With the rapid development of computer technology,millions of images are produced everyday by different sources.How to efficiently process these images and accurately discern the scene in them becomes an important but...With the rapid development of computer technology,millions of images are produced everyday by different sources.How to efficiently process these images and accurately discern the scene in them becomes an important but tough task.In this paper,we propose a novel supervised learning framework based on proposed adaptive binary coding for scene classification.Specifically,we first extract some high-level features of images under consideration based on available models trained on public datasets.Then,we further design a binary encoding method called one-hot encoding to make the feature representation more efficient.Benefiting from the proposed adaptive binary coding,our method is free of time to train or fine-tune the deep network and can effectively handle different applications.Experimental results on three public datasets,i.e.,UIUC sports event dataset,MIT Indoor dataset,and UC Merced dataset in terms of three different classifiers,demonstrate that our method is superior to the state-of-the-art methods with large margins.展开更多
Resting-state functional magnetic resonance imaging (RS-fMRI)[1,2] provides relatively high spatial and temporal resolution for mapping spontaneous brain activity non-invasively. It has been widely used in cognitive n...Resting-state functional magnetic resonance imaging (RS-fMRI)[1,2] provides relatively high spatial and temporal resolution for mapping spontaneous brain activity non-invasively. It has been widely used in cognitive neuroscience and clinical studies. A number of comprehensive software packages have been developed for RS-fMRI data analysis, among which a MATLAB package named REST (RESing-state fMRI data analysis Toolkit, released in October 2008 at http://www.restfmri.net)[3] is the earliest one dedicated to RS-fMRI analysis. REST focuses on RS-fMRI postprocessing metrics.展开更多
Whether the cerebellum is involved in volun-tary motor learning or motor performance is the subject of a new debate. Using functional magnetic resonance imaging (fMRI), we examined cerebellar activation in eight volun...Whether the cerebellum is involved in volun-tary motor learning or motor performance is the subject of a new debate. Using functional magnetic resonance imaging (fMRI), we examined cerebellar activation in eight volun-teers before and after an extended period of training. Activa-tion volume on both sides of cerebellum after learning was significantly reduced compared to that before learning even under the same motor frequency. Remarkably, while motor frequency for the training sequence was significantly higher than the control sequence after 41 d of learning, activation in the cerebellum for both sequences, with respect to activation loci and volumes, was very similar. These results suggest that the cerebellum was involved in motor learning but not motor performance. Changes of cerebellar activation from training thus appear to be associated with learning but not with im-provement on task performance.展开更多
Deep learning approaches,especially convolutional neural networks(CNNs),have become the method of choice in the field of medical image analysis over the last few years.This prevalence is attributed to their excellent ...Deep learning approaches,especially convolutional neural networks(CNNs),have become the method of choice in the field of medical image analysis over the last few years.This prevalence is attributed to their excellent abilities to learn features in a more effective and efficient manner,not only for 2D/3D images in the Euclidean space,but also for meshes and graphs in non-Euclidean space such as cortical surfaces in neuroimaging analysis field.The brain cerebral cortex is a highly convoluted and thin sheet of gray matter(GM)that is thus typically represented by triangular surface meshes with an intrinsic spherical topology for each hemisphere.Accordingly,novel tailored deep learning methods have been developed for cortical surface-based analysis of neuroimaging data.This paper reviewsed the representative deep learning techniques relevant to cortical surface-based analysis and summarizes recent major contributions to the field.Specifically,we surveyed the use of deep learning techniques for cortical surface reconstruction,registration,parcellation,prediction,and other applications.We concluded by discussing the open challenges,limitations,and potentials of these techniques,and suggested directions for future research.展开更多
Hydrocephalus is often treated with a cerebrospinal fluid shunt(CFS) for excessive amounts of cerebrospinal fluid in the brain.However,it is very difficult to distinguish whether the ventricular enlargement is due to ...Hydrocephalus is often treated with a cerebrospinal fluid shunt(CFS) for excessive amounts of cerebrospinal fluid in the brain.However,it is very difficult to distinguish whether the ventricular enlargement is due to hydrocephalus or other causes,such as brain atrophy after brain damage and surgery.The non-trivial evaluation of the consciousness level,along with a continuous drainage test of the lumbar cistern is thus clinically important before the decision for CFS is made.We studied 32 secondary mild hydrocephalus patients with different consciousness levels,who received T1 and diffusion tensor imaging magnetic resonance scans before and after lumbar cerebrospinal fluid drainage.We applied a novel machine-learning method to find the most discriminative features from the multi-modal neuroimages.Then,we built a regression model to regress the JFK Coma Recovery Scale-Revised(CRS-R) scores to quantify the level of consciousness.The experimental results showed that our method not only approximated the CRS-R scores but also tracked the temporal changes in individual patients.The regression model has high potential for the evaluation of consciousness in clinical practice.展开更多
As direct prospecting data,geochemical data play an important role in modelling prospect potential.Geochemical element assemblage anomalies are usually reflected by the correlation between elements.Correlation coeffic...As direct prospecting data,geochemical data play an important role in modelling prospect potential.Geochemical element assemblage anomalies are usually reflected by the correlation between elements.Correlation coefficients are computed from the values of two elements,which reflect only the correlation at a global level.Thus,the spatial details of the correlation structure are ignored.In fact,an element combination anomaly often exists in geological backgrounds,such as on a fault zone or within a lithological unit.This anomaly may cause some combination of anomalies that are submerged inside the overall area and thus cannot be effectively extracted.To address this problem,we propose a local correlation coefficient based on spatial neighbourhoods to reflect the global distribution of elements.In this method,the sampling area is first divided into a set of uniform grid cells.A moving window with a size of 3×3 is defined with an integer of 3 to represent the sampling unit.The local correlation in each unit is expressed by the Pearson correlation coefficient.The whole area is scanned by the moving window,which produces a correlation coefficient matrix,and the result is portrayed with a thermal diagram.The local correlation approach was tested on two selected geochemical soil survey sites in Xiao Mountain,Henan Province.The results show that the areas of high correlation are mainly distributed in the fault zone or the known mineral spots.Therefore,the local correlation method is effective in extracting geochemical element combination anomalies.展开更多
Objective Accurate infant brain parcellation is crucial for understanding early brain development;however,it is challenging due to the inherent low tissue contrast,high noise,and severe partial volume effects in infan...Objective Accurate infant brain parcellation is crucial for understanding early brain development;however,it is challenging due to the inherent low tissue contrast,high noise,and severe partial volume effects in infant magnetic resonance images(MRIs).The aim of this study was to develop an end-to-end pipeline that enabled accurate parcellation of infant brain MRIs.Methods We proposed an end-to-end pipeline that employs a two-stage global-to-local approach for accurate parcellation of infant brain MRIs.Specifically,in the global regions of interest(ROIs)localization stage,a combination of transformer and convolution operations was employed to capture both global spatial features and fine texture features,enabling an approximate localization of the ROIs across the whole brain.In the local ROIs refinement stage,leveraging the position priors from the first stage along with the raw MRIs,the boundaries of the ROIs are refined for a more accurate parcellation.Results We utilized the Dice ratio to evaluate the accuracy of parcellation results.Results on 263 subjects from National Database for Autism Research(NDAR),Baby Connectome Project(BCP)and Cross-site datasets demonstrated the better accuracy and robustness of our method than other competing methods.Conclusion Our end-to-end pipeline may be capable of accurately parcellating 6-month-old infant brain MRIs.展开更多
基金supported by the National Key R&D Program of China 2018YFB1003205by the National Natural Science Foundation of China U1836208,U1536206,U1836110,61972207+2 种基金by the Engineering Research Center of Digital Forensics,Ministry of Educationby the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fundby the Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET)fund,China。
文摘With the rapid development of computer technology,millions of images are produced everyday by different sources.How to efficiently process these images and accurately discern the scene in them becomes an important but tough task.In this paper,we propose a novel supervised learning framework based on proposed adaptive binary coding for scene classification.Specifically,we first extract some high-level features of images under consideration based on available models trained on public datasets.Then,we further design a binary encoding method called one-hot encoding to make the feature representation more efficient.Benefiting from the proposed adaptive binary coding,our method is free of time to train or fine-tune the deep network and can effectively handle different applications.Experimental results on three public datasets,i.e.,UIUC sports event dataset,MIT Indoor dataset,and UC Merced dataset in terms of three different classifiers,demonstrate that our method is superior to the state-of-the-art methods with large margins.
基金supported by Department of Science and Technology, Zhejiang Province (2015C03037)the National Natural Science Foundation of China (81520108016, 81661148045, 61671198, 81671774, 81701776, 81471653)
文摘Resting-state functional magnetic resonance imaging (RS-fMRI)[1,2] provides relatively high spatial and temporal resolution for mapping spontaneous brain activity non-invasively. It has been widely used in cognitive neuroscience and clinical studies. A number of comprehensive software packages have been developed for RS-fMRI data analysis, among which a MATLAB package named REST (RESing-state fMRI data analysis Toolkit, released in October 2008 at http://www.restfmri.net)[3] is the earliest one dedicated to RS-fMRI analysis. REST focuses on RS-fMRI postprocessing metrics.
基金This work was supported by the National Natural science Foundation of China(Grant Nos.30425008&30128005)a foundation from Health Bureau of Zhejiang Province(Grant No.2002B019).
文摘Whether the cerebellum is involved in volun-tary motor learning or motor performance is the subject of a new debate. Using functional magnetic resonance imaging (fMRI), we examined cerebellar activation in eight volun-teers before and after an extended period of training. Activa-tion volume on both sides of cerebellum after learning was significantly reduced compared to that before learning even under the same motor frequency. Remarkably, while motor frequency for the training sequence was significantly higher than the control sequence after 41 d of learning, activation in the cerebellum for both sequences, with respect to activation loci and volumes, was very similar. These results suggest that the cerebellum was involved in motor learning but not motor performance. Changes of cerebellar activation from training thus appear to be associated with learning but not with im-provement on task performance.
基金the National Institutes of Health(NIH)(Grant Nos.MH116225,MH117943,MH123202,and AG075582).
文摘Deep learning approaches,especially convolutional neural networks(CNNs),have become the method of choice in the field of medical image analysis over the last few years.This prevalence is attributed to their excellent abilities to learn features in a more effective and efficient manner,not only for 2D/3D images in the Euclidean space,but also for meshes and graphs in non-Euclidean space such as cortical surfaces in neuroimaging analysis field.The brain cerebral cortex is a highly convoluted and thin sheet of gray matter(GM)that is thus typically represented by triangular surface meshes with an intrinsic spherical topology for each hemisphere.Accordingly,novel tailored deep learning methods have been developed for cortical surface-based analysis of neuroimaging data.This paper reviewsed the representative deep learning techniques relevant to cortical surface-based analysis and summarizes recent major contributions to the field.Specifically,we surveyed the use of deep learning techniques for cortical surface reconstruction,registration,parcellation,prediction,and other applications.We concluded by discussing the open challenges,limitations,and potentials of these techniques,and suggested directions for future research.
基金supported by the National Natural Science Foundation of China (81571025 and 81702461)the National Key Research and Development Program of China (2018YFC0116400)+6 种基金the International Cooperation Project from Shanghai Science Foundation (18410711300)Shanghai Science and Technology Development Funds (16JC1420100)the Shanghai Sailing Program (17YF1426600)STCSM (19QC1400600, 17411953300)the Shanghai Pujiang Program (19PJ1406800)the Shanghai Municipal Science and Technology Major Project (No.2018SHZDZX01) and ZJlabthe Interdisciplinary Program of Shanghai Jiao Tong University。
文摘Hydrocephalus is often treated with a cerebrospinal fluid shunt(CFS) for excessive amounts of cerebrospinal fluid in the brain.However,it is very difficult to distinguish whether the ventricular enlargement is due to hydrocephalus or other causes,such as brain atrophy after brain damage and surgery.The non-trivial evaluation of the consciousness level,along with a continuous drainage test of the lumbar cistern is thus clinically important before the decision for CFS is made.We studied 32 secondary mild hydrocephalus patients with different consciousness levels,who received T1 and diffusion tensor imaging magnetic resonance scans before and after lumbar cerebrospinal fluid drainage.We applied a novel machine-learning method to find the most discriminative features from the multi-modal neuroimages.Then,we built a regression model to regress the JFK Coma Recovery Scale-Revised(CRS-R) scores to quantify the level of consciousness.The experimental results showed that our method not only approximated the CRS-R scores but also tracked the temporal changes in individual patients.The regression model has high potential for the evaluation of consciousness in clinical practice.
基金supported by the National Natural Science Foundation of China(Nos.41272359,210100069)。
文摘As direct prospecting data,geochemical data play an important role in modelling prospect potential.Geochemical element assemblage anomalies are usually reflected by the correlation between elements.Correlation coefficients are computed from the values of two elements,which reflect only the correlation at a global level.Thus,the spatial details of the correlation structure are ignored.In fact,an element combination anomaly often exists in geological backgrounds,such as on a fault zone or within a lithological unit.This anomaly may cause some combination of anomalies that are submerged inside the overall area and thus cannot be effectively extracted.To address this problem,we propose a local correlation coefficient based on spatial neighbourhoods to reflect the global distribution of elements.In this method,the sampling area is first divided into a set of uniform grid cells.A moving window with a size of 3×3 is defined with an integer of 3 to represent the sampling unit.The local correlation in each unit is expressed by the Pearson correlation coefficient.The whole area is scanned by the moving window,which produces a correlation coefficient matrix,and the result is portrayed with a thermal diagram.The local correlation approach was tested on two selected geochemical soil survey sites in Xiao Mountain,Henan Province.The results show that the areas of high correlation are mainly distributed in the fault zone or the known mineral spots.Therefore,the local correlation method is effective in extracting geochemical element combination anomalies.
基金funded by National Institutes of Health(Grant Nos.MH117943,MH109773,MH116225,and MH123202)Additionally,the work leverages approaches developed through an National Institutes of Health(Grant No.1U01MH110274)the efforts of the Baby Connectome Project Consortium at UNC/UMIN.
文摘Objective Accurate infant brain parcellation is crucial for understanding early brain development;however,it is challenging due to the inherent low tissue contrast,high noise,and severe partial volume effects in infant magnetic resonance images(MRIs).The aim of this study was to develop an end-to-end pipeline that enabled accurate parcellation of infant brain MRIs.Methods We proposed an end-to-end pipeline that employs a two-stage global-to-local approach for accurate parcellation of infant brain MRIs.Specifically,in the global regions of interest(ROIs)localization stage,a combination of transformer and convolution operations was employed to capture both global spatial features and fine texture features,enabling an approximate localization of the ROIs across the whole brain.In the local ROIs refinement stage,leveraging the position priors from the first stage along with the raw MRIs,the boundaries of the ROIs are refined for a more accurate parcellation.Results We utilized the Dice ratio to evaluate the accuracy of parcellation results.Results on 263 subjects from National Database for Autism Research(NDAR),Baby Connectome Project(BCP)and Cross-site datasets demonstrated the better accuracy and robustness of our method than other competing methods.Conclusion Our end-to-end pipeline may be capable of accurately parcellating 6-month-old infant brain MRIs.