The brain is the most sophisticated and complex organ in the human body. Nowadays, diagnosing complex and diverse brain diseases is a hot topic. Alzheimer's Disease (AD), Autism Spectrum Disorder (ASD), and others...
详细信息
In this study, a novel training method is innovatively proposed to address the problem of poor generalisation of trained models due to imbalance in Alzheimer’s disease (AD) data. The method alternates AD image data w...
详细信息
The brain is the most sophisticated and complex organ in the human body. Nowadays, diagnosing complex and diverse brain diseases is a hot topic. Alzheimer's Disease (AD), Autism Spectrum Disorder (ASD), and others...
The brain is the most sophisticated and complex organ in the human body. Nowadays, diagnosing complex and diverse brain diseases is a hot topic. Alzheimer's Disease (AD), Autism Spectrum Disorder (ASD), and others are common brain diseases. With the increased usage of Artificial intelligence (AI) in medical image analysis, the endeavor to make AI comprehend brain images for assisting doctors in making objective diagnoses of brain diseases has gained considerable attention. Resting-state functional magnetic resonance imaging (rs-fMRI) is a widely used tool for diagnosing and analyzing brain ***, the Pearson correlation coefficient (PCC) method constructs a dynamic functional connectivity (dFC) network using a fixed window size. However, this method has limitations as it is challenging to extract potential high-level features from the dFC and determine local feature relevance. This paper presents a method for constructing dFC based on multi-scale sliding windows and proposes Multi-scale Convolutional Neural Networks (MsCNN) for learning and analyzing dFC at various scales. Finally, a deep fusion of features learned at different scales is employed for the diagnostic classification of brain *** to the rs-fMRI dataset from ADNI, the classification accuracy was 84.0% for eMCI/lMCI, 84.4% for lMCI/AD, and 58.4% for NC/eMCI/lMCI/AD. Applied to rs-fMRI data from ABIDE, the accuracy was 74.7% for ASD/NC. The proposed method exhibits robust classification performance and introduces a new approach to diagnosing other brain diseases.
Heatmap regression-based models have significantly advanced the progress of facial landmark detection. However, the lack of structural constraints always generates inaccurate heatmaps resulting in poor landmark detect...
详细信息
ISBN:
(数字)9781728148038
ISBN:
(纸本)9781728148045
Heatmap regression-based models have significantly advanced the progress of facial landmark detection. However, the lack of structural constraints always generates inaccurate heatmaps resulting in poor landmark detection performance. While hierarchical structure modeling methods have been proposed to tackle this issue, they all heavily rely on manually designed tree structures. The designed hierarchical structure is likely to be completely corrupted due to the missing or inaccurate prediction of landmarks. To the best of our knowledge, in the context of deep learning, no work before has investigated how to automatically model proper structures for facial landmarks, by discovering their inherent relations. In this paper, we propose a novel Hierarchical Structured Landmark Ensemble (HSLE) model for learning robust facial landmark detection, by using it as the structural constraints. Different from existing approaches of manually designing structures, our proposed HSLE model is constructed automatically via discovering the most robust patterns so HSLE has the ability to robustly depict both local and holistic landmark structures simultaneously. Our proposed HSLE can be readily plugged into any existing facial landmark detection baselines for further performance improvement. Extensive experimental results demonstrate our approach significantly outperforms the baseline by a large margin to achieve a state-of-the-art performance.
In this paper, we study the theory of collaborative upload bandwidth measurement in peer-to-peer environments. A host can use a bandwidth estimation probe to determine the bandwidth between itself and any other host i...
详细信息
In this paper, we study the theory of collaborative upload bandwidth measurement in peer-to-peer environments. A host can use a bandwidth estimation probe to determine the bandwidth between itself and any other host i...
详细信息
ISBN:
(纸本)9781424458363
In this paper, we study the theory of collaborative upload bandwidth measurement in peer-to-peer environments. A host can use a bandwidth estimation probe to determine the bandwidth between itself and any other host in the system. The problem is that the result of such a measurement may not necessarily be the sender's upload bandwidth, since the most bandwidth restricted link on the path could also be the receiver's download bandwidth. In this paper, we formally define the bandwidth determination problem and devise efficient distributed algorithms. We consider two models, the free-departure and no-departure model, respectively, depending on whether hosts keep participating in the algorithm even after their bandwidth has been determined. We present lower bounds on the time-complexity of any collaborative bandwidth measurement algorithm in both models. We then show how, for realistic bandwidth distributions, the lower bounds can be overcome. Specifically, we present O(1) and O(log log n)-time algorithms for the two models. We corroborate these theoretical findings with practical measurements on a implementation on PlanetLab.
暂无评论