Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancem...Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancement.However,the currently prevalent loss functions assign equal weight to each pixel point during loss calculation,which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully.To address this issue,this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task.This novel loss function can adjust the weight of the reconstruction loss based on the grey value of different pixel points,thereby effectively optimizing the network training by differentially utilizing the grey information from the original image.Specifically,we calculate a weight factor for each pixel point based on its grey value and combine it with the reconstruction loss to create a new loss function.This ensures that pixel points with smaller grey values receive greater attention,improving network recovery.In order to verify the effectiveness of the proposed asymmetric loss function,we conducted experimental tests in the image super-resolution task.The experimental results show that the model with the introduction of asymmetric loss weights improves all the indexes of the processing results without increasing the training time.In the typical super-resolution network SRCNN,by introducing asymmetric weights,it is possible to improve the peak signal-to-noise ratio(PSNR)by up to about 0.5%,the structural similarity index(SSIM)by up to about 0.3%,and reduce the root-mean-square error(RMSE)by up to about 1.7%with essentially no increase in training time.In addition,we also further tested the performance of the proposed method in the denoising task to verify the potential applicability of the method in the image restoration task.展开更多
Osmanthus fragrans is one of the top ten traditional flowers in China.It is divided into three different groups according to its color.α-Carotene and β-carotene are the main determinants to distinguish the color dif...Osmanthus fragrans is one of the top ten traditional flowers in China.It is divided into three different groups according to its color.α-Carotene and β-carotene are the main determinants to distinguish the color differences between three groups.However,the dominant genes and transcription factors involved in carotenoid metabolism remain unclear.CPTA treatment(0.7mmol·L−1)remarkably promoted lycopene,α-carotene and β-carotene contents in flowers.Transcriptome sequencing analysis revealed that CPTA treatment could trigger chain reactions in carotenoid metabolism pathway genes.Four up-regulated and 10 down-regulated transcription factors which have close association with carotenoid variation were significantly induced by CPTA treatment.The up-regulated TFs such as MYB43,MYB123,HSF,were further subjected to transcript expression determination in different cultivars with drastic colors.Among them,transcript expression of four up-regulated TFs coincided with the carotenoid accumulation in different cultivars.We selected up-regulated OfMYB43 to verify its function,which is related to stress tolerance and transcriptional regulation.Transient overexpression of OfMYB43 in O.fragrans flowers showed that it could remarkably promote the expression of PDS,ZISO,LCYE and CCD4,leading to increased accumulation of β-branch carotenoids.OfMYB43 was a potential positive regulator of carotenoid biosynthesis in O.fragrans flowers.This study provides insight into the molecular mechanism of carotenoid metabolism in O.fragrans.展开更多
Bipolar disorder is characterised by recurrent and alternating episodes of mania/hypomania and depression.Current breakthroughs in functional MRI techniques have uncovered the functional neuroanatomy of bipolar disord...Bipolar disorder is characterised by recurrent and alternating episodes of mania/hypomania and depression.Current breakthroughs in functional MRI techniques have uncovered the functional neuroanatomy of bipolar disorder.However,the pathophysiology underlying mood instability,mood switching and the development of extreme mood states is less well understood.This reviewpresents a comprehensive overviewof current evidence from functional MRI studies from the perspective of mood states.We first summarise the disrupted brain activation patterns and functional connectivity that have been reported in bipolar disorder,irrespective of the mood state.We next focus on research that solely included patients in a single mood state for a better understanding of the pathophysiology of bipolar disorder and research comparing patients with different mood states to dissect mood state-related effects.Finally,we briefly summarise current theoretical models and conclude this review by proposing potential avenues for future research.A comprehensive understanding of the pathophysiology with consideration of mood states could not only deepen our understanding of how acute mood episodes develop at a neurophysiological level but could also facilitate the identification of biological targets for personalised treatment and the development of new interventions for bipolar disorder.展开更多
Comprehensive Summary The nanoelectrode-based electrochemical method has been widely used for single-cell analysis because of the advantages of high spatiotemporal resolution and in-situ detection capability.As an evo...Comprehensive Summary The nanoelectrode-based electrochemical method has been widely used for single-cell analysis because of the advantages of high spatiotemporal resolution and in-situ detection capability.As an evolutional generation of the electrochemical analysis,photoelectrochemical(PEC)sensors not only inherit the above-mentioned merits,but also possess a lower background and higher sensitivity,because they can operate under unbiased conditions.Moreover,electrodes are often impaired by nonspecific binding in complex biological environments.展开更多
基金supported by the National Natural Science Foundation of China(62201618).
文摘Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancement.However,the currently prevalent loss functions assign equal weight to each pixel point during loss calculation,which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully.To address this issue,this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task.This novel loss function can adjust the weight of the reconstruction loss based on the grey value of different pixel points,thereby effectively optimizing the network training by differentially utilizing the grey information from the original image.Specifically,we calculate a weight factor for each pixel point based on its grey value and combine it with the reconstruction loss to create a new loss function.This ensures that pixel points with smaller grey values receive greater attention,improving network recovery.In order to verify the effectiveness of the proposed asymmetric loss function,we conducted experimental tests in the image super-resolution task.The experimental results show that the model with the introduction of asymmetric loss weights improves all the indexes of the processing results without increasing the training time.In the typical super-resolution network SRCNN,by introducing asymmetric weights,it is possible to improve the peak signal-to-noise ratio(PSNR)by up to about 0.5%,the structural similarity index(SSIM)by up to about 0.3%,and reduce the root-mean-square error(RMSE)by up to about 1.7%with essentially no increase in training time.In addition,we also further tested the performance of the proposed method in the denoising task to verify the potential applicability of the method in the image restoration task.
基金supported by the Fundamental Research Fund for the Central Universities(Grant No.2013PY088).
文摘Osmanthus fragrans is one of the top ten traditional flowers in China.It is divided into three different groups according to its color.α-Carotene and β-carotene are the main determinants to distinguish the color differences between three groups.However,the dominant genes and transcription factors involved in carotenoid metabolism remain unclear.CPTA treatment(0.7mmol·L−1)remarkably promoted lycopene,α-carotene and β-carotene contents in flowers.Transcriptome sequencing analysis revealed that CPTA treatment could trigger chain reactions in carotenoid metabolism pathway genes.Four up-regulated and 10 down-regulated transcription factors which have close association with carotenoid variation were significantly induced by CPTA treatment.The up-regulated TFs such as MYB43,MYB123,HSF,were further subjected to transcript expression determination in different cultivars with drastic colors.Among them,transcript expression of four up-regulated TFs coincided with the carotenoid accumulation in different cultivars.We selected up-regulated OfMYB43 to verify its function,which is related to stress tolerance and transcriptional regulation.Transient overexpression of OfMYB43 in O.fragrans flowers showed that it could remarkably promote the expression of PDS,ZISO,LCYE and CCD4,leading to increased accumulation of β-branch carotenoids.OfMYB43 was a potential positive regulator of carotenoid biosynthesis in O.fragrans flowers.This study provides insight into the molecular mechanism of carotenoid metabolism in O.fragrans.
基金the National Key Technology R&D Program(2015BA/13B01)Beijing National Science Foundation(7222236)+1 种基金Capital Health Research and Development of Special Fund(2022-1-4111)National Natural Science Foundation of China(82071528,82171529,82271569,82371530).
文摘Bipolar disorder is characterised by recurrent and alternating episodes of mania/hypomania and depression.Current breakthroughs in functional MRI techniques have uncovered the functional neuroanatomy of bipolar disorder.However,the pathophysiology underlying mood instability,mood switching and the development of extreme mood states is less well understood.This reviewpresents a comprehensive overviewof current evidence from functional MRI studies from the perspective of mood states.We first summarise the disrupted brain activation patterns and functional connectivity that have been reported in bipolar disorder,irrespective of the mood state.We next focus on research that solely included patients in a single mood state for a better understanding of the pathophysiology of bipolar disorder and research comparing patients with different mood states to dissect mood state-related effects.Finally,we briefly summarise current theoretical models and conclude this review by proposing potential avenues for future research.A comprehensive understanding of the pathophysiology with consideration of mood states could not only deepen our understanding of how acute mood episodes develop at a neurophysiological level but could also facilitate the identification of biological targets for personalised treatment and the development of new interventions for bipolar disorder.
基金funded by the National Natural Science Foundation of China(Nos.21804032,21625503)the Foundation for Creative Research Groups of Hubei Province of China(No.2020CFA035).
文摘Comprehensive Summary The nanoelectrode-based electrochemical method has been widely used for single-cell analysis because of the advantages of high spatiotemporal resolution and in-situ detection capability.As an evolutional generation of the electrochemical analysis,photoelectrochemical(PEC)sensors not only inherit the above-mentioned merits,but also possess a lower background and higher sensitivity,because they can operate under unbiased conditions.Moreover,electrodes are often impaired by nonspecific binding in complex biological environments.