Study on the detection of CT image based on multi-task network method of global attention for fine-fracture / 中国医学装备

Objective:To improve the perception of computed tomography(CT)images in detecting fine fracture through multi-task network of global attention,and to realize the detection of the target of fine fracture at case level through multi-task,and to quickly and accurately identify and locate fracture from a large number of CT images,so as to assist doctors to timely conduct treatment.Methods:A grouped Non-local network method was introduced to calculate the remote dependency relationship between each position of CT image continuous sections and channel.A single-stage detector of multi-objective detection model three dimension(3D)RetinaNet was integrated with the medical image semantic segmentation architecture(3D U-Net).A end-to-end multi-task 3D convolutional network was realized,which realized the detection of case level for fine fracture through multi-task collaboration.Select 600 CT scan images from the Rib Frac Dataset of rib fractures provided by the MICCAI 2020 Challenge,and they were divided into training set(500 cases)and test set(100 cases)as the ratio of 5:1 to test the precise performance of multi-task 3D convolutional network.Results:The precise performance of multi-task 3D convolutional network method was better than that of single-task FracNet,3D RetinaNet and 3D Retina U-Net in detection,which average precision was respectively higher 7.8%and 11.4%than 3D RetinaNet and 3D Retina U-Net.It was better than two kinds of single-task network detection method included 3D Faster R-CNN and 3D Mask R-CNN,and the average precision of that was respectively higher 6.7%and 3.1%than them.Conclusion:The integrated different modules of global attention multi-task network can improve the detection performance of fine fracture.The introduction of grouped Non-local network method can further improve the precise performance for the targets of fine fractures in detection.

Non-local attention and multi-task learning based lung segmentation in chest X-ray / 生物医学工程学杂志

Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.

Fall detection algorithm for community healthcare / 中国医学物理学杂志

A fall detection algorithm for community healthcare is proposed to avoid the secondary injury caused by untimely treatment when the elder living alone falls in the community.The algorithm has two branches,namely 2D convolution and 3D convolution,which allow it can extract spatial and temporal features simultaneously.The dense connections added in the 3D branch enhance the ability to extract temporal features;the residual blocks in the 2D branch are redesigned to improve the ability of spatial feature extraction;and a non-local attention mechanism is introduced to the branch fusion for better feature fusion.The algorithm also takes scene information into consideration,and it is supervised by SIoU loss function and the combined loss function to realize fall detection.The experiment on the expanded public URFD dataset reveals that the proposed method has a detection accuracy of 98.3%,which verifies its performance and robustness for fall detection.

Introduction to Bayesian variable selection methods in high-dimensional omics data analysis / 中华流行病学杂志

With the rapid development of genome sequencing technology and bioinformatics in recent years,it has become possible to measure thousands of omics data which might be associated with the progress of diseases,i.e."high-dimensional data".This type of omics data have a common feature that the number of variable p is usually greater than the observation cases n,and often has high correlation between independent variables.Therefore,it is a great statistical challenge to identify really meaningful variables from omics data.This paper summarizes the methods of Bayesian variable selection in the analysis of high-dimensional data.

Introduction to Bayesian variable selection methods in high-dimensional omics data analysis / 中华流行病学杂志

With the rapid development of genome sequencing technology and bioinformatics in recent years,it has become possible to measure thousands of omics data which might be associated with the progress of diseases,i.e."high-dimensional data".This type of omics data have a common feature that the number of variable p is usually greater than the observation cases n,and often has high correlation between independent variables.Therefore,it is a great statistical challenge to identify really meaningful variables from omics data.This paper summarizes the methods of Bayesian variable selection in the analysis of high-dimensional data.

Survey of acceptance of non-local patients by hospitals in Tianjin / 中华医院管理杂志

Objective To learn the present acceptance of patients from outside Tianjin by local hospitals, for improving the management of their medical services.Methods A study of the hospitals′ network system identified 5 306 inpatients from other places in 2016 as evidenced by their hospital settlement account, with analysis of the patient flow from other places by the hospitals surveyed.Medical workers of eight medical institutions which signed the online settlement contract for non-local patients were subject to questionnaire survey.Results Of the 876 respondents,the number of patients willing to receive non-local insured patients accounted for 78.08%.Non-local patients aged 60 or above accounted for 82.31% among the total non-local patients, of whom 48.55% selected hospitals with national key disciplines, and 30.53% chose those with municipal key disciplines.Conclusions An analysis is required for the demand of non-local patients in terms of the social background and population characteristics.Based on such, non-local patient population needs a better management while those with irrational needs should be discouraged with rules and regulations.

Experiências de quase morte em parada cardíaca: implicações para o conceito de mente não local / Near-death experiences in cardiac arrest: implications for the concept of non-local mind

CONTEXTO: Experiências de quase morte (EQM) são experiências vívidas, realísticas, que frequentemente promovem mudanças profundas na vida de pessoas que estiveram fisiológica ou psicologicamente próximas da morte. As EQM por vezes ocorrem durante uma parada cardíaca, na ausência de atividade cerebral detectável. OBJETIVO: Revisar os estudos prospectivos de EQM induzidas por paradas cardíacas e examinar as implicações desses estudos para o conceito de mente não local. MÉTODO: PubMed foi a principal base de dados utilizada para esta revisão. Os termos-chave da busca incluíram "parada cardíaca", "experiências de quase morte", "fisiologia da experiência de quase morte" e "experiências fora do corpo verídicas". RESULTADOS: Vários estudos prospectivos mostram incidência média de 10% a 20% de EQM induzidas por paradas cardíacas, independentemente de aspectos sociodemográficos, sexo, religião ou quaisquer parâmetros médicos, fisiológicos ou farmacológicos consistentes. Pessoas que passaram por EQM são mais propensas a mudanças de vida positivas que podem durar muitos anos após a experiência do que aquelas que não a tiveram. CONCLUSÕES: As teorias fisicalistas da mente não são capazes de explicar como pessoas que tiveram EQM podem vivenciar - enquanto seus corações estão parados e sua atividade cerebral aparentemente ausente - pensamentos vívidos e complexos e adquirir informações verídicas a respeito de objetos ou eventos distantes de seus corpos. As EQM em paradas cardíacas sugerem que a mente é não local, isto é, não é gerada pelo cérebro e não está confinada a ele ou ao corpo.

BACKGROUND: Near-death experiences (NDE) are vivid, realistic, and often deeply life-changing experiences occurring to people who have been physiologically or psychologically close to death. NDEs sometimes occur during cardiac arrest, in the absence of recordable brain activity. OBJECTIVE: To review prospective studies of cardiac arrest-induced NDEs and examine the implications of these studies for the concept of non-local mind. METHOD: PubMed was the main database used for this review. Key search terms included "cardiac arrest", "near-death experiences", "physiology of near-death experience", and "veridical out-of-body-experiences". RESULTS: Several prospective studies show an average incidence of cardiac arrest-induced NDE of 10%-20%, irrespective of sociodemographic status, sex, religion, or any consistent medical, physiological, or pharmacological measures. NDErs are more likely than non-NDErs to have positive life changes lasting many years following the experience. DISCUSSION: Physicalist theories of the mind cannot explain how NDErs can experience - while their hearts are stopped and brain activity is seemingly absent - vivid and complex thoughts, and acquire veridical information about objects or events remote from their bodies. NDE in cardiac arrest suggest that mind is non-local, i.e. it is not generated by the brain, and it is not confined to the brain and the body.

As experiências de quase morte (EQM) podem contribuir para o debate sobre a consciência? / Can near death experiences (NDEs) contribute to the debate on consciousness?

A EQM é um estado alterado de consciência que no ocidente inclui uma experiência emocional e de conteúdo estereotipado. Algumas características da experiência são transculturais e sugerem ou um mecanismo cerebral similar ou acesso a uma realidade transcendente. Características individuais da experiência indicam mais persuasivamente para transcendência que para um simples mecanismo cerebral limitado. Além disso, não há, até agora, nenhuma explicação reducionista que possa dar conta satisfatoriamente de algumas dessas características: o encontro com parentes falecidos, a aparente capacidade visual em cegos durante a EQM, a aparente aquisição de dons psíquicos e espirituais após a EQM, relato de cura ocorrida durante uma EQM e experiências verídicas durante a ressuscitação pós-parada cardíaca. Embora uma mente não local pudesse explicar muita das características das EQM, a não localidade ainda não é aceita pela corrente predominante da neurociência. Somente aquelas teorias baseadas num entendimento mais amplo da mente poderiam explicar totalmente a experiência subjetiva dos que vivenciaram uma EQM.

The NDE is an altered state of consciousness which in the West has stereotyped content and emotional experience. Some features of the experience are trans-cultural and suggest either a similar brain mechanism or access to a transcendent reality. Individual features of the experience point more persuasively to transcendence than to simple limited brain mechanisms. Moreover there are, so far, no reductionist explanations which can account satisfactorily for some of its features; the meeting of dead relatives, the apparent "sightedness" in the blind during an NDE, the apparent acquisition after an NDE of psychic and spiritual gifts, accounts of healing occurring during an NDE, and of veridical experience during the resuscitation after a cardiac arrest. Although non-local mind would explain many of the NDE features, non locality is not yet accepted by mainstream neuroscience. Only those theories based on a wider understanding of mind could fully explain the subjective experience of the NDEr.