Marleen de Bruijne

Quantitative Analysis of Pulmonary Emphysema Using Local Binary Patterns

We aim at improving quantitative measures of emphysema in computed tomography (CT) images of the lungs. Current standard measures, such as the relative area of emphysema (RA), rely on a single intensity threshold on individual pixels, thus ignoring any interrelations between pixels. Texture analysis allows for a much richer representation that also takes the local structure around pixels into account. This paper presents a texture classification-based system for emphysema quantification in CT images. Measures of emphysema severity are obtained by fusing pixel posterior probabilities output by a classifier. Local binary patterns (LBP) are used as texture features, and joint LBP and intensity histograms are used for characterizing regions of interest (ROIs). Classification is then performed using a k nearest neighbor classifier with a histogram dissimilarity measure as distance. A 95.2% classification accuracy was achieved on a set of 168 manually annotated ROIs, comprising the three classes: normal tissue, centrilobular emphysema, and paraseptal emphysema. The measured emphysema severity was in good agreement with a pulmonary function test (PFT) achieving correlation coefficients of up to |r| = 0.79 in 39 subjects. The results were compared to RA and to a Gaussian filter bank, and the texture-based measures correlated significantly better with PFT than did RA.

A Genome-Wide Association Study Identifies Five Loci Influencing Facial Morphology in Europeans

Inter-individual variation in facial shape is one of the most noticeable phenotypes in humans, and it is clearly under genetic regulation; however, almost nothing is known about the genetic basis of normal human facial morphology. We therefore conducted a genome-wide association study for facial shape phenotypes in multiple discovery and replication cohorts, considering almost ten thousand individuals of European descent from several countries. Phenotyping of facial shape features was based on landmark data obtained from three-dimensional head magnetic resonance images (MRIs) and two-dimensional portrait images. We identified five independent genetic loci associated with different facial phenotypes, suggesting the involvement of five candidate genes—PRDM16, PAX3, TP63, C5orf50, and COL17A1—in the determination of the human face. Three of them have been implicated previously in vertebrate craniofacial development and disease, and the remaining two genes potentially represent novel players in the molecular networks governing facial development. Our finding at PAX3 influencing the position of the nasion replicates a recent GWAS of facial features. In addition to the reported GWA findings, we established links between common DNA variants previously associated with NSCL/P at 2p21, 8q24, 13q31, and 17q22 and normal facial-shape variations based on a candidate gene approach. Overall our study implies that DNA variants in genes essential for craniofacial development contribute with relatively small effect size to the spectrum of normal variation in human facial morphology. This observation has important consequences for future studies aiming to identify more genes involved in the human facial morphology, as well as for potential applications of DNA prediction of facial shape such as in future forensic applications.

Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images

Active Shape Models (ASM) have proven to be an effective approach for image segmentation. In some applications, however, the linear model of gray level appearance around a contour that is used in ASM is not sufficient for accurate boundary localization. Furthermore, the statistical shape model may be too restricted if the training set is limited. This paper describes modifications to both the shape and the appearance model of the original ASM formulation. Shape model flexibility is increased, for tubular objects, by modeling the axis deformation independent of the cross-sectional deformation, and by adding supplementary cylindrical deformation modes. Furthermore, a novel appearance modeling scheme that effectively deals with a highly varying background is developed. In contrast with the conventional ASM approach, the new appearance model is trained on both boundary and non-boundary points, and the probability that a given point belongs to the boundary is estimated non-parametrically. The methods are evaluated on the complex task of segmenting thrombus in abdominal aortic aneurysms (AAA). Shape approximation errors were successfully reduced using the two shape model extensions. Segmentation using the new appearance model significantly outperformed the original ASM scheme; average volume errors are 5.1% and 45% respectively.

Extraction of Airways From CT (EXACT'09)

This paper describes a framework for establishing a reference airway tree segmentation, which was used to quantitatively evaluate fifteen different airway tree extraction algorithms in a standardized manner. Because of the sheer difficulty involved in manually constructing a complete reference standard from scratch, we propose to construct the reference using results from all algorithms that are to be evaluated. We start by subdividing each segmented airway tree into its individual branch segments. Each branch segment is then visually scored by trained observers to determine whether or not it is a correctly segmented part of the airway tree. Finally, the reference airway trees are constructed by taking the union of all correctly extracted branch segments. Fifteen airway tree extraction algorithms from different research groups are evaluated on a diverse set of twenty chest computed tomography (CT) scans of subjects ranging from healthy volunteers to patients with severe pathologies, scanned at different sites, with different CT scanner brands, models, and scanning protocols. Three performance measures covering different aspects of segmentation quality were computed for all participating algorithms. Results from the evaluation showed that no single algorithm could extract more than an average of 74% of the total length of all branches in the reference standard, indicating substantial differences between the algorithms. A fusion scheme that obtained superior results is presented, demonstrating that there is complementary information provided by the different algorithms and there is still room for further improvements in airway segmentation algorithms.

Interactive segmentation of abdominal aortic aneurysms in CTA images

A model-based approach to interactive segmentation of abdominal aortic aneurysms from CTA data is presented. After manual delineation of the aneurysm sac in the first slice, the method automatically detects the contour in subsequent slices, using the result from the previous slice as a reference. If an obtained contour is not sufficiently accurate, the user can intervene and provide an additional manual reference contour. The method is inspired by the active shape model (ASM) segmentation scheme (), in which a statistical shape model, derived from corresponding landmark points in manually labeled training images, is fitted to the image in an iterative manner. In our method, a shape model of the contours in two adjacent image slices is progressively fitted to the entire volume. The contour obtained in one slice thus constrains the possible shapes in the next slice. The optimal fit is determined on the basis of multi-resolution gray level models constructed from gray value patches sampled around each landmark. We propose to use the similarity of adjacent image slices for this gray level model, and compare these to single-slice features that are more generally used with ASM. The performance of various image features is evaluated in leave-one-out experiments on 23 data sets. Features that use the similarity of adjacent image slices outperform measures based on single-slice features in all cases. The average number of slices in our datasets is 51, while on average eight manual initializations are required, which decreases operator segmentation time by a factor of 6.

Vessel-guided airway tree segmentation: A voxel classification approach

This paper presents a method for airway tree segmentation that uses a combination of a trained airway appearance model, vessel and airway orientation information, and region growing. We propose a voxel classification approach for the appearance model, which uses a classifier that is trained to differentiate between airway and non-airway voxels. This is in contrast to previous works that use either intensity alone or hand crafted models of airway appearance. We show that the appearance model can be trained with a set of easily acquired, incomplete, airway tree segmentations. A vessel orientation similarity measure is introduced, which indicates how similar the orientation of an airway candidate is to the orientation of the neighboring vessel. We use this vessel orientation similarity measure to overcome regions in the airway tree that have a low response from the appearance model. The proposed method is evaluated on 250 low dose computed tomography images from a lung cancer screening trial. Our experiments showed that applying the region growing algorithm on the airway appearance model produces more complete airway segmentations, leading to on average 20% longer trees, and 50% less leakage. When combining the airway appearance model with vessel orientation similarity, the improvement is even more significant (p<0.01) than only using the airway appearance model, with on average 7% increase in the total length of branches extracted correctly.

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.

Quantitative vertebral morphometry using neighbor-conditional shape models

A novel method for vertebral fracture quantification from X-ray images is presented. Using pairwise conditional shape models trained on a set of healthy spines, the most likely normal vertebra shapes are estimated conditional on all other vertebrae in the image. The differences between the true shape and the reconstructed normal shape is subsequently used as a measure of abnormality. In contrast with the current (semi-)quantitative grading strategies this method takes the full shape into account, it uses a patient-specific reference by combining population-based information on biological variation in vertebra shape and vertebra interrelations, and it provides a continuous measure of deformity. The method is demonstrated on 212 lateral spine radiographs with in total 78 fractures. The distance between prediction and true shape is 1.0 mm for unfractured vertebrae and 3.7 mm for fractures, which makes it possible to diagnose and assess the severity of a fracture.

PRAGMA-CF. A Quantitative Structural Lung Disease Computed Tomography Outcome in Young Children with Cystic Fibrosis

RATIONALE Chest computed tomography (CT) is the gold standard for demonstrating cystic fibrosis (CF) airway disease. However, there are no standardized outcome measures appropriate for children younger than 6 years. OBJECTIVES We developed the Perth-Rotterdam Annotated Grid Morphometric Analysis for CF (PRAGMA-CF), a quantitative measure of airway disease, and compared it with the commonly used CF-CT scoring method. METHODS CT scans from the Australian Respiratory Early Surveillance Team for CF (AREST CF) cohort in Western Australia were included. PRAGMA-CF was performed by annotating a grid overlaid on 10 axial slices for the presence of bronchiectasis, mucous plugging, or other airway abnormalities (inspiratory scans) and trapped air (expiratory scans). The separate proportions of total disease (%Dis), bronchiectasis (%Bx), and trapped air (%TA) were determined. Thirty scans were used for observer reliability, and 30 paired scans obtained at 1 and 3 years old were used for comparison with a validated standard and biologic plausibility. MEASUREMENTS AND MAIN RESULTS Intraobserver, intraclass correlation coefficients (95% confidence interval) for %Dis, %Bx, and %TA were 0.93 (0.86-0.97), 0.93 (0.85-0.96), and 0.96 (0.91-0.98), respectively. The change in %Dis (P = 0.004) and %Bx (P = 0.001) with PRAGMA-CF was related to neutrophil elastase presence at age 3, whereas only the change in bronchiectasis score was related to neutrophil elastase (P < 0.001) with CF-CT. Sample-size calculations for various effect sizes are presented. CONCLUSIONS PRAGMA-CF is a sensitive and reproducible outcome measure for assessing the extent of lung disease in very young children with CF.

Cystic fibrosis: are volumetric ultra-low-dose expiratory CT scans sufficient for monitoring related lung disease?

PURPOSE To assess whether chest computed tomography (CT) scores from ultra-low-dose end-expiratory scans alone could suffice for assessment of all cystic fibrosis (CF)-related structural lung abnormalities. MATERIALS AND METHODS In this institutional review board-approved study, 20 patients with CF aged 6-20 years (eight males, 12 females) underwent low-dose end-inspiratory CT and ultra-low-dose end-expiratory CT. Informed consent was obtained. Scans were randomized and scored by using the Brody-II CT scoring system to assess bronchiectasis, airway wall thickening, mucus plugging, and opacities. Scoring was performed by two observers who were blinded to patient identity and clinical information. Mean scores were used for all analyses. Statistical analysis included assessment of intra- and interobserver variability, calculation of intraclass correlation coefficients (ICCs), and Bland-Altman plots. RESULTS Median age was 12.6 years (range, 6.3-20.3 years), median forced expiratory volume in 1 second was 100% (range, 46%-127%) of the predicted value, and median forced vital capacity was 99% (range, 61%-123%) of the predicted value. Very good agreement was observed between end-inspiratory and end-expiratory CT scores for Brody-II total score (ICC = 0.96), bronchiectasis (ICC = 0.98), airway wall thickening (ICC = 0.94), mucus plugging (ICC = 0.96), and opacities (ICC = 0.90). Intra- and interobserver agreement were good to very good (ICC range, 0.70-0.98). Bland-Altman plots showed that differences in scores were independent of score magnitude. CONCLUSION In this pilot study, CT scores from end-expiratory and end-inspiratory CT match closely, suggesting that ultra-low-dose end-expiratory CT alone may be sufficient for monitoring CF-related lung disease. This would help reduce radiation dose for a single investigation by up to 75%.