Zobrazeno 1 - 10
of 876
pro vyhledávání: '"ZHAO Qingyu"'
Autor:
Paschali, Magdalini, Jiang, Yu Hang, Siegel, Spencer, Gonzalez, Camila, Pohl, Kilian M., Chaudhari, Akshay, Zhao, Qingyu
Recent advancements in medicine have confirmed that brain disorders often comprise multiple subtypes of mechanisms, developmental trajectories, or severity levels. Such heterogeneity is often associated with demographic aspects (e.g., sex) or disease
Externí odkaz:
http://arxiv.org/abs/2410.00946
Many longitudinal neuroimaging studies aim to improve the understanding of brain aging and diseases by studying the dynamic interactions between brain function and cognition. Doing so requires accurate encoding of their multidimensional relationship
Externí odkaz:
http://arxiv.org/abs/2409.13887
Autor:
Peng, Wei, Xia, Tian, Ribeiro, Fabio De Sousa, Bosschieter, Tomas, Adeli, Ehsan, Zhao, Qingyu, Glocker, Ben, Pohl, Kilian M.
The number of samples in structural brain MRI studies is often too small to properly train deep learning models. Generative models show promise in addressing this issue by effectively learning the data distribution and generating high-fidelity MRI. H
Externí odkaz:
http://arxiv.org/abs/2409.05585
Publikováno v:
南方能源建设, Vol 6, Iss 3, Pp 75-80 (2019)
[Objective] Energy Internet is a complex system that optimizes energy efficiency, load and power grids to achieve optimal energy efficiency. The evaluation index system and comprehensive evaluation of planning schemes are key issues that must be solv
Externí odkaz:
https://doaj.org/article/44faaa9ca52a4c9d807eb7d6d56b5764
Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Traditional methods for ensuring fairness either blindly learn invariant
Externí odkaz:
http://arxiv.org/abs/2404.13798
Autor:
Peng, Wei, Bosschieter, Tomas, Ouyang, Jiahong, Paul, Robert, Adeli, Ehsan, Zhao, Qingyu, Pohl, Kilian M.
Generative AI models hold great potential in creating synthetic brain MRIs that advance neuroimaging studies by, for example, enriching data diversity. However, the mainstay of AI research only focuses on optimizing the visual quality (such as signal
Externí odkaz:
http://arxiv.org/abs/2310.04630
Publikováno v:
E3S Web of Conferences, Vol 185, p 03036 (2020)
This work aims to explore the impact of a proposed lower limb exoskeleton robot on the muscle strength of the tibialis anterior muscle in stroke patients. Firstly, 24 patients with stroke hemiplegia were divided into the robot group and the control g
Externí odkaz:
https://doaj.org/article/41fd1bea60ba4c16b1c3c520a9158022
Publikováno v:
E3S Web of Conferences, Vol 218, p 03050 (2020)
To explore the intervention effect of exoskeleton robot training on anxiety of stroke patients. Methods 24 stroke patients with hemiplegia were randomly divided into experimental group and control group, with 12 cases in each group. Moreover, the rob
Externí odkaz:
https://doaj.org/article/eb0d4aaa5dee4504b079379300d5e8c5
Publikováno v:
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2023
Interpretability is a key issue when applying deep learning models to longitudinal brain MRIs. One way to address this issue is by visualizing the high-dimensional latent spaces generated by deep learning via self-organizing maps (SOM). SOM separates
Externí odkaz:
http://arxiv.org/abs/2310.00213
Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models. For example, the curvature scores computed by Freesurfer are not rel
Externí odkaz:
http://arxiv.org/abs/2308.09907