Arrow Research search

Author name cluster

Stefan Klein

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.

14 papers
1 author row

Possible papers

14

YNIMG Journal 2022 Journal Article

Ten years of image analysis and machine learning competitions in dementia

  • Esther E. Bron
  • Stefan Klein
  • Annika Reinke
  • Janne M. Papma
  • Lena Maier-Hein
  • Daniel C. Alexander
  • Neil P. Oxtoby

Machine learning methods exploiting multi-parametric biomarkers, especially based on neuroimaging, have huge potential to improve early diagnosis of dementia and to predict which individuals are at-risk of developing dementia. To benchmark algorithms in the field of machine learning and neuroimaging in dementia and assess their potential for use in clinical practice and clinical trials, seven grand challenges have been organized in the last decade: MIRIAD (2012), Alzheimer's Disease Big Data DREAM (2014), CADDementia (2014), Machine Learning Challenge (2014), MCI Neuroimaging (2017), TADPOLE (2017), and the Predictive Analytics Competition (2019). Based on two challenge evaluation frameworks, we analyzed how these grand challenges are complementing each other regarding research questions, datasets, validation approaches, results and impact. The seven grand challenges addressed questions related to screening, clinical status estimation, prediction and monitoring in (pre-clinical) dementia. There was little overlap in clinical questions, tasks and performance metrics. Whereas this aids providing insight on a broad range of questions, it also limits the validation of results across challenges. The validation process itself was mostly comparable between challenges, using similar methods for ensuring objective comparison, uncertainty estimation and statistical testing. In general, winning algorithms performed rigorous data pre-processing and combined a wide range of input features. Despite high state-of-the-art performances, most of the methods evaluated by the challenges are not clinically used. To increase impact, future challenges could pay more attention to statistical analysis of which factors (i.e., features, models) relate to higher performance, to clinical questions beyond Alzheimer's disease, and to using testing data beyond the Alzheimer's Disease Neuroimaging Initiative. Grand challenges would be an ideal venue for assessing the generalizability of algorithm performance to unseen data of other cohorts. Key for increasing impact in this way are larger testing data sizes, which could be reached by sharing algorithms rather than data to exploit data that cannot be shared. Given the potential and lessons learned in the past ten years, we are excited by the prospects of grand challenges in machine learning and neuroimaging for the next ten years and beyond.

Details DOI

YNIMG Journal 2021 Journal Article

Analyzing the effect of APOE on Alzheimer’s disease progression using an event-based model for stratified populations

  • Vikram Venkatraghavan
  • Stefan Klein
  • Lana Fani
  • Leontine S. Ham
  • Henri Vrooman
  • M. Kamran Ikram
  • Wiro J. Niessen
  • Esther E. Bron

Alzheimer's disease (AD) is the most common form of dementia and is phenotypically heterogeneous. APOE is a triallelic gene which correlates with phenotypic heterogeneity in AD. In this work, we determined the effect of APOE alleles on the disease progression timeline of AD using a discriminative event-based model (DEBM). Since DEBM is a data-driven model, stratification into smaller disease subgroups would lead to more inaccurate models as compared to fitting the model on the entire dataset. Hence our secondary aim is to propose and evaluate novel approaches in which we split the different steps of DEBM into group-aspecific and group-specific parts, where the entire dataset is used to train the group-aspecific parts and only the data from a specific group is used to train the group-specific parts of the DEBM. We performed simulation experiments to benchmark the accuracy of the proposed approaches and to select the optimal approach. Subsequently, the chosen approach was applied to the baseline data of 417 cognitively normal, 235 mild cognitively impaired who convert to AD within 3 years, and 342 AD patients from the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset to gain new insights into the effect of APOE carriership on the disease progression timeline of AD. In the ε4 carrier group, the model predicted with high confidence that CSF Amyloidβ42 and the cognitive score of Alzheimer's Disease Assessment Scale (ADAS) are early biomarkers. Hippocampus was the earliest volumetric biomarker to become abnormal, closely followed by the CSF Phosphorylated Tau181 (PTAU) biomarker. In the homozygous ε3 carrier group, the model predicted a similar ordering among CSF biomarkers. However, the volume of the fusiform gyrus was identified as one of the earliest volumetric biomarker. While the findings in the ε4 carrier and the homozygous ε3 carrier groups fit the current understanding of progression of AD, the finding in the ε2 carrier group did not. The model predicted, with relatively low confidence, CSF Neurogranin as one of the earliest biomarkers along with cognitive score of Mini-Mental State Examination (MMSE). Amyloid β42 was found to become abnormal after PTAU. The presented models could aid understanding of the disease, and in selecting homogeneous group of presymptomatic subjects at-risk of developing symptoms for clinical trials.

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

YNIMG Journal 2021 Journal Article

Longitudinal diffusion MRI analysis using Segis-Net: A single-step deep-learning framework for simultaneous segmentation and registration

  • Bo Li
  • Wiro J. Niessen
  • Stefan Klein
  • Marius de Groot
  • M. Arfan Ikram
  • Meike W. Vernooij
  • Esther E. Bron

This work presents a single-step deep-learning framework for longitudinal image analysis, coined Segis-Net. To optimally exploit information available in longitudinal data, this method concurrently learns a multi-class segmentation and nonlinear registration. Segmentation and registration are modeled using a convolutional neural network and optimized simultaneously for their mutual benefit. An objective function that optimizes spatial correspondence for the segmented structures across time-points is proposed. We applied Segis-Net to the analysis of white matter tracts from N=8045 longitudinal brain MRI datasets of 3249 elderly individuals. Segis-Net approach showed a significant increase in registration accuracy, spatio-temporal segmentation consistency, and reproducibility compared with two multistage pipelines. This also led to a significant reduction in the sample-size that would be required to achieve the same statistical power in analyzing tract-specific measures. Thus, we expect that Segis-Net can serve as a new reliable tool to support longitudinal imaging studies to investigate macro- and microstructural brain changes over time.

Details DOI

YNIMG Journal 2021 Journal Article

Progression along data-driven disease timelines is predictive of Alzheimer’s disease in a population-based cohort

  • Vikram Venkatraghavan
  • Elisabeth J. Vinke
  • Esther E. Bron
  • Wiro J. Niessen
  • M. Arfan Ikram
  • Stefan Klein
  • Meike W. Vernooij

Data-driven disease progression models have provided important insight into the timeline of brain changes in AD phenotypes. However, their utility in predicting the progression of pre-symptomatic AD in a population-based setting has not yet been investigated. In this study, we investigated if the disease timelines constructed in a case-controlled setting, with subjects stratified according to APOE status, are generalizable to a population-based cohort, and if progression along these disease timelines is predictive of AD. Seven volumetric biomarkers derived from structural MRI were considered. We estimated APOE-specific disease timelines of changes in these biomarkers using a recently proposed method called co-initialized discriminative event-based modeling (co-init DEBM). This method can also estimate a disease stage for new subjects by calculating their position along the disease timelines. The model was trained and cross-validated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and tested on the population-based Rotterdam Study (RS) cohort. We compared the diagnostic and prognostic value of the disease stage in the two cohorts. Furthermore, we investigated if the rate of change of disease stage in RS participants with longitudinal MRI data was predictive of AD. In ADNI, the estimated disease timeslines for ϵ4 non-carriers and carriers were found to be significantly different from one another (p<0.001). The estimate disease stage along the respective timelines distinguished AD subjects from controls with an AUC of 0.83 in both APOEϵ4 non-carriers and carriers. In the RS cohort, we obtained an AUC of 0.83 and 0.85 in ϵ4 non-carriers and carriers, respectively. Progression along the disease timelines as estimated by the rate of change of disease stage showed a significant difference (p<0.005) for subjects with pre-symptomatic AD as compared to the general aging population in RS. It distinguished pre-symptomatic AD subjects with an AUC of 0.81 in APOEϵ4 non-carriers and 0.88 in carriers, which was better than any individual volumetric biomarker, or its rate of change, could achieve. Our results suggest that co-init DEBM trained on case-controlled data is generalizable to a population-based cohort setting and that progression along the disease timelines is predictive of the development of AD in the general population. We expect that this approach can help to identify at-risk individuals from the general population for targeted clinical trials as well as to provide biomarker based objective assessment in such trials.

Details DOI

YNICL Journal 2021 Journal Article

The sequence of structural, functional and cognitive changes in multiple sclerosis

  • Iris Dekker
  • Menno M. Schoonheim
  • Vikram Venkatraghavan
  • Anand J.C. Eijlers
  • Iman Brouwer
  • Esther E. Bron
  • Stefan Klein
  • Mike P. Wattjes

BACKGROUND: As disease progression remains poorly understood in multiple sclerosis (MS), we aim to investigate the sequence in which different disease milestones occur using a novel data-driven approach. METHODS: We analysed a cohort of 295 relapse-onset MS patients and 96 healthy controls, and considered 28 features, capturing information on T2-lesion load, regional brain and spinal cord volumes, resting-state functional centrality ("hubness"), microstructural tissue integrity of major white matter (WM) tracts and performance on multiple cognitive tests. We used a discriminative event-based model to estimate the sequence of biomarker abnormality in MS progression in general, as well as specific models for worsening physical disability and cognitive impairment. RESULTS: We demonstrated that grey matter (GM) atrophy of the cerebellum, thalamus, and changes in corticospinal tracts are early events in MS pathology, whereas other WM tracts as well as the cognitive domains of working memory, attention, and executive function are consistently late events. The models for disability and cognition show early functional changes of the default-mode network and earlier changes in spinal cord volume compared to the general MS population. Overall, GM atrophy seems crucial due to its early involvement in the disease course, whereas WM tract integrity appears to be affected relatively late despite the early onset of WM lesions. CONCLUSION: Data-driven modelling revealed the relative occurrence of both imaging and non-imaging events as MS progresses, providing insights into disease propagation mechanisms, and allowing fine-grained staging of patients for monitoring purposes.

Details DOI

JBHI Journal 2019 Journal Article

Groupwise Multichannel Image Registration

  • Jean-Marie Guyader
  • Wyke Huizinga
  • Valerio Fortunati
  • Dirk H. J. Poot
  • Jifke F. Veenland
  • Margarethus M. Paulides
  • Wiro J. Niessen
  • Stefan Klein

Multichannel image registration is an important challenge in medical image analysis. Multichannel images result from modalities such as dual-energy CT or multispectral microscopy. Besides, multichannel feature images can be derived from acquired images, for instance, by applying multiscale feature banks to the original images to register. Multichannel registration techniques have been proposed, but most of them are applicable to only two multichannel images at a time. In the present study, we propose to formulate multichannel registration as a groupwise image registration problem. In this way, we derive a method that allows the registration of two or more multichannel images in a fully symmetric manner (i. e. , all images play the same role in the registration procedure), and therefore, has transitive consistency by definition. The method that we introduce is applicable to any number of multichannel images, any number of channels per image, and it allows to take into account correlation between any pair of images and not just corresponding channels. In addition, it is fully modular in terms of dissimilarity measure, transformation model, regularisation method, and optimisation strategy. For two multimodal datasets, we computed feature images from the initially acquired images, and applied the proposed registration technique to the newly created sets of multichannel images. MIND descriptors were used as feature images, and we chose total correlation as groupwise dissimilarity measure. Results show that groupwise multichannel image registration is a competitive alternative to the pairwise multichannel scheme, in terms of registration accuracy and insensitivity towards registration reference spaces.

Details DOI

YNICL Journal 2016 Journal Article

Structural and functional brain abnormalities place phenocopy frontotemporal dementia (FTD) in the FTD spectrum

  • Rebecca M.E. Steketee
  • Rozanna Meijboom
  • Esther E. Bron
  • Robert Jan Osse
  • Inge de Koning
  • Lize C. Jiskoot
  • Stefan Klein
  • Frank Jan de Jong

PURPOSE: 'Phenocopy' frontotemporal dementia (phFTD) patients may clinically mimic the behavioral variant of FTD (bvFTD), but do not show functional decline or abnormalities upon visual inspection of routine neuroimaging. We aimed to identify abnormalities in gray matter (GM) volume and perfusion in phFTD and to assess whether phFTD belongs to the FTD spectrum. We compared phFTD patients with both healthy controls and bvFTD patients. MATERIALS & METHODS: Seven phFTD and 11 bvFTD patients, and 20 age-matched controls underwent structural T1-weighted magnetic resonance imaging (MRI) and 3D pseudo-continuous arterial spin labeling (pCASL) at 3T. Normalized GM (nGM) volumes and perfusion, corrected for partial volume effects, were quantified regionally as well as in the entire supratentorial cortex, and compared between groups taking into account potential confounding effects of gender and scanner. RESULTS: PhFTD patients showed cortical atrophy, most prominently in the right temporal lobe. Apart from this regional atrophy, GM volume was generally not different from either controls or from bvFTD. BvFTD however showed extensive frontotemporal atrophy. Perfusion was increased in the left prefrontal cortex compared to bvFTD and to a lesser extent to controls. CONCLUSION: PhFTD and bvFTD show overlapping cortical structural abnormalities indicating a continuum of changes especially in the frontotemporal regions. Together with functional changes suggestive of a compensatory response to incipient pathology in the left prefrontal regions, these findings are the first to support a possible neuropathological etiology of phFTD and suggest that phFTD may be a neurodegenerative disease on the FTD spectrum.

Details DOI

JBHI Journal 2015 Journal Article

Feature Selection Based on the SVM Weight Vector for Classification of Dementia

  • Esther E. Bron
  • Marion Smits
  • Wiro J. Niessen
  • Stefan Klein

Computer-aided diagnosis of dementia using a support vector machine (SVM) can be improved with feature selection. The relevance of individual features can be quantified from the SVM weights as a significance map (p-map). Although these p-maps previously showed clusters of relevant voxels in dementia-related brain regions, they have not yet been used for feature selection. Therefore, we introduce two novel feature selection methods based on p-maps using a direct approach (filter) and an iterative approach (wrapper). To evaluate these p-map feature selection methods, we compared them with methods based on the SVM weight vector directly, t-statistics, and expert knowledge. We used MRI data from the Alzheimer's disease neuroimaging initiative classifying Alzheimer's disease (AD) patients, mild cognitive impairment (MCI) patients who converted to AD (MCIc), MCI patients who did not convert to AD (MCInc), and cognitively normal controls (CN). Features for each voxel were derived from gray matter morphometry. Feature selection based on the SVM weights gave better results than t-statistics and expert knowledge. The p-map methods performed slightly better than those using the weight vector. The wrapper method scored better than the filter method. Recursive feature elimination based on the p-map improved most for AD-CN: the area under the receiver-operating-characteristic curve (AUC) significantly increased from 90. 3% without feature selection to 92. 0% when selecting 1. 5%–3% of the features. This feature selection method also improved the other classifications: AD-MCI 0. 1% improvement in AUC (not significant), MCI-CN 0. 7%, and MCIc-MCInc 0. 1% (not significant). Although the performance improvement due to feature selection was limited, the methods based on the p-map generally had the best performance, and were therefore better in estimating the relevance of individual features.

Details DOI