recognition Algorithm Based on Deep Learning
		Zhang Haowei, Ren Xiaoqian, Liu Ying, Lou Yunzhong
		DOI: 10.3969/j.issn.0258-8021.2019.04.16

		2019 Vol. 38 (4): 503-507 [Abstract] ( 392 ) HTML (0 KB) PDF (3350 KB) ( 229 )

	508	Multi-Parameter Analysis and Application of Diffusion Weighted Imaging in Prostate Cancer Based on Machine Learning
		Sun Xiaomeng, Wan Suiren
		DOI: 10.3969/j.issn.0258-8021.2019.04.17

		2019 Vol. 38 (4): 508-512 [Abstract] ( 265 ) HTML (0 KB) PDF (2353 KB) ( 381 )

Copyright © Editorial Board of Chinese Journal of Biomedical Engineering
Supported by:Beijing Magtech