Biomedical Signal Processing and Control最新文献

{"title":"Synergistic perception: Fusing expert knowledge and foundation models for semi-supervised mammogram segmentation","authors":"Jiaju Huang ,&nbsp;Xin Wang ,&nbsp;Xiangyu Xiong ,&nbsp;Shaobin Chen ,&nbsp;Yue Sun ,&nbsp;Ka-Hou Chan ,&nbsp;Tong Tong ,&nbsp;Qinquan Gao ,&nbsp;Yi Xu ,&nbsp;Shuo Li ,&nbsp;Tao Tan","doi":"10.1016/j.bspc.2025.108633","DOIUrl":"10.1016/j.bspc.2025.108633","url":null,"abstract":"<div><div>Mammography is essential for the early detection of breast cancer, but accurately segmenting complex tissue structures across varying scales remains challenging due to data scarcity and inherent structural variability. We introduce the Synergistic Perception Framework (SPF), a novel approach that integrates specialized components operating at different scales to enhance segmentation performance. The SPF consists of three key components: (1) Expert Unit Models (EUMs) that capture fine-grained, class-specific details; (2) a Hierarchical Feature Fusion Network (HFF-Net) that integrates deep contextual information with localized features through a category-adaptive feature decoupling decoder; and (3) a progressive pseudo-label refinement strategy that leverages unlabeled data. This process uses consistency regularization for initial pseudo-label generation followed by targeted fine-tuning of the Segment Anything Model (SAM) to produce high-quality segmentation targets. Experimental results demonstrate that SPF outperforms existing methods on the segmentation of 11 anatomical structures across multiple test sets, improving the average Dice score by 13.27 percentage points on CSAW-S and 10.1 percentage points on INbreast compared to state-of-the-art (SOTA) methods. The framework particularly excels in segmenting small and complex structures, validating the effectiveness of our multi-scale approach. The code will be made publicly available upon acceptance.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108633"},"PeriodicalIF":4.9,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Active learning in latent spaces for long-term ECG monitoring: Morphology and rhythm analysis","authors":"Roberto Holgado–Cuadrado ,&nbsp;Carmen Plaza–Seco ,&nbsp;Francisco Manuel Melgarejo-Meseguer ,&nbsp;José Luis Rojo-Álvarez ,&nbsp;Manuel Blanco–Velasco","doi":"10.1016/j.bspc.2025.108622","DOIUrl":"10.1016/j.bspc.2025.108622","url":null,"abstract":"<div><div>Electrocardiogram (ECG) processing systems based on deep learning offer potential for advanced cardiac analysis. However, these systems often encounter significant challenges, such as the scarcity of labeled data, which affects their performance, reliability, and integration into clinical practice. This study aims to address these challenges by proposing an Active Learning (AL) methodology to optimize data labeling, reducing annotation effort while improving model performance. We evaluate the AL approach across three distinct applications: (1) sinus rhythm beat classification using synthetic data; (2) clinical severity of noise classification with a long-term ECG monitoring repository acquired under real conditions; and (3) cardiac wave delineation using a gold-standard dataset with expert annotations from the publicly available PhysioNet QT Database (QTDB) and the Lobachevsky University ECG Database (LUDB). In each classification task, our proposed AL framework integrates a neural network based on an autoencoder that generates a visualizable latent space for explainability into the decision-making process. The system iteratively selects the most informative instances using a margin sampling strategy in the latent space and incorporates them into the training process to refine performance. Results demonstrate that the AL approach consistently outperforms random sample selection in precision, recall, and F1-score. Additionally, ECG in-line analysis shows that models trained with the AL strategy outperform those from previous studies, even when trained on smaller subsets of the experimental datasets. This approach can reduce the labeling workload of clinicians, helping to efficiently increase labeled data, improve model performance, foster confidence in decision support systems, and advance ECG analysis applications.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108622"},"PeriodicalIF":4.9,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BioMIFormer: Biologically inspired spatiotemporal transformer for motor imagery EEG interpretation","authors":"Mengxue Liu,&nbsp;Jing Wang,&nbsp;Wanyi Liu,&nbsp;Bingfeng Zhang,&nbsp;Yanjiang Wang","doi":"10.1016/j.bspc.2025.108648","DOIUrl":"10.1016/j.bspc.2025.108648","url":null,"abstract":"<div><div>Electroencephalography (EEG) provides a high temporal resolution into brain activity, yet many existing decoding models overlook its neurophysiological basis, limiting the ability to capture both temporal and spatial dynamics effectively. To address this, we propose BioMIFormer, a Biologically Inspired Spatiotemporal Transformer that integrates neuroscientific insights into the functional architecture of motor imagery (MI)-related brain regions. BioMIFormer simulates functional divisions of the motor cortex through three parallel branches for temporal, spatial, and spatiotemporal feature encoding. It incorporates a biologically inspired temporal modeling mechanism, a multi-scale spatial extraction strategy, and a Transformer-based attention fusion module to capture long-range dependencies and cross-modal relationships in EEG signals. Different from the traditional feature fusion methods, BioMIFormer aligns its modular design with the brain’s functional architecture, enhancing both interpretability and decoding accuracy. Experimental results on two public MI-EEG datasets demonstrate that BioMIFormer achieves state-of-the-art performance, validating the effectiveness of biologically inspired modeling in EEG analysis.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108648"},"PeriodicalIF":4.9,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HetMS-AMRGNN: Heterogeneous multi-scale graph neural network for antimicrobial drug recommendation in electronic health records","authors":"Zhengqiu Yu ,&nbsp;Yueping Ding ,&nbsp;Zhongnan Weng ,&nbsp;Xiangrong Liu","doi":"10.1016/j.bspc.2025.108570","DOIUrl":"10.1016/j.bspc.2025.108570","url":null,"abstract":"<div><h3>Objective:</h3><div>To develop a novel heterogeneous graph representation learning approach for antimicrobial drug recommendation in intensive care units (ICUs) that effectively addresses the complexities of combination therapy and heterogeneous electronic health records (EHRs) data.</div></div><div><h3>Methods:</h3><div>We propose HetMS-AMRGNN, which represents EHR data as a heterogeneous graph with multiple types of nodes and edges capturing clinical relationships. The model employs multi-view feature extraction and multi-scale graph convolution to capture structural information at different scales, while using metapath-based aggregation to integrate diverse semantic relationships. A hierarchical contrastive learning mechanism is introduced to handle intra-node heterogeneity, and the node representations are enhanced with historical diagnosis and drug–drug interaction knowledge for accurate prediction.</div></div><div><h3>Results:</h3><div>Experimental validation on real-world ICU EHR data demonstrates that HetMS-AMRGNN significantly outperforms existing approaches in antimicrobial drug recommendation tasks. The model shows particular strength in recommending combination therapies, effectively capturing complex patient characteristics and drug interaction patterns.</div></div><div><h3>Conclusion:</h3><div>HetMS-AMRGNN provides an effective solution for antimicrobial drug recommendation in ICU settings, successfully addressing the challenges of combination therapy and heterogeneous data integration. The model’s superior performance, particularly in complex cases requiring combination therapy, suggests its potential for improving antimicrobial prescribing practices in critical care.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108570"},"PeriodicalIF":4.9,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing brain tumor classification with a novel attention based explainable deep learning framework","authors":"Md Jahid Hasan ,&nbsp;Mahmudul Hasan ,&nbsp;Sumya Akter ,&nbsp;Abu Bakar Siddique Mahi ,&nbsp;Md Palash Uddin","doi":"10.1016/j.bspc.2025.108636","DOIUrl":"10.1016/j.bspc.2025.108636","url":null,"abstract":"<div><div>Accurate and early detection of brain tumors is essential for effective treatment planning in medical diagnosis. However, deep learning (DL) models often struggle with MRI-based tumor detection due to significant variability in tumor size, shape, and location. Traditional diagnostic techniques are limited by subjectivity and low interpretability, while many DL models operate as black boxes, reducing clinical trust. Incorporating attention mechanisms can help by directing the model’s focus to the most informative regions of an image, thus improving both accuracy and interpretability. However, existing attention methods often fail to capture the complex spatial and contextual features present in medical images such as MRI scans. In this study, we propose a novel attention-based, explainable DL framework designed to improve the performance and transparency of brain tumor diagnosis. We introduce the Strip-Style Pooling Attention Network (SSPANet), which combines the strengths of channel and spatial attention mechanisms to more effectively capture intricate imaging features. We evaluated SSPANet using VGG16 and ResNet50 as backbone architectures, integrating it alongside existing attention methods for comparison. Among all configurations, ResNet50 combined with SSPANet achieves the best results, with 97% accuracy, precision, recall, and F1-score, along with 95% Cohen’s Kappa and Matthews Correlation Coefficient. For interpretability, we employ GradCAM, GradCAM++, and EigenGradCAM across attention-guided DL models. The ResNet50 + SSPANet + GradCAM++ combination consistently provides superior visual explanations, highlighting SSPANet’s ability to capture complex spatial-contextual information effectively. We also offer a theoretical analysis to support the efficiency and effectiveness of the proposed attention mechanism.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108636"},"PeriodicalIF":4.9,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DMID-ESD: A Benchmark Darkfield Microscopy Image Dataset for Erythrocytes and Spirochaete Detection and Classification","authors":"Guotao Lu ,&nbsp;Zizhen Fan ,&nbsp;Minghe Gao ,&nbsp;Jing Chen ,&nbsp;Qingtao Meng ,&nbsp;Hechen Yang ,&nbsp;Hongzan Sun ,&nbsp;Tao Jiang ,&nbsp;Yudong Yao ,&nbsp;Marcin Grzegorzek ,&nbsp;Chen Li","doi":"10.1016/j.bspc.2025.108595","DOIUrl":"10.1016/j.bspc.2025.108595","url":null,"abstract":"<div><div>Since the analysis of erythrocytes and spirochaetes is highly relevant to human health, their automated detection is of significant importance in both medical and computer vision research. However, publicly available datasets in this domain remain scarce. To address this gap, we present the Darkfield Microscopy Image Dataset for Erythrocytes and Spirochaete Detection (DMID-ESD), which consists of 11,794 fully annotated images with labels containing categorical and localization information. We perform comprehensive benchmarking experiments on DMID-ESD to evaluate its utility in tasks such as image classification, object detection, and feature extraction. The results demonstrate that the dataset serves as an effective benchmark for method evaluation. The DMID-ESD dataset is freely available for non-commercial use at: <span><span>https://figshare.com/articles/dataset/DMID-ESD_zip/22179311</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108595"},"PeriodicalIF":4.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Calculation of approximate heart rate variability indicators based on low-resolution heart rate data provided by widely used commercially available wearable devices","authors":"Xue Li ,&nbsp;Goh Onoguchi ,&nbsp;Hiroshi Komatsu ,&nbsp;Chiaki Ono ,&nbsp;Noriko Warita ,&nbsp;Zhiqian Yu ,&nbsp;Atsuko Nagaoka ,&nbsp;Sho Horikoshi ,&nbsp;Kenji Iwabuchi ,&nbsp;Kohei Fuji ,&nbsp;Mizuki Hino ,&nbsp;Yuta Takahashi ,&nbsp;Hisashi Ohseto ,&nbsp;Natsuko Kobayashi ,&nbsp;Saya Kikuchi ,&nbsp;Yasuto Kunii ,&nbsp;Taku Obara ,&nbsp;Shinichi Kuriyama ,&nbsp;Noriyasu Homma ,&nbsp;Parashkev Nachev ,&nbsp;Hiroaki Tomita","doi":"10.1016/j.bspc.2025.108579","DOIUrl":"10.1016/j.bspc.2025.108579","url":null,"abstract":"<div><div>Heart rate variability (HRV) assessment using wearable technology is a valuable tool for monitoring physical and emotional health. However, many widely used wearable devices, such as those from Apple and Fitbit, do not provide high-resolution heart rate (HR) data (i.e., data for every heartbeat) but instead report low-resolution data, typically as average HR values over fixed intervals (e.g., every 5 s). In this study, we developed algorithms to estimate HRV indicators from such low-resolution HR data and evaluated their reliability and accuracy. High-resolution HR data were collected over one week from 154 pregnant women (aged 25–44 years, 23–32 weeks gestation) using a chest-worn portable HR monitor. The average HR over each 5-second interval was calculated to match Fitbit’s data format. HRV indicators were computed from the reconstructed low-resolution data and compared with those from the original high-resolution data using two one-sided tests of equivalence (TOST), correlation analysis, and principal component analysis (PCA). Additional validation using Bland–Altman plots and bootstrap-derived confidence intervals assessed estimation stability. All analyses indicated high similarity between estimated and reference HRV values. TOST confirmed statistical equivalence (p &lt; 0.05) with negligible effect sizes (Cohen’s d &lt; 0.1). Correlation coefficients ranged from 0.714 to 0.921, and PCA yielded a similarity index of 0.95. The algorithms demonstrated robustness through equivalence testing, distributional similarity, error stability, and cross-cohort generalizability. Further validation using both high- and low-resolution HR datasets from publicly available databases supported these findings. These results suggest that HRV indicators derived from low-resolution HR data may be sufficiently accurate for clinical and everyday health monitoring.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108579"},"PeriodicalIF":4.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SKF-YOLO: An enhanced method for real-time blood cell detection","authors":"Zhipeng You ,&nbsp;Kexue Sun ,&nbsp;Luxian Zhang ,&nbsp;Yuheng Zha","doi":"10.1016/j.bspc.2025.108646","DOIUrl":"10.1016/j.bspc.2025.108646","url":null,"abstract":"<div><div>In biomedicine, accurate detection of blood cells in microscopic images is essential for disease diagnosis. However, challenges like cell adhesion and overlapping often lead to missed detections and lower accuracy with traditional methods. To address these issues, this paper introduces an algorithm called SKF-YOLO, which builds on enhancements made to YOLOv11n. The algorithm incorporates several innovative components: a P6 detection head to improve the detection of large blood cells; the Single-Head Self-Attention (SHSA) module embedded in the backbone’s C3K2 module to enhance small-target localization in complex backgrounds; the KernelWarehouse module, which reduces the size of convolutional kernels while increasing their number for better computational efficiency; and the Focaler-MPDIoU loss function, derived from Focaler-IoU and MPDIoU, that emphasizes difficult samples to increase the model’s robustness. Tests on the BCCD blood cell dataset demonstrate SKF-YOLO’s superior performance, achieving a mean Average Precision (mAP) of 94.1 % and an Average Precision (AP) of 96.1 % for platelets. Compared to the baseline YOLOv11n, SKF-YOLO improves mAP by 2.6 % and reduces computation by 2.5 GFLOPs. These results confirm that SKF-YOLO outperforms other algorithms in blood cell detection and recognition, fulfilling the needs of lightweight target detection and offering valuable insights for future blood cell analysis in medical imaging.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108646"},"PeriodicalIF":4.9,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive deep Q-GAN framework for enhanced breast cancer detection in medical imaging","authors":"M.D. Basith ,&nbsp;Pappula Praveen ,&nbsp;Pundru Chandra Shaker Reddy","doi":"10.1016/j.bspc.2025.108638","DOIUrl":"10.1016/j.bspc.2025.108638","url":null,"abstract":"<div><div>Breast cancer continues to be one of the most perilous diseases, necessitating precise and prompt detection for effective intervention. Despite the potential of deep learning approaches in mammogram-based diagnosis, they encounter ongoing obstacles such as dataset imbalance, data scarcity, subpar synthetic augmentation, and duplicate feature inclusion, all of which diminish detection performance and generalization. This article presents an Adaptive Deep Q-GAN architecture that integrates Deep Q-learning into the training of Generative Adversarial Networks, thereby mitigating mode collapse, stabilizing learning, and generating diverse, high-quality synthetic tumor images. U-Net segmentation is utilized to delineate specific regions of interest from mammography images, which undergo preprocessing involving normalization, median filtering, and histogram equalization. The Cuckoo Optimization Algorithm is employed for feature selection, discarding irrelevant and duplicated characteristics to diminish computing complexity. A CNN-based classifier, trained on both actual and synthetic data, achieves enhanced accuracy in tumor classification. The experimental assessment on the CBIS-DDSM dataset indicates that the suggested method attains an accuracy of 99.24%, surpassing leading techniques by as much as 6.8%, while also achieving a 32% improvement in computing efficiency. The framework necessitates substantial training time due to the incorporation of reinforcement learning; however, this constraint can be alleviated by parallelization techniques. The findings demonstrate that the suggested method provides a reliable, generalizable, and therapeutically pertinent solution for automated breast cancer diagnosis in medical imaging.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108638"},"PeriodicalIF":4.9,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145026610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"YOLO-MN: High-Throughput cell micronucleus detection based on prior knowledge and frequency domain perception","authors":"Linfeng Cao,&nbsp;Weiyi Wei,&nbsp;Chen Chen","doi":"10.1016/j.bspc.2025.108631","DOIUrl":"10.1016/j.bspc.2025.108631","url":null,"abstract":"<div><div>Cell micronuclei, key indicators of chromosomal damage, have broad applications in environmental toxicology, radiation research, and drug safety testing. Existing deep learning based micronuclei detection face numerous challenges including morphological similarity between micronuclei and cell nuclei, large size differences, and loss of detail information during multi-scale feature fusion. To address these challenges, this paper proposes an innovative cell micronucleus detection method termed YOLO-MN based on prior knowledge and frequency domain perception. We designed a wavelet feature enhancement (WFE) module based on two-dimensional discrete wavelet transform, which extracts multi-scale features through wavelet decomposition and enhances edge and chromatin texture information of micronuclei during feature fusion. Next, we designed a micronucleus attention module (MAM) and improved CSP feature extraction network (C2f_MAM) based on biological prior knowledge of micronuclei, focusing on shape features and capturing spatial relationships between micronuclei and the main nucleus. Finally, we designed an MNIoU loss function incorporating micronucleus prior knowledge to accelerate model convergence and further improve detection accuracy. Experimental results show that YOLO-MN achieved 91.7% Precision, 93.4% Recall, 94.7% mAP@50, and 59.1% mAP@50–95 on the cell micronucleus dataset, the model’s generalization capability was further validated on the SRCHD and LISC datasets.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108631"},"PeriodicalIF":4.9,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145026609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}