Koen L. Vincken

Muliscale Vessel Enhancement Filtering

The multiscale second order local structure of an image (Hessian) is examined with the purpose of developing a vessel enhancement filter. A vesselness measure is obtained on the basis of all eigenvalues of the Hessian. This measure is tested on two dimensional DSA and three dimensional aortoiliac and cerebral MRA data. Its clinical utility is shown by the simultaneous noise and background suppression and vessel enhancement in maximum intensity projections and volumetric displays.

Probabilistic segmentation of white matter lesions in MR imaging.

A new method has been developed for fully automated segmentation of white matter lesions (WMLs) in cranial MR imaging. The algorithm uses information from T1-weighted (T1-w), inversion recovery (IR), proton density-weighted (PD), T2-weighted (T2-w) and fluid attenuation inversion recovery (FLAIR) scans. It is based on the K-Nearest Neighbor (KNN) classification technique that builds a feature space from voxel intensities and spatial information. The technique generates images representing the probability per voxel being part of a WML. By application of thresholds on these probability maps, binary segmentations can be obtained. ROC curves show that the segmentations achieve both high sensitivity and specificity. A similarity index (SI), overlap fraction (OF) and extra fraction (EF) are calculated for additional quantitative analysis of the result. The SI is also used for determination of the optimal probability threshold for generation of the binary segmentation. Using probabilistic equivalents of the SI, OF and EF, the probability maps can be evaluated directly, providing a powerful tool for comparison of different classification results. This method for automated WML segmentation reaches an accuracy that is comparable to methods for multiple sclerosis (MS) lesion segmentation and is suitable for detection of WMLs in large and longitudinal population studies.

Probabilistic segmentation of brain tissue in MR imaging.

A new method has been developed for probabilistic segmentation of five different types of brain structures: white matter, gray matter, cerebro-spinal fluid without ventricles, ventricles and white matter lesion in cranial MR imaging. The algorithm is based on information from T1-weighted (T1-w), inversion recovery (IR), proton density-weighted (PD), T2-weighted (T2-w) and fluid attenuation inversion recovery (FLAIR) scans. It uses the K-Nearest Neighbor classification technique that builds a feature space from spatial information and voxel intensities. The technique generates for each tissue type an image representing the probability per voxel being part of it. By application of thresholds on these probability maps, binary segmentations can be obtained. A similarity index (SI) and a probabilistic SI (PSI) were calculated for quantitative evaluation of the results. The influence of each image type on the performance was investigated by alternately leaving out one of the five scan types. This procedure showed that the incorporation of the T1-w, PD or T2-w did not significantly improve the segmentation results. Further investigation indicated that the combination of IR and FLAIR was optimal for segmentation of the five brain tissue types. Evaluation with respect to the gold standard showed that the SI-values for all tissues exceeded 0.8 and all PSI-values exceeded 0.7, implying an excellent agreement.

Cognitive impairment in tuberous sclerosis complex is a multifactorial condition

Objective: In patients with tuberous sclerosis complex (TSC), associations between tuber number, infantile spasms, and cognitive impairment have been proposed. We hypothesized that the tuber/brain proportion (TBP), the proportion of the total brain volume occupied by tubers, would be a better determinant of seizures and cognitive function than the number of tubers. We investigated tuber load, seizures, and cognitive function and their relationships. Methods: Tuber number and TBP were characterized on three-dimensional fluid-attenuated inversion recovery MRI with an automated tuber segmentation program. Seizure histories and EEG recordings were obtained. Intelligence equivalents were determined and an individual cognition index (a marker of cognition that incorporated multiple cognitive domains) was calculated. Results: In our sample of 61 patients with TSC, TBP was inversely related to the age at seizure onset and to the intelligence equivalent and tended to be inversely related to the cognition index. Further, a younger age at seizure onset or a history of infantile spasms was related to lower intelligence and lower cognition index. In a multivariable analysis, only age at seizure onset and cognition index were related. Conclusions: Our systematic analysis confirms proposed relationships between tuber load, epilepsy and cognitive function in tuberous sclerosis complex (TSC), but also indicates that tuber/brain proportion is a better predictor of cognitive function than tuber number and that age at seizure onset is the only independent determinant of cognitive function. Seizure control should be the principal neurointervention in patients with TSC.

Probabilistic multiscale image segmentation

A method is presented to segment multidimensional images using a multiscale (hyperstack) approach with probabilistic linking. A hyperstack is a voxel-based multiscale data structure whose levels are constructed by convolving the original image with a Gaussian kernel of increasing width. Between voxels at adjacent scale levels, child-parent linkages are established according to a model-directed linkage scheme. In the resulting tree-like data structure, roots are formed to indicate the most plausible locations in scale space where segments in the original image are represented by a single voxel. The final segmentation is obtained by tracing back the linkages for all roots. The present paper deals with probabilistic (or multiparent) linking. The multiparent linkage structure is translated into a list of probabilities that are indicative of which voxels are partial volume voxels and to which extent. Probability maps are generated to visualize the progress of weak linkages in scale space when going from fine to coarser scale. It is demonstrated that probabilistic linking gives a significantly improved segmentation as compared with conventional (single-parent) linking.

Automatic segmentation of different-sized white matter lesions by voxel probability estimation.

A new method for fully automated segmentation of white matter lesions (WMLs) on cranial MR imaging is presented. The algorithm uses five types of regular MRI-scans. It is based on a K-Nearest Neighbor (KNN) classification technique, which builds a feature space from voxel intensity features and spatial information. The technique generates images representing the probability per voxel being part of a WML. By application of thresholds on these probability maps binary segmentations can be produced. ROC-curves show that the segmentations achieve a high sensitivity and specificity. Three similarity measures, the similarity index (SI), the overlap fraction (OF) and the extra fraction (EF), are calculated for evaluation of the results and determination of the optimal threshold on the probability map. Investigation of the relation between the total lesion volume and the similarity measures shows that the method performs well for lesions larger than 2 cc. The maximum SI per patient is correlated to the total WML volume. No significant relation between the lesion volume and the optimal threshold has been observed. The probabilistic equivalents of the SI, OF en EF (PSI, POF and PEF) allow direct evaluation of the probability maps, which provides a strong tool for comparison of different classification results. A significant correlation between the lesion volume and the PSI and the PEF has been noticed. This method for automated WML segmentation is applicable to lesions of different sizes and shapes, and reaches an accuracy that is comparable to existing methods for multiple sclerosis lesion segmentation. Furthermore, it is suitable for detection of WMLs in large and longitudinal population studies.

Diabetes Increases Atrophy and Vascular Lesions on Brain MRI in Patients With Symptomatic Arterial Disease

Background and Purpose— Diabetes type 2 (DM2) is associated with accelerated cognitive decline and structural brain abnormalities. Macrovascular disease has been described as a determinant for brain MRI changes in DM2, but little is known about the involvement of other DM2-related factors. Methods— Brain MRI was performed in 1043 participants (151 DM2) with symptomatic arterial disease. Brain volumes were obtained through automated segmentation. Results— Patients with arterial disease and DM2 had more global and subcortical brain atrophy (−1.20% brain/intracranial volume [95%CI −1.58 to −0.82], P<0.0005 and 0.20% ventricular/intracranial volume [0.05 to 0.34], P<0.01), larger WMH volumes (0.22 logtransformed volume [0.07 to 0.38], P<0.005), and more lacunar infarcts (OR 1.75 [1.13 to 2.69], P<0.01) than identical patients without DM2. In patients with DM2, high glucose levels (B−0.12% per mmol/L [−0.23 to −0.01], P<0.05) and diabetes duration (B−0.05% per year [−0.10 to −0.001], P<0.05) were associated with global brain atrophy. Conclusion— In patients with symptomatic arterial disease, DM2 has an added detrimental effect on the brain. In patients with DM2, hyperglycemia and diabetes duration contribute to brain atrophy.

MRBrainS challenge: online evaluation framework for brain image segmentation in 3T MRI scans

Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi)automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65–80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand.

Multiscale Segmentation of Three-Dimensional MR Brain Images

Segmentation of MR brain images using intensity values is severely limited owing to field inhomogeneities, susceptibility artifacts and partial volume effects. Edge based segmentation methods suffer from spurious edges and gaps in boundaries. A multiscale method to MRI brain segmentation is presented which uses both edge and intensity information. First a multiscale representation of an image is created, which can be made edge dependent to favor intra-tissue diffusion over inter-tissue diffusion. Subsequently a multiscale linking model (the hyperstack) is used to group voxels into a number of objects based on intensity. It is shown that both an improvement in accuracy and a reduction in image post-processing can be achieved if edge dependent diffusion is used instead of linear diffusion. The combination of edge dependent diffusion and intensity based linking facilitates segmentation of grey matter, white matter and cerebrospinal fluid with minimal user interaction. To segment the total brain (white matter plus grey matter) morphological operations are applied to remove small bridges between the brain and cranium. If the total brain is segmented, grey matter, white matter and cerebrospinal fluid can be segmented by joining a small number of segments. Using a supervised segmentation technique and MRI simulations of a brain phantom for validation it is shown that the errors are in the order of or smaller than reported in literature.

Brain volumes and cerebrovascular lesions on MRI in patients with atherosclerotic disease. The SMART-MR study

OBJECTIVE To estimate brain volumes, white matter lesion (WML) volume and asymptomatic infarcts on MRI in a large cohort of patients with atherosclerotic disease. METHODS Within the SMART-MR (Second Manifestations of ARTerial disease-Magnetic Resonance) study, a prospective cohort study on determinants and course of brain changes on MRI, cross-sectional analyses were performed in 1044 patients (mean age 58+/-10 years, 80% male) with coronary artery disease, cerebrovascular disease, peripheral arterial disease, or abdominal aortic aneurysm. Brain segmentation was used to quantify volumes of cortical gray matter, white matter, sulcal and ventricular cerebrospinal fluid, and WML. All volumes were expressed relative to intracranial volume. Brain infarcts were rated visually and distinctions were made between cortical infarcts, large subcortical infarcts, lacunar infarcts, and infarcts in the cerebellum and brainstem. RESULTS With older age a nonlinear (quadratic) decrease in total brain volume was observed and a nonlinear increase in ventricular volume and WML. Cortical gray matter volume showed a linear decrease with age and was stronger in men than in women. WML volumes also increased more strongly in men than in women, while ventricular volume decrease showed no sex difference. Silent brain infarcts were present in 14% of men and women, and increased to 24% of subjects aged 65 years or older. CONCLUSION In a population with atherosclerotic diseases, decrease in brain volumes with increasing age is comparable with findings from the general population. However, vascular pathology on MRI, as indicated by white matter lesions and silent brain infarcts may be more common.