Arrow Research search

Author name cluster

Geert Jan Biessels

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers
1 author row

Possible papers

15

YNICL Journal 2025 Journal Article

Individualized lesion-symptom mapping using explainable artificial intelligence for the cognitive impact of white matter hyperintensities

  • Ryanne Offenberg
  • Alberto de Luca
  • Geert Jan Biessels
  • Frederik Barkhof
  • Wiesje M. van der Flier
  • Argonde C. van Harten
  • Ewoud van der Lelij
  • Josien Pluim

Lesion-symptom mapping methods assess the relationship between lesions caused by cerebral small vessel disease and cognition, but current technology like support vector regression (SVR)) primarily provide group-level results. We propose a novel lesion-symptom mapping approach that can indicate how lesion patterns contribute to cognitive impairment on an individual level. A convolutional neural network (CNN) predicts cognitive scores and is combined with explainable artificial intelligence (XAI) to map the relation between cognition and vascular lesions. This method was evaluated primarily using real white matter hyperintensity maps of 821 memory clinic patients and simulated cognitive data, with weighted lesions and noise levels. Simulated data provided ground truth locations to assess predictive performance of the CNN and accuracy of strategic lesion identification by XAI, using an established lesion-symptom mapping method, SVR, and a simple fully connected neural network (FNN) as benchmarks. Real cognitive scores were used in a final proof-of-principle analysis. Predictive performance in simulation experiments was high for the CNN (R2 = 0. 964), SVR (R2 = 0. 875), and FNN (R2 = 0. 863). CNN with XAI provided patient-specific attribution maps that highlighted the ground truth locations. All methods showed similar sensitivity to noise. Using real cognitive scores, SVR (R2 = 0. 291) obtained a somewhat higher predictive performance than the CNN (R2 = 0. 216), although both methods substantially exceeded the predictive performance of total WMH volume alone (R2 = 0. 013). The FNN performed worse on real data (R2 = 0. 020). To conclude, results show that CNNs combined with XAI can perform lesion-symptom mapping and generate individual attribution maps, which could be a valuable feature with further method development.

Details DOI

YNICL Journal 2023 Journal Article

Spatial distributions of white matter hyperintensities on brain MRI: A pooled analysis of individual participant data from 11 memory clinic cohorts

  • Mirthe Coenen
  • Geert Jan Biessels
  • Charles DeCarli
  • Evan F. Fletcher
  • Pauline M. Maillard
  • Frederik Barkhof
  • Josephine Barnes
  • Thomas Benke

INTRODUCTION: The spatial distribution of white matter hyperintensities (WMH) on MRI is often considered in the diagnostic evaluation of patients with cognitive problems. In some patients, clinicians may classify WMH patterns as "unusual", but this is largely based on expert opinion, because detailed quantitative information about WMH distribution frequencies in a memory clinic setting is lacking. Here we report voxel wise 3D WMH distribution frequencies in a large multicenter dataset and also aimed to identify individuals with unusual WMH patterns. METHODS: Individual participant data (N = 3525, including 777 participants with subjective cognitive decline, 1389 participants with mild cognitive impairment and 1359 patients with dementia) from eleven memory clinic cohorts, recruited through the Meta VCI Map Consortium, were used. WMH segmentations were provided by participating centers or performed in Utrecht and registered to the Montreal Neurological Institute (MNI)-152 brain template for spatial normalization. To determine WMH distribution frequencies, we calculated WMH probability maps at voxel level. To identify individuals with unusual WMH patterns, region-of-interest (ROI) based WMH probability maps, rule-based scores, and a machine learning method (Local Outlier Factor (LOF)), were implemented. RESULTS: WMH occurred in 82% of voxels from the white matter template with large variation between subjects. Only a small proportion of the white matter (1.7%), mainly in the periventricular areas, was affected by WMH in at least 20% of participants. A large portion of the total white matter was affected infrequently. Nevertheless, 93.8% of individual participants had lesions in voxels that were affected in less than 2% of the population, mainly located in subcortical areas. Only the machine learning method effectively identified individuals with unusual patterns, in particular subjects with asymmetric WMH distribution or with WMH at relatively rarely affected locations despite common locations not being affected. DISCUSSION: Aggregating data from several memory clinic cohorts, we provide a detailed 3D map of WMH lesion distribution frequencies, that informs on common as well as rare localizations. The use of data-driven analysis with LOF can be used to identify unusual patterns, which might serve as an alert that rare causes of WMH should be considered.

Details DOI

YNICL Journal 2022 Journal Article

Improved sensitivity and precision in multicentre diffusion MRI network analysis using thresholding and harmonization

  • Bruno M. de Brito Robalo
  • Alberto de Luca
  • Christopher Chen
  • Anna Dewenter
  • Marco Duering
  • Saima Hilal
  • Huiberdina L. Koek
  • Anna Kopczak

PURPOSE: To investigate if network thresholding and raw data harmonization improve consistency of diffusion MRI (dMRI)-based brain networks while also increasing precision and sensitivity to detect disease effects in multicentre datasets. METHODS: Brain networks were reconstructed from dMRI of five samples with cerebral small vessel disease (SVD; 629 patients, 166 controls), as a clinically relevant exemplar condition for studies on network integrity. We evaluated consistency of network architecture in age-matched controls, by calculating cross-site differences in connection probability and fractional anisotropy (FA). Subsequently we evaluated precision and sensitivity to disease effects by identifying connections with low FA in sporadic SVD patients relative to controls, using more severely affected patients with a pure form of genetically defined SVD as reference. RESULTS: In controls, thresholding and harmonization improved consistency of network architecture, minimizing cross-site differences in connection probability and FA. In patients relative to controls, thresholding improved precision to detect disrupted connections by removing false positive connections (precision, before: 0.09-0.19; after: 0.38-0.70). Before harmonization, sensitivity was low within individual sites, with few connections surviving multiple testing correction (k = 0-25 connections). Harmonization and pooling improved sensitivity (k = 38), while also achieving higher precision when combined with thresholding (0.97). CONCLUSION: We demonstrated that network consistency, precision and sensitivity to detect disease effects in SVD are improved by thresholding and harmonization. We recommend introducing these techniques to leverage large existing multicentre datasets to better understand the impact of disease on brain networks.

Details DOI

YNICL Journal 2022 Journal Article

Network impact score is an independent predictor of post-stroke cognitive impairment: A multicenter cohort study in 2341 patients with acute ischemic stroke

  • J. Matthijs Biesbroek
  • Nick A. Weaver
  • Hugo P. Aben
  • Hugo J. Kuijf
  • Jill Abrigo
  • Hee-Joon Bae
  • Mélanie Barbay
  • Jonathan G. Best

BACKGROUND: Post-stroke cognitive impairment (PSCI) is a common consequence of stroke. Accurate prediction of PSCI risk is challenging. The recently developed network impact score, which integrates information on infarct location and size with brain network topology, may improve PSCI risk prediction. AIMS: To determine if the network impact score is an independent predictor of PSCI, and of cognitive recovery or decline. METHODS: We pooled data from patients with acute ischemic stroke from 12 cohorts through the Meta VCI Map consortium. PSCI was defined as impairment in ≥ 1 cognitive domain on neuropsychological examination, or abnormal Montreal Cognitive Assessment. Cognitive recovery was defined as conversion from PSCI 24 months) and cognitive recovery or decline using logistic regression. Models were adjusted for age, sex, education, prior stroke, infarct volume, and study site. RESULTS: We included 2341 patients with 4657 cognitive assessments. PSCI was present in 398/844 patients (47%) 24 months. Cognitive recovery occurred in 64/181 (35%) patients and cognitive decline in 26/287 (9%). The network impact score predicted PSCI in the univariable (OR 1.50, 95%CI 1.34-1.68) and multivariable (OR 1.27, 95%CI 1.10-1.46) GEE model, with similar ORs in the logistic regression models for specified post-stroke intervals. The network impact score was not associated with cognitive recovery or decline. CONCLUSIONS: The network impact score is an independent predictor of PSCI. As such, the network impact score may contribute to a more precise and individualized cognitive prognostication in patients with ischemic stroke. Future studies should address if multimodal prediction models, combining the network impact score with demographics, clinical characteristics and other advanced brain imaging biomarkers, will provide accurate individualized prediction of PSCI. A tool for calculating the network impact score is freely available at https://metavcimap.org/features/software-tools/lsm-viewer/.

Details DOI

YNICL Journal 2021 Journal Article

Cross-cohort generalizability of deep and conventional machine learning for MRI-based diagnosis and prediction of Alzheimer’s disease

  • Esther E. Bron
  • Stefan Klein
  • Janne M. Papma
  • Lize C. Jiskoot
  • Vikram Venkatraghavan
  • Jara Linders
  • Pauline Aalten
  • Peter Paul De Deyn

This work validates the generalizability of MRI-based classification of Alzheimer's disease (AD) patients and controls (CN) to an external data set and to the task of prediction of conversion to AD in individuals with mild cognitive impairment (MCI). We used a conventional support vector machine (SVM) and a deep convolutional neural network (CNN) approach based on structural MRI scans that underwent either minimal pre-processing or more extensive pre-processing into modulated gray matter (GM) maps. Classifiers were optimized and evaluated using cross-validation in the Alzheimer's Disease Neuroimaging Initiative (ADNI; 334 AD, 520 CN). Trained classifiers were subsequently applied to predict conversion to AD in ADNI MCI patients (231 converters, 628 non-converters) and in the independent Health-RI Parelsnoer Neurodegenerative Diseases Biobank data set. From this multi-center study representing a tertiary memory clinic population, we included 199 AD patients, 139 participants with subjective cognitive decline, 48 MCI patients converting to dementia, and 91 MCI patients who did not convert to dementia. AD-CN classification based on modulated GM maps resulted in a similar area-under-the-curve (AUC) for SVM (0.940; 95%CI: 0.924–0.955) and CNN (0.933; 95%CI: 0.918–0.948). Application to conversion prediction in MCI yielded significantly higher performance for SVM (AUC = 0.756; 95%CI: 0.720-0.788) than for CNN (AUC = 0.742; 95%CI: 0.709-0.776) (p<0.01 for McNemar's test). In external validation, performance was slightly decreased. For AD-CN, it again gave similar AUCs for SVM (0.896; 95%CI: 0.855–0.932) and CNN (0.876; 95%CI: 0.836–0.913). For prediction in MCI, performances decreased for both SVM (AUC = 0.665; 95%CI: 0.576-0.760) and CNN (AUC = 0.702; 95%CI: 0.624-0.786). Both with SVM and CNN, classification based on modulated GM maps significantly outperformed classification based on minimally processed images (p=0.01). Deep and conventional classifiers performed equally well for AD classification and their performance decreased only slightly when applied to the external cohort. We expect that this work on external validation contributes towards translation of machine learning to clinical practice.

Details DOI

YNICL Journal 2021 Journal Article

Diffusion MRI harmonization enables joint-analysis of multicentre data of patients with cerebral small vessel disease

  • Bruno M. de Brito Robalo
  • Geert Jan Biessels
  • Christopher Chen
  • Anna Dewenter
  • Marco Duering
  • Saima Hilal
  • Huiberdina L. Koek
  • Anna Kopczak

OBJECTIVES: Acquisition-related differences in diffusion magnetic resonance imaging (dMRI) hamper pooling of multicentre data to achieve large sample sizes. A promising solution is to harmonize the raw diffusion signal using rotation invariant spherical harmonic (RISH) features, but this has not been tested in elderly subjects. Here we aimed to establish if RISH harmonization effectively removes acquisition-related differences in multicentre dMRI of elderly subjects with cerebral small vessel disease (SVD), while preserving sensitivity to disease effects. METHODS: Five cohorts of patients with SVD (N = 397) and elderly controls (N = 175) with 3 Tesla MRI on different systems were included. First, to establish effectiveness of harmonization, the RISH method was trained with data of 13 to 15 age and sex-matched controls from each site. Fractional anisotropy (FA) and mean diffusivity (MD) were compared in matched controls between sites using tract-based spatial statistics (TBSS) and voxel-wise analysis, before and after harmonization. Second, to assess sensitivity to disease effects, we examined whether the contrast (effect sizes of FA, MD and peak width of skeletonized MD - PSMD) between patients and controls within each site remained unaffected by harmonization. Finally, we evaluated the association between white matter hyperintensity (WMH) burden, FA, MD and PSMD using linear regression analyses both within individual cohorts as well as with pooled scans from multiple sites, before and after harmonization. RESULTS: = 0.60). CONCLUSIONS: We showed that RISH harmonization effectively removes acquisition-related differences in dMRI of elderly subjects while preserving sensitivity to SVD-related effects. This study provides proof of concept for future multicentre SVD studies with pooled datasets.

Details DOI

YNIMG Journal 2021 Journal Article

Strain Tensor Imaging: Cardiac-induced brain tissue deformation in humans quantified with high-field MRI

  • Jacob Jan Sloots
  • Geert Jan Biessels
  • Alberto de Luca
  • Jaco J.M. Zwanenburg

The cardiac cycle induces blood volume pulsations in the cerebral microvasculature that cause subtle deformation of the surrounding tissue. These tissue deformations are highly relevant as a potential source of information on the brain's microvasculature as well as of tissue condition. Besides, cyclic brain tissue deformations may be a driving force in clearance of brain waste products. We have developed a high-field magnetic resonance imaging (MRI) technique to capture these tissue deformations with full brain coverage and sufficient signal-to-noise to derive the cardiac-induced strain tensor on a voxel by voxel basis, that could not be assessed non-invasively before. We acquired the strain tensor with 3 mm isotropic resolution in 9 subjects with repeated measurements for 8 subjects. The strain tensor yielded both positive and negative eigenvalues (principle strains), reflecting the Poison effect in tissue. The principle strain associated with expansion followed the known funnel shaped brain motion pattern pointing towards the foramen magnum. Furthermore, we evaluate two scalar quantities from the strain tensor: the volumetric strain and octahedral shear strain. These quantities showed consistent patterns between subjects, and yielded repeatable results: the peak systolic volumetric strain (relative to end-diastolic strain) was 4. 19⋅10−4 ± 0. 78⋅10−4 and 3. 98⋅10−4 ± 0. 44⋅10−4 (mean ± standard deviation for first and second measurement, respectively), and the peak octahedral shear strain was 2. 16⋅10−3 ± 0. 31⋅10−3 and 2. 31⋅10−3 ± 0. 38⋅10−3, for the first and second measurement, respectively. The volumetric strain was typically highest in the cortex and lowest in the periventricular white matter, while anisotropy was highest in the subcortical white matter and basal ganglia. This technique thus reveals new, regional information on the brain's cardiac-induced deformation characteristics, and has the potential to advance our understanding of the role of microvascular pulsations in health and disease.

Details DOI

YNIMG Journal 2020 Journal Article

Cardiac and respiration-induced brain deformations in humans quantified with high-field MRI

  • Jacob Jan Sloots
  • Geert Jan Biessels
  • Jaco J.M. Zwanenburg

Microvascular blood volume pulsations due to the cardiac and respiratory cycles induce brain tissue deformation and, as such, are considered to drive the brain’s waste clearance system. We have developed a high-field magnetic resonance imaging (MRI) technique to quantify both cardiac and respiration-induced tissue deformations, which could not be assessed noninvasively before. The technique acquires motion encoded snapshot images in which various forms of motion and confounders are entangled. First, we optimized the motion sensitivity for application in the human brain. Next, we isolated the heartbeat and respiration-related deformations, by introducing a linear model that fits the snapshot series to the recorded physiological information. As a result, we obtained maps of the physiological tissue deformation with 3mm isotropic spatial resolution. Heartbeat and respiration-induced volumetric strain were significantly different from zero in the basal ganglia (median (25–75% interquartile range): 0. 85·10−3 (0. 39·10−3–1. 05·10−3), p ​= ​0. 0008 and −0. 28·10−3 (−0. 41·10−3–0. 06·10−3), p ​= ​0. 047, respectively. Smaller volumetric strains were observed in the white matter of the centrum semi ovale (0. 28·10−3 (0–0. 59·10−3) and −0. 06·10−3 (−0. 17·10−3–0. 20·10−3)), which was only significant for the heartbeat (p ​= ​0. 02 and p ​= ​0. 7, respectively). Furthermore, heartbeat-induced volumetric strain was about three times larger than respiration-induced volumetric strain. This technique opens a window on the driving forces of the human brain clearance system.

Details DOI

YNICL Journal 2018 Journal Article

Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI

  • Pim Moeskops
  • Jeroen de Bresser
  • Hugo J. Kuijf
  • Adriënne M. Mendrik
  • Geert Jan Biessels
  • Josien P.W. Pluim
  • Ivana Išgum

Automatic segmentation of brain tissues and white matter hyperintensities of presumed vascular origin (WMH) in MRI of older patients is widely described in the literature. Although brain abnormalities and motion artefacts are common in this age group, most segmentation methods are not evaluated in a setting that includes these items. In the present study, our tissue segmentation method for brain MRI was extended and evaluated for additional WMH segmentation. Furthermore, our method was evaluated in two large cohorts with a realistic variation in brain abnormalities and motion artefacts. The method uses a multi-scale convolutional neural network with a T1-weighted image, a T2-weighted fluid attenuated inversion recovery (FLAIR) image and a T1-weighted inversion recovery (IR) image as input. The method automatically segments white matter (WM), cortical grey matter (cGM), basal ganglia and thalami (BGT), cerebellum (CB), brain stem (BS), lateral ventricular cerebrospinal fluid (lvCSF), peripheral cerebrospinal fluid (pCSF), and WMH. Our method was evaluated quantitatively with images publicly available from the MRBrainS13 challenge (n =20), quantitatively and qualitatively in relatively healthy older subjects (n =96), and qualitatively in patients from a memory clinic (n =110). The method can accurately segment WMH (Overall Dice coefficient in the MRBrainS13 data of 0. 67) without compromising performance for tissue segmentations (Overall Dice coefficients in the MRBrainS13 data of 0. 87 for WM, 0. 85 for cGM, 0. 82 for BGT, 0. 93 for CB, 0. 92 for BS, 0. 93 for lvCSF, 0. 76 for pCSF). Furthermore, the automatic WMH volumes showed a high correlation with manual WMH volumes (Spearman's ρ =0. 83 for relatively healthy older subjects). In both cohorts, our method produced reliable segmentations (as determined by a human observer) in most images (relatively healthy/memory clinic: tissues 88%/77% reliable, WMH 85%/84% reliable) despite various degrees of brain abnormalities and motion artefacts. In conclusion, this study shows that a convolutional neural network-based segmentation method can accurately segment brain tissues and WMH in MR images of older patients with varying degrees of brain abnormalities and motion artefacts.

Details DOI

YNICL Journal 2018 Journal Article

The cumulative effect of small vessel disease lesions is reflected in structural brain networks of memory clinic patients

  • Rutger Heinen
  • Naomi Vlegels
  • Jeroen de Bresser
  • Alexander Leemans
  • Geert Jan Biessels
  • Yael D. Reijmer

Background and purpose: Mechanisms underlying cognitive impairment in patients with small vessel disease (SVD) are still unknown. We hypothesized that cognition is affected by the cumulative effect of multiple SVD-related lesions on brain connectivity. We therefore assessed the relationship between the total SVD burden on MRI, global brain network efficiency, and cognition in memory clinic patients with vascular brain injury. Methods: 173 patients from the memory clinic of the University Medical Center Utrecht underwent a 3 T brain MRI scan (including diffusion MRI sequences) and neuropsychological testing. MRI markers for SVD were rated and compiled in a previously developed total SVD score. Structural brain networks were reconstructed using fiber tractography followed by graph theoretical analysis. The relationship between total SVD burden score, global network efficiency and cognition was assessed using multiple linear regression analyses. Results: = .12). Conclusion: Global network efficiency is sensitive to the cumulative effect of multiple manifestations of SVD on brain connectivity. Global network efficiency may therefore serve as a useful marker for functionally relevant SVD-related brain injury in clinical trials.

Details DOI

YNICL Journal 2013 Journal Article

Hippocampal T2 hyperintensities on 7 Tesla MRI

  • Susanne J. van Veluw
  • Laura E.M. Wisse
  • Hugo J. Kuijf
  • Wim G.M. Spliet
  • Jeroen Hendrikse
  • Peter R. Luijten
  • Mirjam I. Geerlings
  • Geert Jan Biessels

Hippocampal focal T2 hyperintensities (HT2Hs), also referred to as hippocampal sulcal cavities, are a common finding on Magnetic Resonance (MR) images. There is uncertainty about their etiology and clinical significance. In this study we aimed to describe these HT2Hs in more detail using high resolution 7 Tesla MR imaging, addressing 1) the MR signal characteristics of HT2Hs, 2) their occurrence frequency, 3) their location within the hippocampus, and 4) their relation with age. We also performed an explorative post-mortem study to examine the histology of HT2Hs. Fifty-eight persons without a history of invalidating neurological or psychiatric disease (mean age 64 ± 8 years; range 43-78 years), recruited through their general practitioners, were included in this study. They all underwent 7 Tesla MRI, including a T1, T2, and FLAIR image. MR signal characteristics of the HT2Hs were assessed on these images by two raters. Also, the location and number of the HT2Hs were assessed. In addition, four formalin-fixed brain slices from two subjects were scanned overnight. HT2Hs identified in these slices were subjected to histopathological analysis. HT2Hs were present in 97% of the subjects (median number per person 10; range 0-20). All HT2Hs detected on the T2 sequence were hypointense on T1 weighted images. Of all HT2Hs, 94% was hypointense and 6% hyperintense on FLAIR. FLAIR hypointense HT2Hs were all located in the vestigial sulcus of the hippocampus, FLAIR hyperintense HT2Hs in the hippocampal sulcus or the gray matter. Post-mortem MRI and histopathological analysis suggested that the hypointense HT2Hs on FLAIR were cavities filled with cerebrospinal fluid. A hyperintense HT2H on FLAIR proved to be a microinfarct upon microscopy. In conclusion, hippocampal T2Hs are extremely common and unrelated to age. They can be divided into two types (hypo- and hyperintense on FLAIR), probably with different etiology.

Details DOI