liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 68) Show all publications
Jönemo, J. & Eklund, A. (2023). Brain Age Prediction Using 2D Projections Based on Higher-Order Statistical Moments and Eigenslices from 3D Magnetic Resonance Imaging Volumes. Journal of Imaging, 9(12), Article ID 271.
Open this publication in new window or tab >>Brain Age Prediction Using 2D Projections Based on Higher-Order Statistical Moments and Eigenslices from 3D Magnetic Resonance Imaging Volumes
2023 (English)In: Journal of Imaging, E-ISSN 2313-433X, Vol. 9, no 12, article id 271Article in journal (Refereed) Published
Abstract [en]

Brain age prediction from 3D MRI volumes using deep learning has recently become a popular research topic, as brain age has been shown to be an important biomarker. Training deep networks can be very computationally demanding for large datasets like the U.K. Biobank (currently 29,035 subjects). In our previous work, it was demonstrated that using a few 2D projections (mean and standard deviation along three axes) instead of each full 3D volume leads to much faster training at the cost of a reduction in prediction accuracy. Here, we investigated if another set of 2D projections, based on higher-order statistical central moments and eigenslices, leads to a higher accuracy. Our results show that higher-order moments do not lead to a higher accuracy, but that eigenslices provide a small improvement. We also show that an ensemble of such models provides further improvement.

Place, publisher, year, edition, pages
MDPI, 2023
Keywords
Brain age, deep learning, magnetic resonance imaging, convolutional neural network, skewness, kurtosis
National Category
Medical Image Processing Neurosciences Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:liu:diva-199514 (URN)10.3390/jimaging9120271 (DOI)001131474900001 ()38132689 (PubMedID)
Funder
Vinnova, 2021-01954
Note

Funding: ITEA/VINNOVA

Available from: 2023-12-07 Created: 2023-12-07 Last updated: 2024-01-16
Spyretos, C., Tampu, I. E., Eklund, A. & Haj-Hosseini, N. (2023). Classification of Brain Tumour Tissue in Histopathology Images Using Deep Learning. In: : . Paper presented at Medicinteknikdagarna 2023, Stockholm, Sweden, 9-11 oktober, 2023. Stockholm
Open this publication in new window or tab >>Classification of Brain Tumour Tissue in Histopathology Images Using Deep Learning
2023 (English)Conference paper, Poster (with or without abstract) (Other academic)
Abstract [en]

Deep learning models have achieved prominent performance in digital pathology, with the potential to provide healthcare professionals with accurate decision-making assistance in their workflow. In this study, ViT and CNN models were implemented and compared for patch-level classification of four major glioblastoma tissue structures in histology images.

A subset of the IvyGAP dataset (41 subjects, 123 images) was used, stain-normalised and patches of size 256x256 pixels were extracted. A per-subject split approach was applied to obtain training, validation and testing sets. Three models were implemented, a ViT and a CNN trained from scratch, and a ViT pre-trained on a different brain tumour histology dataset. The models' performance was assessed using a range of metrics, including accuracy and Matthew's correlation coefficient (MCC). In addition, calibration experiments were conducted and evaluated to align the models with the ground truth, utilising the temperature scaling technique. The models' uncertainty was estimated using the Monte Carlo dropout method. Lastly, the models were compared using the Wilcoxon signed-rank statistical significance test with Bonferroni correction.

Among the models, the scratch-trained ViT obtained the highest test accuracy of 67% and an MCC of 0.45. The scratch-trained CNN reached a test accuracy of 49% and an MCC of 0.15, and the pre-trained ViT only achieved a test accuracy of 28% and an MCC of 0.034. Comparing the reliability graphs and metrics before and after applying temperature scaling, the subsequent experiments proceeded with the uncalibrated ViTs and the calibrated CNN. The calibrated CNN demonstrated moderate to high uncertainty across classes, and the ViTs had an overall high uncertainty. Statistically, there was no difference among the models at a significance level of 0.017. 

In conclusion, the scratch-trained ViT model considerably outperformed the scratch-trained CNN and the pre-trained ViT in classification. However, there was no statistically significant difference among the models.

Place, publisher, year, edition, pages
Stockholm: , 2023
Keywords
cancer, brain tumor, digital pathology, deep learning, artificial intelligence
National Category
Medical Engineering Medical Image Processing Cancer and Oncology
Identifiers
urn:nbn:se:liu:diva-198158 (URN)
Conference
Medicinteknikdagarna 2023, Stockholm, Sweden, 9-11 oktober, 2023
Available from: 2023-09-27 Created: 2023-09-27 Last updated: 2023-10-04Bibliographically approved
Jönemo, J., Akbar, M. U., Kämpe, R., Hamilton, J. P. & Eklund, A. (2023). Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections. Brain Sciences, 13(9), Article ID 1329.
Open this publication in new window or tab >>Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections
Show others...
2023 (English)In: Brain Sciences, ISSN 2076-3425, E-ISSN 2076-3425, Vol. 13, no 9, article id 1329Article in journal (Refereed) Published
Abstract [en]

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 test accuracy (mean absolute error of about 3.5 years) when predicting age from brain volumes. Using our approach, one training epoch with 20,324 subjects takes 20–50 s using a single GPU, which is two orders of magnitude faster than a small 3D CNN. This speedup is explained by the fact that 3D brain volumes contain a lot of redundant information, which can be efficiently compressed using 2D projections. These results are important for researchers who do not have access to expensive GPU hardware for 3D CNNs.

Place, publisher, year, edition, pages
MDPI, 2023
Keywords
brain age, 3D CNN, 2D projections, deep learning
National Category
Radiology, Nuclear Medicine and Medical Imaging Medical Image Processing
Identifiers
urn:nbn:se:liu:diva-197835 (URN)10.3390/brainsci13091329 (DOI)001077104000001 ()37759930 (PubMedID)
Funder
Vinnova, 2021-01954
Note

Funding: ITEA/VINNOVA [2021-01954]; Ake Wiberg foundation

Available from: 2023-09-17 Created: 2023-09-17 Last updated: 2024-02-12Bibliographically approved
Jönemo, J., Abramian, D. & Eklund, A. (2023). Evaluation of Augmentation Methods in Classifying Autism Spectrum Disorders from fMRI Data with 3D Convolutional Neural Networks. Diagnostics, 13(17), Article ID 2773.
Open this publication in new window or tab >>Evaluation of Augmentation Methods in Classifying Autism Spectrum Disorders from fMRI Data with 3D Convolutional Neural Networks
2023 (English)In: Diagnostics, ISSN 2075-4418, Vol. 13, no 17, article id 2773Article in journal (Refereed) Published
Abstract [en]

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 millions of parameters. In this study, deep learning was applied to derivatives from resting state functional MRI data, to investigate how different 3D augmentation techniques affect the test accuracy. Specifically, resting state derivatives from 1112 subjects in ABIDE (Autism Brain Imaging Data Exchange) preprocessed were used to train a 3D convolutional neural network (CNN) to classify each subject according to presence or absence of autism spectrum disorder. The results show that augmentation only provide minor improvements to the test accuracy.

Place, publisher, year, edition, pages
MDPI, 2023
Keywords
functional MRI; resting state; deep learning; augmentation; autism
National Category
Medical Image Processing Neurosciences
Identifiers
urn:nbn:se:liu:diva-197216 (URN)10.3390/diagnostics13172773 (DOI)001061986000001 ()37685311 (PubMedID)
Funder
Vinnova, 2021-01954Swedish Research Council, 2017-04889Åke Wiberg Foundation, M22-0088
Note

Funding: Swedish research council [2017-04889]; ITEA/VINNOVA [2021-01954]; Ake Wiberg foundation [M22-0088]

Available from: 2023-08-27 Created: 2023-08-27 Last updated: 2024-01-17
Abramian, D., Blystad, I. & Eklund, A. (2023). Evaluation of inverse treatment planning for gamma knife radiosurgery using fMRI brain activation maps as organs at risk. Medical physics (Lancaster), 50(9), 5297-5311
Open this publication in new window or tab >>Evaluation of inverse treatment planning for gamma knife radiosurgery using fMRI brain activation maps as organs at risk
2023 (English)In: Medical physics (Lancaster), ISSN 0094-2405, Vol. 50, no 9, p. 5297-5311Article in journal (Refereed) Published
Abstract [en]

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 setting maximum radiation dose constraints in the treatment planning process.Purpose: We propose using activation maps from functional MRI (fMRI) to map the eloquent regions of the brain and define functional OARs (fOARs) for Gamma Knife SRS treatment planning.Methods: We implemented a pipeline for analyzing patient fMRI data, generating fOARs from the resulting activation maps, and loading them onto the GammaPlan treatment planning software. We used the Lightning inverse planner to generate multiple treatment plans from open MRI data of five subjects, and evaluated the effects of incorporating the proposed fOARs.Results: The Lightning optimizer designs treatment plans with high conformity to the specified parameters. Setting maximum dose constraints on fOARs successfully limits the radiation dose incident on them, but can have a negative impact on treatment plan quality metrics. By masking out fOAR voxels surrounding the tumor target it is possible to achieve high quality treatment plans while controlling the radiation dose on fOARs.Conclusions: The proposed method can effectively reduce the radiation dose incident on the eloquent brain areas during Gamma Knife SRS of brain tumors.

Place, publisher, year, edition, pages
WILEY, 2023
Keywords
fMRI, radiotherapy, radiosurgery, gamma knife, brain tumor
National Category
Radiology, Nuclear Medicine and Medical Imaging Cancer and Oncology
Identifiers
urn:nbn:se:liu:diva-196436 (URN)10.1002/mp.16660 (DOI)001041239600001 ()37531209 (PubMedID)
Funder
Vinnova, 2018‐02230Vinnova, 2021‐01954
Note

Funding: Centrum foer Industriell Informationsteknologi, Linkoepings Universitet; Vinnova [2018-02230, 2021-01954]

Available from: 2023-08-03 Created: 2023-08-03 Last updated: 2023-12-18
Schilcher, J., Nilsson, A., Andlid, O. & Eklund, A. (2023). Fusion of electronic health records and radiographic images for a multimodal deep learning prediction model of atypical femur fractures. Computers in Biology and Medicine, 168, Article ID 107704.
Open this publication in new window or tab >>Fusion of electronic health records and radiographic images for a multimodal deep learning prediction model of atypical femur fractures
2023 (English)In: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 168, article id 107704Article in journal (Refereed) Published
Abstract [en]

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 rare and the radiologic changes are subtle currently only 7% of AFFs are correctly identified, which hinders adequate treatment for most patients with AFF. Deep learning models could be trained to classify automatically a fracture as AFF or NFF, thereby assisting radiologists in detecting these rare fractures. Historically, for this classification task, only imaging data have been used, using convolutional neural networks (CNN) or vision transformers applied to radiographs. However, to mimic situations in which all available data are used to arrive at a diagnosis, we adopted an approach of deep learning that is based on the integration of image data and tabular data (from electronic health records) for 159 patients with AFF and 914 patients with NFF. We hypothesized that the combinatorial data, compiled from all the radiology departments of 72 hospitals in Sweden and the Swedish National Patient Register, would improve classification accuracy, as compared to using only one modality. At the patient level, the area under the ROC curve (AUC) increased from 0.966 to 0.987 when using the integrated set of imaging data and seven pre-selected variables, as compared to only using imaging data. More importantly, the sensitivity increased from 0.796 to 0.903. We found a greater impact of data fusion when only a randomly selected subset of available images was used to make the image and tabular data more balanced for each patient. The AUC then increased from 0.949 to 0.984, and the sensitivity increased from 0.727 to 0.849.

These AUC improvements are not large, mainly because of the already excellent performance of the CNN (AUC of 0.966) when only images are used. However, the improvement is clinically highly relevant considering the importance of accuracy in medical diagnostics. We expect an even greater effect when imaging data from a clinical workflow, comprising a more diverse set of diagnostic images, are used.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Atypical femoral fractures; Multimodal; Fusion; Deep learning
National Category
Orthopaedics Medical Image Processing Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:liu:diva-199184 (URN)10.1016/j.compbiomed.2023.107704 (DOI)001119023400001 ()37980797 (PubMedID)
Funder
Vinnova, 2021-01954Knut and Alice Wallenberg FoundationSwedish Research Council, 2023-01942
Note

Funding: ITEA/VINNOVA [2021-01954]; Region Ostergotland; Knut and Alice Wallenberg Foundation; Swedish research council [2023-01942]

Available from: 2023-11-15 Created: 2023-11-15 Last updated: 2024-01-17Bibliographically approved
Svantesson, M., Olausson, H., Eklund, A. & Thordstein, M. (2023). Get a New Perspective on EEG: Convolutional Neural Network Encoders for Parametric t-SNE. Brain Sciences, 13(3), Article ID 453.
Open this publication in new window or tab >>Get a New Perspective on EEG: Convolutional Neural Network Encoders for Parametric t-SNE
2023 (English)In: Brain Sciences, ISSN 2076-3425, E-ISSN 2076-3425, Vol. 13, no 3, article id 453Article in journal (Refereed) Published
Abstract [en]

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 not known which features are optimal. The principle of t-SNE was used to train convolutional neural network (CNN) encoders to learn to produce both a high- and a low-dimensional representation, eliminating the need for feature engineering. To evaluate the method, the Temple University EEG Corpus was used to create three datasets with distinct EEG characters: (1) wakefulness and sleep; (2) interictal epileptiform discharges; and (3) seizure activity. The CNN encoders produced low-dimensional representations of the datasets with a structure that conformed well to the EEG characters and generalized to new data. Compared to parametric t-SNE for either a short-time Fourier transform or wavelet representation of the datasets, the developed CNN encoders performed equally well in separating categories, as assessed by support vector machines. The CNN encoders generally produced a higher degree of clustering, both visually and in the number of clusters detected by k-means clustering. The developed principle is promising and could be further developed to create general tools for exploring relations in EEG data.

Place, publisher, year, edition, pages
MDPI, 2023
Keywords
EEG; deep learning; convolutional neural networks; t-SNE; categories
National Category
Neurology Medical Image Processing Computer Sciences
Identifiers
urn:nbn:se:liu:diva-192243 (URN)10.3390/brainsci13030453 (DOI)000957780800001 ()36979263 (PubMedID)
Funder
Vinnova, 2021-01954Region Östergötland, LIO-936176 and RÖ-941359Linköpings universitet
Note

Funding: Linkoping University; University Hospital of Linkoeping; ALF of Region OEstergoetland [LIO-936176, ROE-941359]; ITEA3/VINNOVA

Available from: 2023-03-07 Created: 2023-03-07 Last updated: 2023-04-18
Boito, D., Eklund, A., Tisell, A., Levi, R., Özarslan, E. & Blystad, I. (2023). MRI with generalized diffusion encoding reveals damaged white matter in patients previously hospitalized for COVID-19 and with persisting symptoms at follow-up. Brain Communications, 5(6), Article ID fcad284.
Open this publication in new window or tab >>MRI with generalized diffusion encoding reveals damaged white matter in patients previously hospitalized for COVID-19 and with persisting symptoms at follow-up
Show others...
2023 (English)In: Brain Communications, E-ISSN 2632-1297, Vol. 5, no 6, article id fcad284Article in journal (Refereed) Published
Abstract [en]

There is mounting evidence of the long-term effects of COVID-19 on the central nervous system, with patients experiencing diverse symptoms, often suggesting brain involvement. Conventional brain MRI of these patients shows unspecific patterns, with no clear connection of the symptomatology to brain tissue abnormalities, whereas diffusion tensor studies and volumetric analyses detect measurable changes in the brain after COVID-19. Diffusion MRI exploits the random motion of water molecules to achieve unique sensitivity to structures at the microscopic level, and new sequences employing generalized diffusion encoding provide structural information which are sensitive to intravoxel features. In this observational study, a total of 32 persons were investigated: 16 patients previously hospitalized for COVID-19 with persisting symptoms of post-COVID condition (mean age 60 years: range 41–79, all male) at 7-month follow-up and 16 matched controls, not previously hospitalized for COVID-19, with no post-COVID symptoms (mean age 58 years, range 46–69, 11 males). Standard MRI and generalized diffusion encoding MRI were employed to examine the brain white matter of the subjects. To detect possible group differences, several tissue microstructure descriptors obtainable with the employed diffusion sequence, the fractional anisotropy, mean diffusivity, axial diffusivity, radial diffusivity, microscopic anisotropy, orientational coherence (Cc) and variance in compartment’s size (CMD) were analysed using the tract-based spatial statistics framework. The tract-based spatial statistics analysis showed widespread statistically significant differences (P < 0.05, corrected for multiple comparisons using the familywise error rate) in all the considered metrics in the white matter of the patients compared to the controls. Fractional anisotropy, microscopic anisotropy and Cc were lower in the patient group, while axial diffusivity, radial diffusivity, mean diffusivity and CMD were higher. Significant changes in fractional anisotropy, microscopic anisotropy and CMD affected approximately half of the analysed white matter voxels located across all brain lobes, while changes in Cc were mainly found in the occipital parts of the brain. Given the predominant alteration in microscopic anisotropy compared to Cc, the observed changes in diffusion anisotropy are mostly due to loss of local anisotropy, possibly connected to axonal damage, rather than white matter fibre coherence disruption. The increase in radial diffusivity is indicative of demyelination, while the changes in mean diffusivity and CMD are compatible with vasogenic oedema. In summary, these widespread alterations of white matter microstructure are indicative of vasogenic oedema, demyelination and axonal damage. These changes might be a contributing factor to the diversity of central nervous system symptoms that many patients experience after COVID-19.

Place, publisher, year, edition, pages
Oxford University Press, 2023
Keywords
MRI; Q-space trajectory imaging; microscopic fractional anisotropy; fractional anisotropy; COVID-19
National Category
Radiology, Nuclear Medicine and Medical Imaging Neurosciences Medical Image Processing
Identifiers
urn:nbn:se:liu:diva-199215 (URN)10.1093/braincomms/fcad284 (DOI)001103246200003 ()37953843 (PubMedID)
Funder
Vinnova, 2021-01954Wallenberg Foundations
Note

Funding: Analytic Imaging Diagnostic Arena (AIDA), a Medtech4Health initiative; ITEA/ VINNOVA (The Swedish Innovation Agency) project ASSIST (Automation, Surgery Support and Intuitive 3D visualization to optimize workflow in IGT SysTems) [2021-01954]; Wallenberg Center for Molecular Medicine

Available from: 2023-11-19 Created: 2023-11-19 Last updated: 2024-01-03Bibliographically approved
Nilsonne, G., Dahlgren, P., Eklund, A., Danielsson, H., Carlsson, R., Innes-Ker, Å., . . . Willén, R. (2023). "Sluta betala för att få publicera forskning". Svenska Dagbladet
Open this publication in new window or tab >>"Sluta betala för att få publicera forskning"
Show others...
2023 (Swedish)In: Svenska Dagbladet, ISSN 1101-2412Article in journal, News item (Other (popular science, discussion, etc.)) Published
Place, publisher, year, edition, pages
Stockholm: Svenska Dagbladet AB & Co, 2023
Keywords
öppen tillgång
Identifiers
urn:nbn:se:liu:diva-192754 (URN)
Available from: 2023-03-29 Created: 2023-03-29 Last updated: 2023-04-04Bibliographically approved
Richie-Halford, A., Cieslak, M., Ai, L., Caffarra, S., Covitz, S., Franco, A. R., . . . Rokem, A. (2022). An analysis-ready and quality controlled resource for pediatric brain white-matter research. Scientific Data, 9(1)
Open this publication in new window or tab >>An analysis-ready and quality controlled resource for pediatric brain white-matter research
Show others...
2022 (English)In: Scientific Data, E-ISSN 2052-4463, Vol. 9, no 1Article in journal (Refereed) Published
Abstract [en]

We created a set of resources to enable research based on openly-available diffusion MRI (dMRI) data from the Healthy Brain Network (HBN) study. First, we curated the HBN dMRI data (N?=?2747) into the Brain Imaging Data Structure and preprocessed it according to best-practices, including denoising and correcting for motion effects, susceptibility-related distortions, and eddy currents. Preprocessed, analysis-ready data was made openly available. Data quality plays a key role in the analysis of dMRI. To optimize QC and scale it to this large dataset, we trained a neural network through the combination of a small data subset scored by experts and a larger set scored by community scientists. The network performs QC highly concordant with that of experts on a held out set (ROC-AUC?=?0.947). A further analysis of the neural network demonstrates that it relies on image features with relevance to QC. Altogether, this work both delivers resources to advance transdiagnostic research in brain connectivity and pediatric mental health, and establishes a novel paradigm for automated QC of large datasets.

Place, publisher, year, edition, pages
Nature Publishing Group, 2022
National Category
Radiology, Nuclear Medicine and Medical Imaging
Identifiers
urn:nbn:se:liu:diva-189363 (URN)10.1038/s41597-022-01695-7 (DOI)000866490900002 ()36224186 (PubMedID)
Available from: 2022-10-19 Created: 2022-10-19 Last updated: 2023-10-02Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-7061-7995

Search in DiVA

Show all publications