Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Abramian, David"'
Classifying subjects as healthy or diseased using neuroimaging data has gained a lot of attention during the last 10 years. Here we apply deep learning to derivatives from resting state fMRI data, and investigate how different 3D augmentation techniq
Externí odkaz:
http://arxiv.org/abs/2110.10489
Training segmentation networks requires large annotated datasets, which in medical imaging can be hard to obtain. Despite this fact, data augmentation has in our opinion not been fully explored for brain tumor segmentation. In this project we apply d
Externí odkaz:
http://arxiv.org/abs/2010.13372
Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histological sub-regions, i.e., peritumoral edema, necrotic core, enhancing and non-enhancing tumour core.
Externí odkaz:
http://arxiv.org/abs/2003.13653
Brain activation mapping using functional MRI (fMRI) based on blood oxygenation level-dependent (BOLD) contrast has been conventionally focused on probing gray matter, the BOLD contrast in white matter having been generally disregarded. Recent result
Externí odkaz:
http://arxiv.org/abs/1910.11308
Existing Bayesian spatial priors for functional magnetic resonance imaging (fMRI) data correspond to stationary isotropic smoothing filters that may oversmooth at anatomical boundaries. We propose two anatomically informed Bayesian spatial models for
Externí odkaz:
http://arxiv.org/abs/1910.08415
Anatomy of the human brain constrains the formation of large-scale functional networks. Here, given measured brain activity in gray matter, we interpolate these functional signals into the white matter on a structurally-informed high-resolution voxel
Externí odkaz:
http://arxiv.org/abs/1908.09593
Autor:
Abramian, David, Eklund, Anders
Registration between an fMRI volume and a T1-weighted volume is challenging, since fMRI volumes contain geometric distortions. Here we present preliminary results showing that 3D CycleGAN can be used to synthesize fMRI volumes from T1-weighted volume
Externí odkaz:
http://arxiv.org/abs/1907.08533
Autor:
Abramian, David, Eklund, Anders
Publikováno v:
IEEE International Symposium on Biomedical Imaging, 2019
Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing. However, recent developments in deep learning may raise the bar on the amount of distortion that needs
Externí odkaz:
http://arxiv.org/abs/1810.06455
Autor:
Jönemo, Johan1,2 (AUTHOR), Abramian, David1,2 (AUTHOR), Eklund, Anders1,2,3 (AUTHOR) anders.eklund@liu.se
Publikováno v:
Diagnostics (2075-4418). Sep2023, Vol. 13 Issue 17, p2773. 10p.
Autor:
Abramian, David, Larsson, Martin, Eklund, Anders, Aganj, Iman, Westin, Carl-Fredrik, Behjat, Hamid
Publikováno v:
In NeuroImage 15 August 2021 237