Anders Eklund

Linköping University | LiU · Department of Biomedical Engineering

Using 3D CNNs on high-resolution medical volumes is very computationally demanding, especially for large datasets like UK Biobank, which aims to scan 100,000 subjects. Here, we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of 3D volumes leads to reasonable...

Classifying subjects as healthy or diseased using neuroimaging data has gained a lot of attention during the last 10 years, and recently, different deep learning approaches have been used. Despite this fact, there has not been any investigation regarding how 3D augmentation can help to create larger datasets, required to train deep networks with mi...

The infiltrative nature of malignant gliomas results in active tumor spreading into the peritumoral edema, which is not visible in conventional magnetic resonance imaging (cMRI) even after contrast injection. MR relaxometry (qMRI) measures relaxation rates dependent on tissue properties, and can offer additional contrast mechanisms to highlight the...

Background: Stereotactic radiosurgery (SRS) can be an effective primary or adjuvant treatment option for intracranial tumors. However, it carries risks of various radiation toxicities, which can lead to functional deficits for the patients. Current inverse planning algorithms for SRS provide an efficient way for sparing organs at risk (OARs) by se...

Atypical femur fractures (AFF) represent a very rare type of fracture that can be difficult to discriminate radiologically from normal femur fractures (NFF). AFFs are associated with drugs that are administered to prevent osteoporosis-related fragility fractures, which are highly prevalent in the elderly population. Given that these fractures are r...

Large annotated datasets are required for training deep learning models, but in medical imaging data sharing is often complicated due to ethics, anonymization and data protection legislation (e.g. the general data protection regulation (GDPR)). Generative AI models, such as generative adversarial networks (GANs) and diffusion models, can today prod...

Brain tumors are among the leading causes of cancer deaths in children. Initial diagnosis based on MR images can be a challenging task for radiologists, depending on the tumor type and location. Deep learning methods could support the diagnosis by predicting the tumor type. A subset (181 subjects) of the data from "Children's Brain Tumor Network" (...

Diffusion models were initially developed for text-to-image generation and are now being utilized to generate high quality synthetic images. Preceded by GANs, diffusion models have shown impressive results using various evaluation metrics. However, commonly used metrics such as FID and IS are not suitable for determining whether diffusion models ar...

Diffusion magnetic resonance imaging (diffusion MRI) is widely employed to probe the diffusive motion of water molecules within the tissue. Numerous diseases and processes affecting the central nervous system can be detected and monitored via diffusion MRI thanks to its sensitivity to microstructural alterations in tissue. The latter has prompted i...

The infiltrative nature of malignant gliomas results in active tumor spreading into the peritumoral edema, which is not visible in conventional magnetic resonance imaging (cMRI) even after contrast injection. MR relaxometry (qMRI) measures relaxation rates dependent on tissue properties, and can offer additional contrast mechanisms to highlight the...

t-distributed stochastic neighbor embedding (t-SNE) is a method for reducing high-dimensional data to a low-dimensional representation, and is mostly used for visualizing data. In parametric t-SNE, a neural network learns to reproduce this mapping. When used for EEG analysis, the data are usually first transformed into a set of features, but it is...

Stereotactic radiosurgery (SRS) can be an effective primary or adjuvant treatment option for intracranial tumors. However, it carries risks of various radiation toxicities, including radionecrosis and functional deficits. Current SRS inverse planning algorithms allow efficient inclusion of organs at risk (OARs) in the treatment planning process, wh...

Background t-distributed stochastic neighbor embedding (t-SNE) is a method for reducing high-dimensional data to a low-dimensional representation and is mostly used for visualizing data. In parametric t-SNE, a neural network learns to reproduce this mapping. When used for EEG analysis, the data is usually first transformed into a set of features, b...

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. Here we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of the 3D volumes leads to reas...

Large annotated datasets are required to train segmentation networks. In medical imaging, it is often difficult, time consuming and expensive to create such datasets, and it may also be difficult to share these datasets with other researchers. Different AI models can today generate very realistic synthetic images, which can potentially be openly sh...

Intraoperative guidance tools for thyroid surgery based on optical coherence tomography (OCT) could aid distinguish between normal and diseased tissue. However, OCT images are difficult to interpret, thus, real‐time automatic analysis could support the clinical decision making. In this study, several deep learning models were investigated for thyro...

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. Given the micrometer resolution of OCT systems, consecutive images are often very similar in both visible structures and noise. Thus, an inappropriate data split can result i...

Peer review is one of the major cornerstones in the academic society, but howto review papers is often something that each researcher has to learn on theirown. Several available resources on how to review papers do, in my opinion,lack several important aspects such as checking the sample size and checkinghow multiple comparison correction was perfo...

Diffusion MRI (dMRI) is the only non-invasive technique sensitive to tissue micro-architecture, which can, in turn, be used to reconstruct tissue microstructure and white matter pathways. The accuracy of such tasks is hampered by the low signal-to-noise ratio in dMRI. Today, the noise is characterized mainly by visual inspection of residual maps an...

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. Given the micrometer resolution of OCT systems, consecutive images are often very similar in both visible structures and noise. Thus, an inappropriate data split can result i...

Analysis of brain connectivity is important for understanding how information is processed by the brain. We propose a novel Bayesian vector autoregression (VAR) hierarchical model for analyzing brain connectivity in a resting-state fMRI data set with autism spectrum disorder (ASD) patients and healthy controls. Our approach models functional and ef...

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 techniques affect the test accuracy. Specifically, we use resting state derivatives from 1,112 subjects in...

Effective, robust, and automatic tools for brain tumor segmentation are needed for the extraction of information useful in treatment planning. Recently, convolutional neural networks have shown remarkable performance in the identification of tumor regions in magnetic resonance (MR) images. Context-aware artificial intelligence is an emerging concep...

Brain activation mapping using functional magnetic resonance imaging (fMRI) has been extensively studied in brain gray matter (GM), whereas in large disregarded for probing white matter (WM). This unbalanced treatment has been in part due to controversies in relation to the nature of the blood oxygenation level-dependent (BOLD) contrast in WM and i...

Brainhack is an innovative meeting format that promotes scientific collaboration and education in an open, inclusive environment. This NeuroView describes the myriad benefits for participants and the research community and how Brainhacks complement conventional formats to augment scientific progress.

In this work, we leverage the Laplacian eigenbasis of voxel-wise white matter (WM) graphs derived from diffusion-weighted MRI data, dubbed WM harmonics, to characterize the spatial structure of WM fMRI data. Our motivation for such a characterization is based on studies that show WM fMRI data exhibit a spatial correlational anisotropy that coincide...

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. Although brain tumours can easily be detected using multi-modal MRI, accurate tumor segmentation is...

Background In clinical practice, EEGs are assessed visually. For practical reasons, recordings often need to be performed with a reduced number of electrodes and artifacts make assessment difficult. To circumvent these obstacles, different interpolation techniques can be utilized. These techniques usually perform better for higher electrode densiti...

Brainhack is an innovative meeting format that promotes scientific collaboration and education in an open and inclusive environment. Departing from the formats of typical scientific workshops, these events are based on grassroots projects and training, and foster open and reproducible scientific practices. We describe here the multifaceted, lasting...

In this work, we leverage the Laplacian eigenbasis of voxel-wise white matter (WM) graphs derived from diffusion-weighted MRI data, dubbed WM harmonics, to characterize the spatial structure of WM fMRI data. By quantifying the energy content of WM fMRI data associated with subsets of WM harmonics across multiple spectral bands, we show that the dat...

Effective, robust and automatic tools for brain tumor segmentation are needed for extraction of information useful in treatment planning. In recent years, convolutional neural networks have shown state-of-the-art performance in the identification of tumor regions in magnetic resonance (MR) images. A large portion of the current research is devoted...

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 (a possible explanation is that the number of training subjects (369) is rather large in the BraTS 2020 dataset). Here we apply...

The BOLD signal in white matter (WM) exhibits a spatial correlation structure that is highly anisotropic and closely linked to local axonal structure in terms of shape and orientation. This suggests that isotropic Gaussian filters conventionally used for smoothing fMRI data are inadequate for enhancing the SNR of the BOLD signal in WM. We propose a...

Development of world-class artificial intelligence (AI) for medical imaging requires access to massive amounts of training data from clinical sources, but effective data sharing is often hindered by uncertainty regarding data protection. We describe an initiative to reduce this uncertainty through a policy describing a national community consensus...

Training segmentation networks requires large annotated datasets, but manual annotation is time consuming and costly. We here investigate if the combination of a noise-to-image GAN and an image-to-image GAN can be used to synthesize realistic brain tumor images as well as the corresponding tumor annotations (labels), to substantially increase the n...

To investigate the potential of optical coherence tomography (OCT) to distinguish between normal and pathologic thyroid tissue, 3D OCT images were acquired on ex vivo thyroid samples from adult subjects (n=22) diagnosed with a variety of pathologies. The follicular structure was analyzed in terms of count, size, density and sphericity. Results show...

Background In clinical practice, EEGs are assessed visually. For practical reasons, recordings often need to be performed with a reduced number of electrodes and artifacts make assessment difficult. To circumvent these obstacles, different interpolation techniques can be utilized. These techniques usually perform better for higher electrode densiti...

We propose a 3D volume-to-volume Generative Adversarial Network (GAN) for segmentation of brain tumours. The proposed model, called Vox2Vox, generates segmentations from multi-channel 3D MR images. The best results are obtained when the generator loss (a 3D U-Net) is weighted 5 times higher compared to the discriminator loss (a 3D GAN). For the Bra...

Analyzing resting state fMRI data is difficult due to a weak signal and several noise sources. Head motion is also a major problem and it is common to apply motion scrubbing, i.e. to remove time points where a subject has moved more than some pre-defined motion threshold. A problem arises if one cohort on average moves more than another, since the...

Deep learning requires large datasets for training (convolutional) networks with millions of parameters. In neuroimaging, there are few open datasets with more than 100 subjects, which makes it difficult to, for example, train a classifier to discriminate controls from diseased persons. Generative adversarial networks (GANs) can be used to synthesi...

Purpose: Susceptibility distortions impact diffusion MRI data analysis and is typically corrected during preprocessing. Correction strategies involve three classes of methods: registration to a structural image, the use of a fieldmap, or the use of images acquired with opposing phase encoding directions. It has been demonstrated that phase encoding...

There are many techniques using sensors and wearable devices for detecting and monitoring patients with Parkinson's disease (PD). A recent development is the utilization of human interaction with computer keyboards for analyzing and identifying motor signs in the early stages of the disease. Current designs for classification of time series of comp...

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 results have provided evidence of the functional significance of the white matter BOLD signal, showing at...

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 fMRI data with local smoothing in each voxel based on a tensor field estimated from a T1-weighted a...

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 fMRI data with local smoothing in each voxel based on a tensor field estimated from a T1-weighted a...

Purpose Susceptibility distortions impact diffusion MRI data analysis and is typically corrected during preprocessing. Correction strategies involve three classes of methods: registration to a structural image, the use of a fieldmap, or the use of images acquired with opposing phase encoding directions. It has been demonstrated that phase encoding...

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 volumes, and vice versa, which can facilitate registration.

The human brain cortical layer has a convoluted morphology that is unique to each individual. Characterization of the cortical morphology is necessary in longitudinal studies of structural brain change, as well as in discriminating individuals in health and disease. A method for encoding the cortical morphology in the form of a graph is presented....

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. The proposed inference algorithms are computationally demanding however, and the proposed spatial priors have several less appealing prop...

Purpose: Estimation of uncertainty of MAP-MRI metrics is an important topic, for several reasons. Bootstrap derived uncertainty, such as the standard deviation, provides valuable information, and can be incorporated in MAP-MRI studies to provide more extensive insight. Methods: In this paper, the uncertainty of different MAP-MRI metrics was quantif...

Diffusion magnetic resonance imaging (diffusion MRI) is a non-invasive microstructure assessment technique. Scalar measures, such as FA (fractional anisotropy) and MD (mean diffusivity), quantifying micro-structural tissue properties can be obtained using diffusion models and data processing pipelines. However, it is costly and time consuming to co...

1 Background Histopathological evaluation and Gleason grading on Hemotoxylin and Eosin (HE) stained specimens is the clinical standard in grading prostate cancer. Recently , deep learning models have been trained to assist pathologists in detecting prostate cancer [1]. However, these predictions could be improved further regarding variations in mor...

The human brain cortical layer has a convoluted morphology that is unique to each individual. Characterization of the cortical morphology is necessary in longitudinal studies of structural brain change, as well as in discriminating individuals in health and disease. A method for encoding the cortical morphology in the form of a graph is presented....

One-sided t-tests are commonly used in the neuroimaging field, but two-sided tests should be the default unless a researcher has a strong reason for using a one-sided test. Here we extend our previous work on cluster false positive rates, which used one-sided tests, to two-sided tests. Briefly, we found that parametric methods perform worse for two...

Methodological research rarely generates a broad interest, yet our work on the validity of cluster inference methods for functional magnetic resonance imaging (fMRI) created intense discussion on both the minutia of our approach and its implications for the discipline. In the present work, we take on various critiques of our work and further explor...

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 to be applied to guarantee anonymity. To test such possibilities, we have applied the novel CycleGAN...

One-sided t-tests are commonly used in the neuroimaging field, but two-sided tests should be the default unless a researcher has a strong reason for using a one-sided test. Here we extend our previous work on cluster false positive rates, which used one-sided tests, to two-sided tests. Briefly, we found that parametric methods perform worse for two...

Diffusion magnetic resonance imaging (diffusion MRI) is a non-invasive microstructure assessment method. Scalar measures quantifying micro-structural tissue properties can be obtained using diffusion models and data processing pipelines. However, it is costly and time consuming to collect high quality diffusion data. We demonstrate how Generative A...

In medical imaging, a general problem is that it is costly and time consuming to collect high quality data from healthy and diseased subjects. Generative adversarial networks (GANs) is a deep learning method that has been developed for synthesizing data. GANs can thereby be used to generate more realistic training data, to improve classification pe...