Chinese Journal of Biomedical Engineering

Home

Editorial Board

Download

Quick Search

Office Online

Current Issue

Download Articles

Download

Links

2023 Vol. 42, No. 6 Published: 2023-12-20

Reviews Regular Papers Expert Consensus

Expert Consensus

	641	Chinese Expert Consensus on Automation and Routine Sequencing of Next-Generation Sequencing in Clinical Practice
		Laboratory Medicine Engineering Branch of Chinese Society of Biomedical Engineering
		DOI: 10.3969/j.issn.0258-8021.2023.06.001
		The matured automatically and routinely detection methods have not been generated since the overdecadeapplication of next-generation sequencing (NGS) in clinical practice. This consensus is oriented to the disciplines and applications of clinical NGS testing and provided relevant advices of constructing automatically and routinely path of clinical NGS, which was based on the current clinical application states and combined related testing products, consensus specifications and actual clinical demands from domestic and abroad. The consensus aimed at spreading the application, and promoting the entire level and the efficiency of precision medical services of clinical NGS in China.
		2023 Vol. 42 (6): 641-650 [Abstract] ( 375 ) HTML (1 KB) PDF (846 KB) ( 662 )

Regular Papers

	651	Stereo-Electroencephalography Guided Radiofrequency Thermocoagulation Prognosis Prediction Based on Brain Network Features of Patients with Refractory Epilepsy
		Yang Shuyao, Xie Yuhai, Gong Yuchen, Liu Qiangqiang, Zhang Puming
		DOI: 10.3969/j.issn.0258-8021.2023.06.002
		The outcome of radiofrequency thermocoagulation (RFTC) in different patients with refractory epilepsy is usually largely different. This study aimed to investigate graph theory indexes of brain networks and establish a RFTC prognosis prediction model. Based on the stereo-electroencephalography (SEEG) signals of 45 patients with refractory epilepsy before RFTC, a time-variant multi-variate autoregressive model was constructed. Spectrum-weighted time-variant partial directed coherence was computed to build an effective connectivity network of the brain and graph theory indexes of the effective connectivity network were analyzed. According to the Engel classification at least three months after RFTC, the patients were divided into RFTC responder group (Engel I & II) and RFTC non-responder group (Engel III). The graph theory indexes were used for statistical analysis between the two groups and for establishing prognosis prediction by support vector machine (SVM). The normalized average clustering coefficient (P=0.000) and small-worldness (P=0.022) of the patients in RFTC responder group were significantly higher than those in RFTC non-responder group, and the normalized characteristic path length was significantly lower than those in the RFTC non-responder group (P=0.032) (The normalized average clustering coefficient, the small-worldness and the normalized characteristic path length of the patients in the RFTC responder group were 0.995 3±0.000 2, 0.853 0±0.006 2 and 1.168 8±0.008 5, respectively. The normalized average clustering coefficient, small-worldness and normalized characteristic path length of the patients in RFTC non-responder group were 0.994 0±0.000 2, 0.833 5±0.005 6 and 1.194 4±0.008 0, respectively. Based on the three indexes, the accuracy of the prognosis prediction reached 81.97% by SVM. The RFTC prognosis prediction model based on the graph theory indexes (normalized average clustering coefficient, normalized characteristic path length, and small-worldness) of the effective connectivity networks before RFTC could effectively predict the postoperative outcome.
		2023 Vol. 42 (6): 651-658 [Abstract] ( 240 ) HTML (1 KB) PDF (3057 KB) ( 310 )

	659	Transfer Learning for Motor Imagery EEG Signals in Riemannian Manifold Tangent Space
		Xu Hui, He Hong, Zhang Huiming, Zhang Li
		DOI: 10.3969/j.issn.0258-8021.2023.06.003
		Aiming at the few-shot problem of motor imagery EEG signals, most of the existing analysis methods are based on Riemannian manifolds design classifiers after alignment in the manifold, or classify in Euclidean space after tangent space projection. It is complicated to design classifier operation in manifold, and direct classification in tangent space will lead to errors due to the inconsistency of tangent space distribution between the source and target domain. Therefore, a transfer learning algorithm based on Riemannian manifold was proposed in this study to classify motor imagery EEG signals. By calculating the covariance matrices of the source and target domain and obtaining their Riemannian mean as the tangent points, the covariance matrices were respectively mapped into the tangent spaces, and then the two tangent spaces were aligned by using a set of common feature bases to complete transfer learning. Three motor imagery datasets with 7, 9 and 9 subjects were used for validation, and there were 300, 144 and 120 samples in the three datasets, respectively. The performance of the algorithm was evaluated using classification accuracy, data distribution map and statistical methods. The average classification accuracy of the proposed algorithm on the three data sets is 81.45%, 77.14% and 66.94% respectively, which increased by 25.05%, 17.69% and 10.98% higher compared with that of the model without transfer learning. The Mann-Whitney U test verified that the difference between the classification results under the two models was statistically significant. Compared with other four comparison algorithms, the performance of the proposed algorithm was significantly different, which showed the superiority of the proposed algorithm. The proposed algorithm can effectively reduce the distribution difference of data between different domains, improve the classification accuracy of cross-subject data, and achieve the expansion of few-shot data to a certain extent.
		2023 Vol. 42 (6): 659-667 [Abstract] ( 239 ) HTML (1 KB) PDF (1949 KB) ( 228 )

	668	Identification of Paroxysmal Atrial Fibrillation Based on Integral Mean Mode Decompositionand Sample Entropy of Intrinsic Modal Functions
		Lu Lirong, Niu Xiaodong, Wang Jian, Zhang Xu
		DOI: 10.3969/j.issn.0258-8021.2023.06.004
		In order to solve the problem that the short duration of paroxysmal atrial fibrillation (PAF) can easily lead to false detection and missed detection, an identification algorithm based on integral mean mode decomposition (IMMD) and sample entropy of intrinsic mode function (IMFSE) was proposed in this paper. In this work, heart rate variability (HRV) signal fragments with a duration of 20 minutes were subjected to IMMD to obtain a series of intrinsic mode functions (IMFs). Then, the IMFSE was calculated, and next, the feature of PAF identification was extracted by statistical analysis of the IMFSE results. Finally, PAF identification was achieved by support vector machine and cross-validation. The PAF Prediction Challenge Database (AFPDB) provides ECG signals of normal subjects, patients with PAF attacks and patients far away from PAF attacks. From these signals, 25 HRV signal segments with a duration of 20 minutes were obtained, which constituted normal group, PAF attack group and PAF non-attack group. The performance of the proposed method in identification PAF episodes was evaluated with these 75 signals. Our proposed method obtained the values of 94%, 96% and 92% for the evaluation criteria of correct rate, sensitivity, and specificity, respectively. The experimental results showed that the PAF identification algorithm proposed in this paper provided a method basis for further automatic detection of PAF, and had a great application prospect in the long-term automatic detection and identification of PAF in wearable devices.
		2023 Vol. 42 (6): 668-676 [Abstract] ( 160 ) HTML (1 KB) PDF (1399 KB) ( 208 )

	677	Segmentation of Intracranial Hemorrhage in CT Images Based on Multi-Instance Learningand Thresholding Pseudo-Labels Extraction
		Zhang Tongyu, Li Enhui, Li Zhenyu, Cui Pengcheng, Zhang Weiwei
		DOI: 10.3969/j.issn.0258-8021.2023.06.005
		Intracranial hemorrhage is the bleeding caused by the rupture of intracranial blood vessels, and the volume of the hematoma is clinically important for treatment decision and prognosis analysis. The segmentation of the hematoma based on CT images is the basis of the volume measurement. Fully supervised methods rely on manually outlined labels, which are time-consuming and laborious, while existing weakly supervised segmentation methods have poor robustness and are prone to be affected by artifacts. To this end, this study proposed MIL-ICH, a multi-instance learning based weakly supervised network for intracranial hemorrhage segmentation. The network is composed of a two-branch structure. First, the multi-instance learning decoder generated heatmap to locate the hemorrhage area. Then, based on the heatmap, the pseudo-labels were extracted and optimized by CT value thresholding and pixel-adaptive refinement module to train the segmentation decoder. Finally, the two branches were trained simultaneously to improve training efficiency and leverage the multi-branch collaboration to further improve segmentation performance. The test results on 200 CT scans from the RSNA intracranial hemorrhage dataset showed that the Dice similarity coefficient and volume similarity of MIL-ICH reached 0.822 and 0.896, respectively. The correlation of the hematoma volume measured by this network with the actual hematoma volume is better than the ABC/2 estimation method commonly used in clinical practice. In conclusion, the method proposed in this work can improve the performance of weakly supervised segmentation of intracranial hemorrhage and benefit the volume measurement and prognostic evaluation for clinical purposes.
		2023 Vol. 42 (6): 677-686 [Abstract] ( 183 ) HTML (1 KB) PDF (10456 KB) ( 121 )

	687	Mitotic Detection in Breast Histopathology Images Using Local and Regional Hierarchical Information
		Cai Yu, Tang Qiling, Liu Ziyi
		DOI: 10.3969/j.issn.0258-8021.2023.06.006
		Statistically counting the number of mitotic cells in histological images of breast tumor tissue is an important diagnostic basis for the grading and prognosis of breast cancer. Currently, the counting tasks are performed manually by pathologists, which is a time-consuming and laborious task. To address this challenge, this paper proposed a method for mitotic detection in breast cancer pathology images from local to regional stratification. The framework as a whole consisted of two stages. The first stage was a cell localization network, which was responsible for screening and locating candidate mitotic cell blocks from whole section images while introducing a deep supervision mechanism with decoupled detection heads to enhance performance. The second stage was the mitotic cell validation network, which was responsible for further refining the classification of a large number of candidate cell image blocks by using a contextual fusion network based on a graph-attention mechanism to modulate the original response of local central blocks by integrating a large range of regional features to obtain more accurate classification results. We achieved F-Scores of 0.676, 0.809, and 0.797 on the ICPR MITOSIS 2014, ICPR MITOSIS 2012, and TUPAC16 datasets, respectively, using 960, 35, and 649 HPF as training sets, and 240, 15, and 7 HPF as test sets, respectively, where the recall rates all achieved optimal results of 0.878, 0.858 and 0.875, respectively. The results indicated that the proposed automatic detection method efficiently detected the cancer cells in the pathological sections, showing significant clinical application value.
		2023 Vol. 42 (6): 687-697 [Abstract] ( 200 ) HTML (1 KB) PDF (12913 KB) ( 86 )

	698	Prediction Model of Tumor Mutation Burden for Lung Adenocarcinoma Based on Pathological Tissue Slice
		Meng Xiangfu, Yang Ziyi, Yang Xiaolin, Hou Jiayue
		DOI: 10.3969/j.issn.0258-8021.2023.06.007
		Lung cancer is one of the deadliest malignancies, particularly non-small cell lung cancer (NSCLC), poses a significant threat to public health. Recent medical research has found out the crucial role of tumor mutation burden (TMB) in predicting the efficacy of immunotherapy and chemotherapy for cancer treatment. However, traditional methods for calculating TMB through genetic sequencing suffer from drawbacks, such as high detection costs, lengthy processing periods, and sample dependency. To address above problems, this paper proposed a novel deep learning model named as FCA-Former, which combined convolutional neural networks and self-attention mechanisms to predict TMB. The model employed CoAtNet as a backbone network, integrating coordinate attention and depth wise separable convolutions to enhance computational efficiency and global feature extraction capabilities from pathological tissue biopsy images. Experimental data sourced from the TCGA database comprised a dataset of lung adenocarcinoma digital pathology images, including 271 samples with high TMB levels and 66 samples with low TMB levels. The experimental results demonstrated the effectiveness of the proposed approach, achieving a remarkable maximumarea under the curve (AUC) of 98.1%. This AUC outperformed the state-of-the-art RcaNet method by 9.8%. The results of this study have significant implications for guiding prognostic and therapeutic strategies for NSCLC patients.
		2023 Vol. 42 (6): 698-709 [Abstract] ( 178 ) HTML (1 KB) PDF (6175 KB) ( 247 )

	710	Deep Learning Model Using DCE-MRI Mapping for Prediction of Response to NeoadjuvantChemotherapy in Breast Cancer
		Liu Xin, Fan Ming, Li Lihua
		DOI: 10.3969/j.issn.0258-8021.2023.06.008
		Neoadjuvant chemotherapy is helpful to improve the later survival rate of breast cancer patients, but the efficacy evaluation has a certain lag. Accurate evaluation of the efficacy of neoadjuvant chemotherapy can give medical doctors more effective clinical suggestions and implement more optimized treatment plans. In order to make better use of the spatial information of the image and the time series information of the enhanced image, a dynamic enhanced image mapping pattern map was proposed to predict the efficacy of neoadjuvant chemotherapy for breast cancer. The images of 208 patients with breast cancer before neoadjuvant chemotherapy were retrospectively collected. According to the Miller & Payne grading system, the data were labeled as response group and non-response group, and randomly divided into training set (126 cases) and test set (82 cases). After image preprocessing and segmentation of the region of interest, the maximum diameter of the tumor and its adjacent 7 slices were selected to construct the mapping mode map. The original slice image, multi-sequence images under different mapping modes and multi-sequence images under fusion two mapping modes were constructed by combining the enhanced time series. The deep learning network was used to predict the mapping pattern graph, the ROC curve of the prediction results was drawn, and the evaluation indicators such as AUC, sensitivity, specificity were calculated to evaluate the performance of the model type. Among them, the prediction model of multi-sequence images fused with two mapping modes achieved the best result, with an AUC of 0.832. Experimental results showed that compared with the original slice images, the method combining longitudinal time series images and spatial features between slices effectively improved the classification effect of neoadjuvant chemotherapy response prediction.
		2023 Vol. 42 (6): 710-719 [Abstract] ( 167 ) HTML (1 KB) PDF (6756 KB) ( 174 )

	720	Research on Multi-Label Viral Pneumonia Image Segmentation Method
		Wu Yihong, Yang Yong, Ye Hongwei, Wang Xiaozhuang, Sun Fangfang
		DOI: 10.3969/j.issn.0258-8021.2023.06.009
		Researches on the segmentation algorithm of COVID-19’s lesion are mostly based on the single-label segmentation algorithm, but the accuracy can’t reach the clinical criteria. In this paper, a new method of COVID-19’s lesion segmentation based on multi-label was proposed, training on COVID-19 Lung CT Lesion Segmentation Challenge-2020 dataset in the Grand Challenge. The dataset contains 179 cases, including 139 cases in the training set and the rest 40 cases in both of the validation and prediction set. We conducted lung regions with existing lung region segmentation model, which generated from LUNA16 dataset. The generated lung region label was incorporated with the lesion label to form the multi-label of training dataset. The One-Hot coding principle and improved 3D-UNet network model is used for training. This paper also proposed a new evaluation index, focus-lung ratio which was used to reflect the proportion of lesion regions in the lung and measured the model’s robustness with other indicators. In the end, the prediction’s Dice reached 70.10 %, which is 4.20 % higher than the single-label segmentation method under the same network. Besides, our results were compared with some published data, and ours displayed better performance, the validation’s accuracy of dataset reached 75.70 %. Experimental results showed that the proposed algorithm improved the accuracy of pneumonia lesion segmentation and the robustness of the model, therefore, is of clinical value and potential significance for future studies.
		2023 Vol. 42 (6): 720-729 [Abstract] ( 181 ) HTML (1 KB) PDF (6559 KB) ( 271 )

Reviews

	730	Progress in Application of Optically Pumped Magnetometers Magnetoencephalography
		Ji Mengqi, Shi Yujie, Xue Zhiyuan, Zhong Fan, Jiang Rui, Zhang Junpeng
		DOI: 10.3969/j.issn.0258-8021.2023.06.010
		Magnetoencephalography (MEG) , as a new technology for non-invasive acquisition of brain signals, can accurately reflect the neural activity of the brain, however, traditional MEG equipment requires low-temperature superconducting environment and high operation and maintenance costs, which limit the development of this technology. Optically pumped magnetometer is a new type of magnetic field strength detection device that has many advantages including relatively low cost, high signal-to-noise ratio, no need for cryogenic liquid helium cooling, and are expected to promote MEG technology to wider applications. Based on the concept of MEG, this paper introduced the implementation principle of the optical-pump magnetometer-magnetic encephalography system from a technical point of view, clarifies the naming confusions that are existing in the system, and summarized the application and research progress of the system from several aspects including neural speech decoding, MEG source reconstruction, functional neuroimaging, brain-computer interface, and clinical assistance, meanwhile, summarized the unique advantages of the new MEG system. The potential application of this technology in the future was prospected, and the possible problems in the current research were analyzed and discussed.
		2023 Vol. 42 (6): 730-739 [Abstract] ( 216 ) HTML (1 KB) PDF (2878 KB) ( 336 )

	740	A Review of Dynamic Causal Modelling Based on Neuronal Population Models
		Li Shuangyan, Yue Xuanya, Wang Longlong, Xu Guizhi
		DOI: 10.3969/j.issn.0258-8021.2023.06.011
		Brain is the most complex organ and plays functional roles through the complex neural networks consisted by the connections in various brain regions. Changes of the network characteristics are closely related to the physiological and pathological states of the brain. In recent years, there has been an increasing focus on brain network analysis algorithms. Among all the methods, dynamic causal modeling (DCM) has received extensive attention due to its biophysical plausibility. This article reviewed advances of DCM from the aspects of basic principles, neuron mass models and applications. After introducing DCM principle, the development of two kinds of neuron mass models: the convolutional based model and the conductance-based model were reviewed, sincethey play key role in the biophysical plausibility of the DCM algorithm. The application examples of DCM in the field of neural signal analysis related to cognitive function and disease pathology were further presented, indicating the effectiveness of DCM. Finally, the research progress and limitations of the DCM algorithm were summarized.
		2023 Vol. 42 (6): 740-749 [Abstract] ( 180 ) HTML (1 KB) PDF (4800 KB) ( 249 )

	750	Research Progress of Cognitive Linguistics Studies Based on Eye-Tracking Technology
		Ma Hengfen, Zhang Changjie
		DOI: 10.3969/j.issn.0258-8021.2023.06.012
		Bilingual individuals are competent to acquire, store and use two languages, demonstrating the cognitive competence of the human brain to control bilingualism. However, the language representation and processing process remain unclear. In recent years, the research has revealed that eye-tracking technology can identify and interpret linguistic cognitive processes and objectively express brain responses related to bilingual processing, which has become a new research direction and hotspot in the field of cognitive linguistics. Eye-tracking technology combining with brain imaging is the most promising research method for cognitive linguistics. This paper systematically reviewed the research on bilingual tasks and the related brain mechanism on account of eye-tracking technology and imaging technology as well as its application in the field of aphasia and dyslexia, meanwhile, clarified the positive effects of eye-tracking data analysis on the exploration of bilingual brain function, aiming to provide new thoughts for the investigation of bilingual processing brain mechanism.
		2023 Vol. 42 (6): 750-756 [Abstract] ( 252 ) HTML (1 KB) PDF (813 KB) ( 649 )

	757	The Mechanism and Applications of Cryoablation for Tumor
		Chen Mu, Liu Wei, Liu Baolin
		DOI: 10.3969/j.issn.0258-8021.2023.06.013
		Cryoablation is a non-invasive tumor therapy which carry out repeated freeze-thaw cycles with the aid of refrigerant (eg.nitrogen and helium), causing damage to the tumor tissues by ice crystals formation, microcirculation injury, apoptosis and cryo-immunologic response. In recent years, cryoablation has become an important treatment method for many types of tumors due to its less invasiveness, high targeting property and good visualization of the ice ball in cryotherapy. However, cryoablation still faces many difficulties, such as causing several kinds of complications and the freezing boundary is difficult to control. This paper reviewed the mechanism, technical features, application status, main advantages and disadvantages and development trend of cryoablation. At the same time, how to improve the complications of cryoablation by optimizing the freeze-thaw program and combining immunotherapy were also discussed. The challenges facing the complete ablation of large tumors were prospected and summarized.
		2023 Vol. 42 (6): 757-768 [Abstract] ( 320 ) HTML (1 KB) PDF (1700 KB) ( 349 )

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