Bram van Ginneken

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.

Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge

Prostate MRI image segmentation has been an area of intense research due to the increased use of MRI as a modality for the clinical workup of prostate cancer. Segmentation is useful for various tasks, e.g. to accurately localize prostate boundaries for radiotherapy or to initialize multi-modal registration algorithms. In the past, it has been difficult for research groups to evaluate prostate segmentation algorithms on multi-center, multi-vendor and multi-protocol data. Especially because we are dealing with MR images, image appearance, resolution and the presence of artifacts are affected by differences in scanners and/or protocols, which in turn can have a large influence on algorithm accuracy. The Prostate MR Image Segmentation (PROMISE12) challenge was setup to allow a fair and meaningful comparison of segmentation methods on the basis of performance and robustness. In this work we will discuss the initial results of the online PROMISE12 challenge, and the results obtained in the live challenge workshop hosted by the MICCAI2012 conference. In the challenge, 100 prostate MR cases from 4 different centers were included, with differences in scanner manufacturer, field strength and protocol. A total of 11 teams from academic research groups and industry participated. Algorithms showed a wide variety in methods and implementation, including active appearance models, atlas registration and level sets. Evaluation was performed using boundary and volume based metrics which were combined into a single score relating the metrics to human expert performance. The winners of the challenge where the algorithms by teams Imorphics and ScrAutoProstate, with scores of 85.72 and 84.29 overall. Both algorithms where significantly better than all other algorithms in the challenge (p<0.05) and had an efficient implementation with a run time of 8min and 3s per case respectively. Overall, active appearance model based approaches seemed to outperform other approaches like multi-atlas registration, both on accuracy and computation time. Although average algorithm performance was good to excellent and the Imorphics algorithm outperformed the second observer on average, we showed that algorithm combination might lead to further improvement, indicating that optimal performance for prostate segmentation is not yet obtained. All results are available online at http://promise12.grand-challenge.org/.

Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study

The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases.

Early Identification of Small Airways Disease on Lung Cancer Screening CT: Comparison of Current Air Trapping Measures

BackgroundLung cancer screening CT scans might provide valuable information about air trapping as an early indicator of smoking-related lung disease. We studied which of the currently suggested measures is most suitable for detecting functionally relevant air trapping on low-dose computed tomography (CT) in a population of subjects with early-stage disease.MethodsThis study was ethically approved and informed consent was obtained. Three quantitative CT air trapping measures were compared against a functional reference standard in 427 male lung cancer screening participants. This reference standard for air trapping was derived from the residual volume over total lung capacity ratio (RV/TLC) beyond the 95th percentile of predicted. The following CT air trapping measures were compared: expiratory to inspiratory relative volume change of voxels with attenuation values between −860 and −950 Hounsfield Units (RVC−860 to −950), expiratory to inspiratory ratio of mean lung density (E/I-ratioMLD) and percentage of voxels below −856xa0HU in expiration (EXP−856). Receiver operating characteristic (ROC) analysis was performed and area under the ROC curve compared.ResultsFunctionally relevant air trapping was present in 38 (8.9xa0%) participants. E/I-ratioMLD showed the largest area under the curve (0.85, 95xa0% CI 0.813–0.883), which was significantly larger than RVC−860 to −950 (0.703, 0.657–0.746; pxa0<xa00.001) and EXP−856 (0.798, 0.757–0.835; pxa0=xa00.002). At the optimum for sensitivity and specificity, E/I-ratioMLD yielded an accuracy of 81.5xa0%.ConclusionsThe expiratory to inspiratory ratio of mean lung density (E/I-ratioMLD) is most suitable for detecting air trapping on low-dose screening CT and performs significantly better than other suggested quantitative measures.

Fusion of local and global detection systems to detect tuberculosis in chest radiographs

Automatic detection of tuberculosis (TB) on chest radiographs is a difficult problem because of the diverse presentation of the disease. A combination of detection systems for abnormalities and normal anatomy is used to improve detection performance. A textural abnormality detection system operating at the pixel level is combined with a clavicle detection system to suppress false positive responses. The output of a shape abnormality detection system operating at the image level is combined in a next step to further improve performance by reducing false negatives. Strategies for combining systems based on serial and parallel configurations were evaluated using the minimum, maximum, product, and mean probability combination rules. The performance of TB detection increased, as measured using the area under the ROC curve, from 0.67 for the textural abnormality detection system alone to 0.86 when the three systems were combined. The best result was achieved using the sum and product rule in a parallel combination of outputs.

Coronary Artery Calcification Scoring in Low-Dose Ungated CT Screening for Lung Cancer: Interscan Agreement

OBJECTIVEnIn previous studies detection of coronary artery calcification (CAC) with low-dose ungated MDCT performed for lung cancer screening has been compared with detection with cardiac CT. We evaluated the interscan agreement of CAC scores from two consecutive low-dose ungated MDCT examinations.nnnSUBJECTS AND METHODSnThe subjects were 584 participants in the screening segment of a lung cancer screening trial who underwent two low-dose ungated MDCT examinations within 4 months (mean, 3.1 +/- 0.6 months) of a baseline CT examination. Agatston score, volume score, and calcium mass score were measured by two observers. Interscan agreement of stratification of participants into four Agatston score risk categories (0, 1-100, 101-400, > 400) was assessed with kappa values. Interscan variability and 95% repeatability limits were calculated for all three calcium measures and compared by repeated measures analysis of variance.nnnRESULTSnAn Agatston score > 0 was detected in 443 baseline CT examinations (75.8%). Interscan agreement of the four risk categories was good (kappa = 0.67). The Agatston scores were in the same risk category in both examinations in 440 cases (75.3%); 578 participants (99.0%) had scores differing a maximum of one category. Furthermore, mean interscan variability ranged from 61% for calcium volume score to 71% for Agatston score (p < 0.01). A limitation of this study was that no comparison of CAC scores between low-dose ungated CT and the reference standard ECG-gated CT was performed.nnnCONCLUSIONnCardiovascular disease risk stratification with low-dose ungated MDCT is feasible and has good interscan agreement of stratification of participants into Agatston score risk categories. High mean interscan variability precludes the use of this technique for monitoring CAC scores for individual patients.

Toward automatic regional analysis of pulmonary function using inspiration and expiration thoracic CT

PURPOSEnTo analyze pulmonary function using a fully automatic technique which processes pairs of thoracic CT scans acquired at breath-hold inspiration and expiration, respectively. The following research objectives are identified to: (a) describe and systematically analyze the processing pipeline and its results; (b) verify that the quantitative, regional ventilation measurements acquired through CT are meaningful for pulmonary function analysis; (c) identify the most effective of the calculated measurements in predicting pulmonary function; and (d) demonstrate the potential of the system to deliver clinically important information not available through conventional spirometry.nnnMETHODSnA pipeline of automatic segmentation and registration techniques is presented and demonstrated on a database of 216 subjects well distributed over the various stages of COPD (chronic obstructive pulmonary disorder). Lungs, fissures, airways, lobes, and vessels are automatically segmented in both scans and the expiration scan is registered with the inspiration scan using a fully automatic nonrigid registration algorithm. Segmentations and registrations are examined and scored by expert observers to analyze the accuracy of the automatic methods. Quantitative measures representing ventilation are computed at every image voxel and analyzed to provide information about pulmonary function, both globally and on a regional basis. These CT derived measurements are correlated with results from spirometry tests and used as features in a kNN classifier to assign COPD global initiative for obstructive lung disease (GOLD) stage.nnnRESULTSnThe steps of anatomical segmentation (of lungs, lobes, and vessels) and registration in the workflow were shown to perform very well on an individual basis. All CT-derived measures were found to have good correlation with spirometry results, with several having correlation coefficients, r, in the range of 0.85-0.90. The best performing kNN classifier succeeded in classifying 67% of subjects into the correct COPD GOLD stage, with a further 29% assigned to a class neighboring the correct one.nnnCONCLUSIONSnPulmonary function information can be obtained from thoracic CT scans using the automatic pipeline described in this work. This preliminary demonstration of the system already highlights a number of points of clinical importance such as the fact that an inspiration scan alone is not optimal for predicting pulmonary function. It also permits measurement of ventilation on a per lobe basis which reveals, for example, that the condition of the lower lobes contributes most to the pulmonary function of the subject. It is expected that this type of regional analysis will be instrumental in advancing the understanding of multiple pulmonary diseases in the future.

Clavicle segmentation in chest radiographs

Automated delineation of anatomical structures in chest radiographs is difficult due to superimposition of multiple structures. In this work an automated technique to segment the clavicles in posterior-anterior chest radiographs is presented in which three methods are combined. Pixel classification is applied in two stages and separately for the interior, the border and the head of the clavicle. This is used as input for active shape model segmentation. Finally dynamic programming is employed with an optimized cost function that combines appearance information of the interior of the clavicle, the border, the head and shape information derived from the active shape model. The method is compared with a number of previously described methods and with independent human observers on a large database. This database contains both normal and abnormal images and will be made publicly available. The mean contour distance of the proposed method on 249 test images is 1.1±1.6mm and the intersection over union is 0.86±0.10.

Computer-aided detection of ground glass nodules in thoracic CT images using shape, intensity and context features

Ground glass nodules (GGNs) occur less frequent in computed tomography (CT) scans than solid nodules but have a much higher chance of being malignant. Accurate detection of these nodules is therefore highly important. A complete system for computer-aided detection of GGNs is presented consisting of initial segmentation steps, candidate detection, feature extraction and a two-stage classification process. A rich set of intensity, shape and context features is constructed to describe the appearance of GGN candidates. We apply a two-stage classification approach using a linear discriminant classifier and a GentleBoost classifier to efficiently classify candidate regions. The system is trained and independently tested on 140 scans that contained one or more GGNs from around 10,000 scans obtained in a lung cancer screening trial. The system shows a high sensitivity of 73% at only one false positive per scan.

Low-dose CT measurements of airway dimensions and emphysema associated with airflow limitation in heavy smokers: a cross sectional study

BackgroundIncreased airway wall thickness (AWT) and parenchymal lung destruction bothcontribute to airflow limitation. Advances in computed tomography (CT)post-processing imaging allow to quantify these features. The aim of thisDutch population study is to assess the relationships between AWT, lungfunction, emphysema and respiratory symptoms.MethodsAWT and emphysema were assessed by low-dose CT in 500 male heavy smokers,randomly selected from a lung cancer screening population. AWT was measuredin each lung lobe in cross-sectionally reformatted images with an automatedimaging program at locations with an internal diameter of 3.5u2009mm, andvalidated in smaller cohorts of patients. The 15th percentilemethod (Perc15) was used to assess the severity of emphysema. Informationabout respiratory symptoms and smoking behavior was collected byquestionnaires and lung function by spirometry.ResultsMedian AWT in airways with an internal diameter of 3.5u2009mm(AWT3.5) was 0.57 (0.44 - 0.74) mm. Median AWT in subjectswithout symptoms was 0.52 (0.41-0.66) and in those with dyspnea and/orwheezing 0.65 (0.52-0.81) mm (p<0.001). In the multivariate analysisonly AWT3.5 and emphysema independently explained 31.1%and9.5%of the variance in FEV1%predicted, respectively,after adjustment for smoking behavior.ConclusionsPost processing standardization of airway wall measurements provides areliable and useful method to assess airway wall thickness. Increased airwaywall thickness contributes more to airflow limitation than emphysema in asmoking male population even after adjustment for smoking behavior.