Search Results for author: Anders Eklund

Found 20 papers, 9 papers with code

Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models

1 code implementation5 Jun 2023 Muhammad Usman Akbar, Måns Larsson, Anders Eklund

Our results show that segmentation networks trained on synthetic images reach Dice scores that are 80% - 90% of Dice scores when training with real images, but that memorization of the training images can be a problem for diffusion models if the original dataset is too small.

Brain Tumor Segmentation Ethics +3

Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray images

no code implementations12 May 2023 Muhammad Usman Akbar, Wuhao Wang, Anders Eklund

Diffusion models were initially developed for text-to-image generation and are now being utilized to generate high-quality synthetic images.

Efficient brain age prediction from 3D MRI volumes using 2D projections

1 code implementation10 Nov 2022 Johan Jönemo, Muhammad Usman Akbar, Robin Kämpe, J Paul Hamilton, Anders Eklund

Using 3D CNNs on high resolution medical volumes is very computationally demanding, especially for large datasets like the UK Biobank which aims to scan 100, 000 subjects.

Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images

1 code implementation21 Feb 2022 Iulian Emil Tampu, Anders Eklund, Neda Haj-Hosseini

In the application of deep learning on optical coherence tomography (OCT) data, it is common to train classification networks using 2D images originating from volumetric data.

Classification Test

Evaluation of augmentation methods in classifying autism spectrum disorders from fMRI data with 3D convolutional neural networks

no code implementations20 Oct 2021 Johan Jönemo, David Abramian, Anders Eklund

Classifying subjects as healthy or diseased using neuroimaging data has gained a lot of attention during the last 10 years.


What is the best data augmentation for 3D brain tumor segmentation?

2 code implementations26 Oct 2020 Marco Domenico Cirillo, David Abramian, Anders Eklund

Training segmentation networks requires large annotated datasets, which in medical imaging can be hard to obtain.

Brain Tumor Segmentation Data Augmentation +2

Does anatomical contextual information improve 3D U-Net based brain tumor segmentation?

no code implementations26 Oct 2020 Iulian Emil Tampu, Neda Haj-Hosseini, Anders Eklund

The BraTS2020 dataset was used to train and test two standard 3D U-Net models that, in addition to the conventional MR image modalities, used the anatomical contextual information as extra channels in the form of binary masks (CIM) or probability maps (CIP).

Anatomy Brain Tumor Segmentation +3

Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADE

no code implementations13 Sep 2020 Mehdi Foroozandeh, Anders Eklund

Training segmentation networks requires large annotated datasets, but manual annotation is time consuming and costly.


Vox2Vox: 3D-GAN for Brain Tumour Segmentation

3 code implementations19 Mar 2020 Marco Domenico Cirillo, David Abramian, Anders Eklund

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.

Generative Adversarial Network Segmentation +1

Feeding the zombies: Synthesizing brain volumes using a 3D progressive growing GAN

1 code implementation11 Dec 2019 Anders Eklund

Deep learning requires large datasets for training (convolutional) networks with millions of parameters.

Generating fMRI volumes from T1-weighted volumes using 3D CycleGAN

no code implementations19 Jul 2019 David Abramian, Anders Eklund

Registration between an fMRI volume and a T1-weighted volume is challenging, since fMRI volumes contain geometric distortions.

Spatial 3D Matérn priors for fast whole-brain fMRI analysis

no code implementations25 Jun 2019 Per Sidén, Finn Lindgren, David Bolin, Anders Eklund, Mattias Villani

Bayesian whole-brain functional magnetic resonance imaging (fMRI) analysis with three-dimensional spatial smoothing priors have been shown to produce state-of-the-art activity maps without pre-smoothing the data.

Methodology Applications Computation

Graph Spectral Characterization of Brain Cortical Morphology

no code implementations19 Feb 2019 Sevil Maghsadhagh, Anders Eklund, Hamid Behjat

The human brain cortical layer has a convoluted morphology that is unique to each individual.

Characterization of Brain Cortical Morphology Using Localized Topology-Encoding Graphs

no code implementations17 Oct 2018 Sevil Maghsadhagh, Mousa Shamsi, Anders Eklund, Hamid Behjat

Spectral features of these graphs are then studied and proposed as descriptors of cortical morphology.

Refacing: reconstructing anonymized facial features using GANs

1 code implementation15 Oct 2018 David Abramian, Anders Eklund

Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing.

Test Translation +1

Generating Diffusion MRI scalar maps from T1 weighted images using generative adversarial networks

1 code implementation5 Oct 2018 Xuan Gu, Hans Knutsson, Markus Nilsson, Anders Eklund

Diffusion magnetic resonance imaging (diffusion MRI) is a non-invasive microstructure assessment technique.

Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT

3 code implementations20 Jun 2018 Per Welander, Simon Karlsson, Anders Eklund

Here, we evaluate two unsupervised GAN models (CycleGAN and UNIT) for image-to-image translation of T1- and T2-weighted MR images, by comparing generated synthetic MR images to ground truth images.

Computed Tomography (CT) Image-to-Image Translation +2

Gaussian process regression can turn non-uniform and undersampled diffusion MRI data into diffusion spectrum imaging

no code implementations9 Nov 2016 Jens Sjölund, Anders Eklund, Evren Özarslan, Hans Knutsson

We propose to use Gaussian process regression to accurately estimate the diffusion MRI signal at arbitrary locations in q-space.

regression Unity

Cannot find the paper you are looking for? You can Submit a new open access paper.