Neuroimaging has emerged over the last few decades as a crucial tool in diagnosing Alzheimer’s disease(AD).Mild cognitive impairment(MCI)is a condition that falls between the spectrum of normal cognitive function and...Neuroimaging has emerged over the last few decades as a crucial tool in diagnosing Alzheimer’s disease(AD).Mild cognitive impairment(MCI)is a condition that falls between the spectrum of normal cognitive function and AD.However,previous studies have mainly used handcrafted features to classify MCI,AD,and normal control(NC)individuals.This paper focuses on using gray matter(GM)scans obtained through magnetic resonance imaging(MRI)for the diagnosis of individuals with MCI,AD,and NC.To improve classification performance,we developed two transfer learning strategies with data augmentation(i.e.,shear range,rotation,zoom range,channel shift).The first approach is a deep Siamese network(DSN),and the second approach involves using a cross-domain strategy with customized VGG-16.We performed experiments on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset to evaluate the performance of our proposed models.Our experimental results demonstrate superior performance in classifying the three binary classification tasks:NC vs.AD,NC vs.MCI,and MCI vs.AD.Specifically,we achieved a classification accuracy of 97.68%,94.25%,and 92.18%for the three cases,respectively.Our study proposes two transfer learning strategies with data augmentation to accurately diagnose MCI,AD,and normal control individuals using GM scans.Our findings provide promising results for future research and clinical applications in the early detection and diagnosis of AD.展开更多
The phase transition of water molecules in nanochannels under varying external electric fields is studied by molecular dynamics simulations.It is found that the phase transition of water molecules in nanochannels occu...The phase transition of water molecules in nanochannels under varying external electric fields is studied by molecular dynamics simulations.It is found that the phase transition of water molecules in nanochannels occurs by changing the frequency of the varying electric field.Water molecules maintain the ice phase when the frequency of the varying electric field is less than 16 THz or greater than 30 THz,and they completely melt when the frequency of the varying electric field is 24 THz.This phenomenon is attributed to the breaking of hydrogen bonds when the frequency of the varying electric field is close to their inherent resonant frequency.Moreover,the study demonstrates that the critical frequency varies with the confinement situation.The new mechanism of regulating the phase transition of water molecules in nanochannels revealed in this study provides a perspective for further understanding of the phase transition of water molecules in nanochannels,and has great application potential in preventing icing and deicing.展开更多
基金Research work funded by Zhejiang Normal University Research Fund YS304023947 and YS304023948.
文摘Neuroimaging has emerged over the last few decades as a crucial tool in diagnosing Alzheimer’s disease(AD).Mild cognitive impairment(MCI)is a condition that falls between the spectrum of normal cognitive function and AD.However,previous studies have mainly used handcrafted features to classify MCI,AD,and normal control(NC)individuals.This paper focuses on using gray matter(GM)scans obtained through magnetic resonance imaging(MRI)for the diagnosis of individuals with MCI,AD,and NC.To improve classification performance,we developed two transfer learning strategies with data augmentation(i.e.,shear range,rotation,zoom range,channel shift).The first approach is a deep Siamese network(DSN),and the second approach involves using a cross-domain strategy with customized VGG-16.We performed experiments on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset to evaluate the performance of our proposed models.Our experimental results demonstrate superior performance in classifying the three binary classification tasks:NC vs.AD,NC vs.MCI,and MCI vs.AD.Specifically,we achieved a classification accuracy of 97.68%,94.25%,and 92.18%for the three cases,respectively.Our study proposes two transfer learning strategies with data augmentation to accurately diagnose MCI,AD,and normal control individuals using GM scans.Our findings provide promising results for future research and clinical applications in the early detection and diagnosis of AD.
基金partially supported by the National Natural Science Foundation of China (Nos. 12172334 and 12274110)the Zhejiang Provincial Natural Science Foundation of China (No. LR21A020001)
文摘The phase transition of water molecules in nanochannels under varying external electric fields is studied by molecular dynamics simulations.It is found that the phase transition of water molecules in nanochannels occurs by changing the frequency of the varying electric field.Water molecules maintain the ice phase when the frequency of the varying electric field is less than 16 THz or greater than 30 THz,and they completely melt when the frequency of the varying electric field is 24 THz.This phenomenon is attributed to the breaking of hydrogen bonds when the frequency of the varying electric field is close to their inherent resonant frequency.Moreover,the study demonstrates that the critical frequency varies with the confinement situation.The new mechanism of regulating the phase transition of water molecules in nanochannels revealed in this study provides a perspective for further understanding of the phase transition of water molecules in nanochannels,and has great application potential in preventing icing and deicing.