Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 2004
An automated method for coronary calcification detection is presented. First the heart region is ... more An automated method for coronary calcification detection is presented. First the heart region is extracted, in which objects potentially representing calcifications are obtained by thresholding. Besides coronary calcifications, the set of objects includes other heart calcifications, bony structures and noise. For each object, features describing its size, shape, position and appearance are computed. Several classifiers and classification strategies are evaluated. Best results are obtained with a specifically designed sequence of kNN classifiers that employ sequential forward feature selection. First obvious non-calcifications are removed, then calcifications are distinguished from non-calcifications and a final classifier discerns coronary calcifications from other cardiac calcifications. In 14 CT scans containing 61 coronary calcifications, 46 (75%) are detected at the expense of on average 0.9 false positive objects per scan.
ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005., 2005
An automated method for coronary calcification detection from ECG-triggered multi-slice CT data i... more An automated method for coronary calcification detection from ECG-triggered multi-slice CT data is presented. The method first segments the heart region. In the obtained volume candidate objects are extracted by thresholding. They include coronary calcification, calcium located elsewhere in the heart, for example, in the valves or the myocardium, and other high density structures mostly representing noise and bone. A set of 57 features is calculated for each candidate object. In the feature space objects are classified with a k-NN classifier and feature selection in three consecutive stages. The method is tested on 51 scans of the heart. They contain 320 calcification in the coronary arteries, 291 in the aorta and 62 calcifications in the heart. The system correctly detected 177 calcifications in the coronaries at the expense of 56 false positive objects. On average the method makes 3.8 errors per scan.
Atlas-based segmentation is a popular generic technique for automated delineation of structures i... more Atlas-based segmentation is a popular generic technique for automated delineation of structures in volumetric data sets. Several studies have shown that multi-atlas based segmentation methods outperform schemes that use only a single atlas, but running multiple registrations on large volumetric data is too time-consuming for routine clinical use. We propose a generally applicable adaptive local multi-atlas segmentation method (ALMAS) that
Preterm birth is often associated with impaired brain development. The state and expected progres... more Preterm birth is often associated with impaired brain development. The state and expected progression of preterm brain development can be evaluated using quantitative assessment of MR images. Such measurements require accurate segmentation of different tissue types in those images. This paper presents an algorithm for the automatic segmentation of unmyelinated white matter (WM), cortical grey matter (GM), and cerebrospinal fluid in the extracerebral space (CSF). The algorithm uses supervised voxel classification in three subsequent stages. In the first stage, voxels that can easily be assigned to one of the three tissue types are labelled. In the second stage, dedicated analysis of the remaining voxels is performed. The first and the second stage both use two-class classification for each tissue type separately. Possible inconsistencies that could result from these tissue-specific segmentation stages are resolved in the third stage, which performs multi-class classification. A set of T1- and T2-weighted images was analysed, but the optimised system performs automatic segmentation using a T2-weighted image only. We have investigated the performance of the algorithm when using training data randomly selected from completely annotated images as well as when using training data from only partially annotated images. The method was evaluated on images of preterm infants acquired at 30 and 40 weeks postmenstrual age (PMA). When the method was trained using random selection from the completely annotated images, the average Dice coefficients were 0.95 for WM, 0.81 for GM, and 0.89 for CSF on an independent set of images acquired at 30 weeks PMA. When the method was trained using only the partially annotated images, the average Dice coefficients were 0.95 for WM, 0.78 for GM and 0.87 for CSF for the images acquired at 30 weeks PMA, and 0.92 for WM, 0.80 for GM and 0.85 for CSF for the images acquired at 40 weeks PMA. Even though the segmentations obtained using training data from the partially annotated images resulted in slightly lower Dice coefficients, the performance in all experiments was close to that of a second human expert (0.93 for WM, 0.79 for GM and 0.86 for CSF for the images acquired at 30 weeks, and 0.94 for WM, 0.76 for GM and 0.87 for CSF for the images acquired at 40 weeks). These results show that the presented method is robust to age and acquisition protocol and that it performs accurate segmentation of WM, GM, and CSF when the training data is extracted from complete annotations as well as when the training data is extracted from partial annotations only. This extends the applicability of the method by reducing the time and effort necessary to create training data in a population with different characteristics.
IEEE transactions on medical imaging, Jan 16, 2015
The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardio... more The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. We present a system that automatically quantifies total patient and per coronary artery CAC in non-contrast-enhanced, ECGtriggered cardiac CT. The system identifies candidate calcifications that cannot be automatically labeled with high certainty and optionally presents these to an expert for review. Candidates were extracted by intensity-based thresholding and described by location features derived from estimated coronary artery positions, as well as size, shape and intensity features. Next, a two-class classifier distinguished between coronary calcifications and negatives or a multiclass classifier labeled CAC per coronary artery. Candidates that could not be labeled with high certainty were identified by entropy-based ambiguity detection and presented to an expert for review and possible relabeling. The system was evaluated with 530 test images. Using the two-class cl...
Certain pulmonary diseases are associated with cardiovascular disease (CVD). Therefore we investi... more Certain pulmonary diseases are associated with cardiovascular disease (CVD). Therefore we investigated the incremental predictive value of pulmonary, mediastinal and pleural features over cardiovascular imaging findings. A total of 10,410 patients underwent diagnostic chest CT for non-cardiovascular indications. Using a case-cohort approach, we visually graded CTs from the cases and from an approximately 10 % random sample of the baseline cohort (n = 1,203) for cardiovascular, pulmonary, mediastinal and pleural findings. The incremental value of pulmonary disease-related CT findings above cardiovascular imaging findings in cardiovascular event risk prediction was quantified by comparing discrimination and reclassification. During a mean follow-up of 3.7 years (max. 7.0 years), 1,148 CVD events (cases) were identified. Addition of pulmonary, mediastinal and pleural features to a cardiovascular imaging findings-based prediction model led to marginal improvement of discrimination (incr...
Atlas-based segmentation is a powerful generic technique for automatic delineation of structures ... more Atlas-based segmentation is a powerful generic technique for automatic delineation of structures in volumetric images. Several studies have shown that multi-atlas segmentation methods outperform schemes that use only a single atlas, but running multiple registrations on volumetric data is time-consuming. Moreover, for many scans or regions within scans, a large number of atlases may not be required to achieve good segmentation performance and may even deteriorate the results. It would therefore be worthwhile to include the decision which and how many atlases to use for a particular target scan in the segmentation process. To this end, we propose two generally applicable multi-atlas segmentation methods, adaptive multi-atlas segmentation (AMAS) and adaptive local multi-atlas segmentation (ALMAS). AMAS automatically selects the most appropriate atlases for a target image and automatically stops registering atlases when no further improvement is expected. ALMAS takes this concept one step further by locally deciding how many and which atlases are needed to segment a target image. The methods employ a computationally cheap atlas selection strategy, an automatic stopping criterion, and a technique to locally inspect registration results and determine how much improvement can be expected from further registrations.
This work presents a system for automatic coronary calcium scoring and cardiovascular risk strati... more This work presents a system for automatic coronary calcium scoring and cardiovascular risk stratification in thoracic CT scans. Data was collected from a Dutch-Belgian lung cancer screening trial. In 121 low-dose, non-ECG synchronized, non-contrast enhanced thoracic CT scans an expert scored coronary calcifications manually. A key element of the proposed algorithm is that the approximate position of the coronary arteries
Purpose: Volumetric measurements of neonatal brain tissues may be used as a biomarker for later n... more Purpose: Volumetric measurements of neonatal brain tissues may be used as a biomarker for later neurodevelopmental outcome. We propose an automatic method for probabilistic brain segmentation in neonatal MRIs.
To investigate the frequency of aortic calcifications at the outer edge of the false lumen and th... more To investigate the frequency of aortic calcifications at the outer edge of the false lumen and the frequency of fully circular aortic calcifications in a consecutive series of patients with aortic dissection who underwent contrast-enhanced CT. The study population compromised of 69 consecutive subjects aged 60 years and older with a contrast-enhanced CT scan demonstrating an aortic dissection. All CT scans were evaluated for the frequency of aortic calcifications at the outer edge of the false lumen and the frequency of fully circular aortic calcifications by two experienced observers. Between observer reliability was evaluated by using Cohen's Kappa. Differences between groups were tested using unpaired T test and Chi-square test. Presumed media calcifications were observed in 22 (32%) patients of 60 years and older and were found more frequently in chronic aortic dissection (N = 12/23, 52%) than in acute aortic dissection (N = 10/46, 22%). As the intima has been torn away by the aortic dissection it is highly likely that CT scans can visualize the calcifications in the tunica media of the aorta.
Objective: To determine the agreement and reliability of fully automated coronary artery calcium ... more Objective: To determine the agreement and reliability of fully automated coronary artery calcium (CAC) scoring in a lung cancer screening population.
Journal of cardiovascular computed tomography, Jan 20, 2014
To evaluate the incremental prognostic value of the number and maximum volume of coronary artery ... more To evaluate the incremental prognostic value of the number and maximum volume of coronary artery calcifications over modified Agatston score strata, age, pack-years, and smoking status for predicting cardiovascular events. A total of 3559 male current and former smokers received a CT examination for lung cancer screening. Smoking characteristics, patient demographics, and physician-diagnosed cardiovascular events were collected. Images were acquired without electrocardiography gating on 16-slice CT scanners. The association between the presence of both fatal and nonfatal cardiovascular events and the predictors was quantified using Cox proportional hazard analysis. Median follow-up period was 2.9 years. Incident cardiovascular events occurred in 186 participants. Adjusted hazard ratios for modified Agatston score strata of 1 to 10, 11 to 100, 101 to 400, and >400 were 3.39 (95% confidence interval [CI], 1.20-9.59), 6.52 (95% CI, 2.73-15.60), 6.58 (95% CI, 2.75-15.78), and 12.58 (...
Contextual information plays an important role in medical image understanding. Medical experts ma... more Contextual information plays an important role in medical image understanding. Medical experts make use of context to detect and differentiate pathologies in medical images, especially when interpreting difficult cases. The majority of computer-aided diagnosis (CAD) systems, however, employ only local information to classify candidates, without taking into account global image information or the relation of a candidate with neighboring structures. In this paper, we present a generic system for including contextual information in a CAD system. Context is described by means of high-level features based on the spatial relation between lesion candidates and surrounding anatomical landmarks and lesions of different classes (static contextual features) and lesions of the same type (dynamic contextual features). We demonstrate the added value of contextual CAD for two real-world CAD tasks: the identification of exudates and drusen in 2D retinal images and coronary calcifications in 3D comp...
The objective of this study was to investigate the association of spirometry and pulmonary CT bio... more The objective of this study was to investigate the association of spirometry and pulmonary CT biomarkers with cardiovascular events. In this lung cancer screening trial 3,080 male participants without a prior cardiovascular event were analysed. Fatal and non-fatal cardiovascular events were included. Spirometry included forced expiratory volume measured in units of one-second percent predicted (FEV1%predicted) and FEV1 divided by forced vital capacity (FVC; FEV1/FVC). CT examinations were quantified for coronary artery calcium volume, pulmonary emphysema (perc15) and bronchial wall thickness (pi10). Data were analysed via a Cox proportional hazard analysis, net reclassification improvement (NRI) and C-indices. 184 participants experienced a cardiovascular event during a median follow-up of 2.9 years. Age, pack-years and smoking status adjusted hazard ratios were 0.992 (95% confidence interval (CI) 0.985-0.999) for FEV1%predicted, 1.000 (95%CI 0.986-1.015) for FEV1/FVC, 1.014 (95%CI ...
A novel atlas-based segmentation approach based on the combination of multiple registrations is p... more A novel atlas-based segmentation approach based on the combination of multiple registrations is presented. Multiple atlases are registered to a target image. To obtain a segmentation of the target, labels of the atlas images are propagated to it. The propagated labels are combined by spatially varying decision fusion weights. These weights are derived from local assessment of the registration success.
To retrospectively evaluate the effect of a small variation of scan starting position on coronary... more To retrospectively evaluate the effect of a small variation of scan starting position on coronary artery calcium scores based on nonoverlapping 3-mm multidetector computed tomographic (CT) data sets.
Background: Current smokers have an increased cardiovascular disease (CVD) risk compared to ex-sm... more Background: Current smokers have an increased cardiovascular disease (CVD) risk compared to ex-smokers due to reversible as well as irreversible effects of smoking. We investigated if current smokers remain to have an increased CVD risk compared to ex-smokers in subjects with a long and intense smoking history. We in addition studied if the effect of smoking continuation on CVD risk is independent of or modified by the presence of cardiovascular calcifications.
A fully automated method for coronary calcification detection from non-contrast-enhanced, ECG-gat... more A fully automated method for coronary calcification detection from non-contrast-enhanced, ECG-gated multi-slice computed tomography (CT) data is presented. Candidates for coronary calcifications are extracted by thresholding and component labeling. These candidates include coronary calcifications, calcifications in the aorta and in the heart, and other high-density structures such as noise and bone. A dedicated set of 64 features is calculated for each candidate object. They characterize the object's spatial position relative to the heart and the aorta, for which an automatic segmentation scheme was developed, its size and shape, and its appearance, which is described by a set of approximated Gaussian derivatives for which an efficient computational scheme is presented. Three classification strategies were designed. The first one tested direct classification without feature selection. The second approach also utilized direct classification, but with feature selection. Finally, the third scheme employed two-stage classification. In a computationally inexpensive first stage, the most easily recognizable false positives were discarded. The second stage discriminated between more difficult to separate coronary calcium and other candidates. Performance of linear, quadratic, nearest neighbor, and support vector machine classifiers was compared. The method was tested on 76 scans containing 275 calcifications in the coronary arteries and 335 calcifications in the heart and aorta. The best performance was obtained employing a two-stage classification system with a k-nearest neighbor (k-NN) classifier and a feature selection scheme. The method detected 73.8% of coronary calcifications at the expense of on average 0.1 false positives per scan. A calcium score was computed for each scan and subjects were assigned one of four risk categories based on this score. The method assigned the correct risk category to 93.4% of all scans.
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., 2004
An automated method for coronary calcification detection is presented. First the heart region is ... more An automated method for coronary calcification detection is presented. First the heart region is extracted, in which objects potentially representing calcifications are obtained by thresholding. Besides coronary calcifications, the set of objects includes other heart calcifications, bony structures and noise. For each object, features describing its size, shape, position and appearance are computed. Several classifiers and classification strategies are evaluated. Best results are obtained with a specifically designed sequence of kNN classifiers that employ sequential forward feature selection. First obvious non-calcifications are removed, then calcifications are distinguished from non-calcifications and a final classifier discerns coronary calcifications from other cardiac calcifications. In 14 CT scans containing 61 coronary calcifications, 46 (75%) are detected at the expense of on average 0.9 false positive objects per scan.
ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005., 2005
An automated method for coronary calcification detection from ECG-triggered multi-slice CT data i... more An automated method for coronary calcification detection from ECG-triggered multi-slice CT data is presented. The method first segments the heart region. In the obtained volume candidate objects are extracted by thresholding. They include coronary calcification, calcium located elsewhere in the heart, for example, in the valves or the myocardium, and other high density structures mostly representing noise and bone. A set of 57 features is calculated for each candidate object. In the feature space objects are classified with a k-NN classifier and feature selection in three consecutive stages. The method is tested on 51 scans of the heart. They contain 320 calcification in the coronary arteries, 291 in the aorta and 62 calcifications in the heart. The system correctly detected 177 calcifications in the coronaries at the expense of 56 false positive objects. On average the method makes 3.8 errors per scan.
Atlas-based segmentation is a popular generic technique for automated delineation of structures i... more Atlas-based segmentation is a popular generic technique for automated delineation of structures in volumetric data sets. Several studies have shown that multi-atlas based segmentation methods outperform schemes that use only a single atlas, but running multiple registrations on large volumetric data is too time-consuming for routine clinical use. We propose a generally applicable adaptive local multi-atlas segmentation method (ALMAS) that
Preterm birth is often associated with impaired brain development. The state and expected progres... more Preterm birth is often associated with impaired brain development. The state and expected progression of preterm brain development can be evaluated using quantitative assessment of MR images. Such measurements require accurate segmentation of different tissue types in those images. This paper presents an algorithm for the automatic segmentation of unmyelinated white matter (WM), cortical grey matter (GM), and cerebrospinal fluid in the extracerebral space (CSF). The algorithm uses supervised voxel classification in three subsequent stages. In the first stage, voxels that can easily be assigned to one of the three tissue types are labelled. In the second stage, dedicated analysis of the remaining voxels is performed. The first and the second stage both use two-class classification for each tissue type separately. Possible inconsistencies that could result from these tissue-specific segmentation stages are resolved in the third stage, which performs multi-class classification. A set of T1- and T2-weighted images was analysed, but the optimised system performs automatic segmentation using a T2-weighted image only. We have investigated the performance of the algorithm when using training data randomly selected from completely annotated images as well as when using training data from only partially annotated images. The method was evaluated on images of preterm infants acquired at 30 and 40 weeks postmenstrual age (PMA). When the method was trained using random selection from the completely annotated images, the average Dice coefficients were 0.95 for WM, 0.81 for GM, and 0.89 for CSF on an independent set of images acquired at 30 weeks PMA. When the method was trained using only the partially annotated images, the average Dice coefficients were 0.95 for WM, 0.78 for GM and 0.87 for CSF for the images acquired at 30 weeks PMA, and 0.92 for WM, 0.80 for GM and 0.85 for CSF for the images acquired at 40 weeks PMA. Even though the segmentations obtained using training data from the partially annotated images resulted in slightly lower Dice coefficients, the performance in all experiments was close to that of a second human expert (0.93 for WM, 0.79 for GM and 0.86 for CSF for the images acquired at 30 weeks, and 0.94 for WM, 0.76 for GM and 0.87 for CSF for the images acquired at 40 weeks). These results show that the presented method is robust to age and acquisition protocol and that it performs accurate segmentation of WM, GM, and CSF when the training data is extracted from complete annotations as well as when the training data is extracted from partial annotations only. This extends the applicability of the method by reducing the time and effort necessary to create training data in a population with different characteristics.
IEEE transactions on medical imaging, Jan 16, 2015
The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardio... more The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. We present a system that automatically quantifies total patient and per coronary artery CAC in non-contrast-enhanced, ECGtriggered cardiac CT. The system identifies candidate calcifications that cannot be automatically labeled with high certainty and optionally presents these to an expert for review. Candidates were extracted by intensity-based thresholding and described by location features derived from estimated coronary artery positions, as well as size, shape and intensity features. Next, a two-class classifier distinguished between coronary calcifications and negatives or a multiclass classifier labeled CAC per coronary artery. Candidates that could not be labeled with high certainty were identified by entropy-based ambiguity detection and presented to an expert for review and possible relabeling. The system was evaluated with 530 test images. Using the two-class cl...
Certain pulmonary diseases are associated with cardiovascular disease (CVD). Therefore we investi... more Certain pulmonary diseases are associated with cardiovascular disease (CVD). Therefore we investigated the incremental predictive value of pulmonary, mediastinal and pleural features over cardiovascular imaging findings. A total of 10,410 patients underwent diagnostic chest CT for non-cardiovascular indications. Using a case-cohort approach, we visually graded CTs from the cases and from an approximately 10 % random sample of the baseline cohort (n = 1,203) for cardiovascular, pulmonary, mediastinal and pleural findings. The incremental value of pulmonary disease-related CT findings above cardiovascular imaging findings in cardiovascular event risk prediction was quantified by comparing discrimination and reclassification. During a mean follow-up of 3.7 years (max. 7.0 years), 1,148 CVD events (cases) were identified. Addition of pulmonary, mediastinal and pleural features to a cardiovascular imaging findings-based prediction model led to marginal improvement of discrimination (incr...
Atlas-based segmentation is a powerful generic technique for automatic delineation of structures ... more Atlas-based segmentation is a powerful generic technique for automatic delineation of structures in volumetric images. Several studies have shown that multi-atlas segmentation methods outperform schemes that use only a single atlas, but running multiple registrations on volumetric data is time-consuming. Moreover, for many scans or regions within scans, a large number of atlases may not be required to achieve good segmentation performance and may even deteriorate the results. It would therefore be worthwhile to include the decision which and how many atlases to use for a particular target scan in the segmentation process. To this end, we propose two generally applicable multi-atlas segmentation methods, adaptive multi-atlas segmentation (AMAS) and adaptive local multi-atlas segmentation (ALMAS). AMAS automatically selects the most appropriate atlases for a target image and automatically stops registering atlases when no further improvement is expected. ALMAS takes this concept one step further by locally deciding how many and which atlases are needed to segment a target image. The methods employ a computationally cheap atlas selection strategy, an automatic stopping criterion, and a technique to locally inspect registration results and determine how much improvement can be expected from further registrations.
This work presents a system for automatic coronary calcium scoring and cardiovascular risk strati... more This work presents a system for automatic coronary calcium scoring and cardiovascular risk stratification in thoracic CT scans. Data was collected from a Dutch-Belgian lung cancer screening trial. In 121 low-dose, non-ECG synchronized, non-contrast enhanced thoracic CT scans an expert scored coronary calcifications manually. A key element of the proposed algorithm is that the approximate position of the coronary arteries
Purpose: Volumetric measurements of neonatal brain tissues may be used as a biomarker for later n... more Purpose: Volumetric measurements of neonatal brain tissues may be used as a biomarker for later neurodevelopmental outcome. We propose an automatic method for probabilistic brain segmentation in neonatal MRIs.
To investigate the frequency of aortic calcifications at the outer edge of the false lumen and th... more To investigate the frequency of aortic calcifications at the outer edge of the false lumen and the frequency of fully circular aortic calcifications in a consecutive series of patients with aortic dissection who underwent contrast-enhanced CT. The study population compromised of 69 consecutive subjects aged 60 years and older with a contrast-enhanced CT scan demonstrating an aortic dissection. All CT scans were evaluated for the frequency of aortic calcifications at the outer edge of the false lumen and the frequency of fully circular aortic calcifications by two experienced observers. Between observer reliability was evaluated by using Cohen's Kappa. Differences between groups were tested using unpaired T test and Chi-square test. Presumed media calcifications were observed in 22 (32%) patients of 60 years and older and were found more frequently in chronic aortic dissection (N = 12/23, 52%) than in acute aortic dissection (N = 10/46, 22%). As the intima has been torn away by the aortic dissection it is highly likely that CT scans can visualize the calcifications in the tunica media of the aorta.
Objective: To determine the agreement and reliability of fully automated coronary artery calcium ... more Objective: To determine the agreement and reliability of fully automated coronary artery calcium (CAC) scoring in a lung cancer screening population.
Journal of cardiovascular computed tomography, Jan 20, 2014
To evaluate the incremental prognostic value of the number and maximum volume of coronary artery ... more To evaluate the incremental prognostic value of the number and maximum volume of coronary artery calcifications over modified Agatston score strata, age, pack-years, and smoking status for predicting cardiovascular events. A total of 3559 male current and former smokers received a CT examination for lung cancer screening. Smoking characteristics, patient demographics, and physician-diagnosed cardiovascular events were collected. Images were acquired without electrocardiography gating on 16-slice CT scanners. The association between the presence of both fatal and nonfatal cardiovascular events and the predictors was quantified using Cox proportional hazard analysis. Median follow-up period was 2.9 years. Incident cardiovascular events occurred in 186 participants. Adjusted hazard ratios for modified Agatston score strata of 1 to 10, 11 to 100, 101 to 400, and >400 were 3.39 (95% confidence interval [CI], 1.20-9.59), 6.52 (95% CI, 2.73-15.60), 6.58 (95% CI, 2.75-15.78), and 12.58 (...
Contextual information plays an important role in medical image understanding. Medical experts ma... more Contextual information plays an important role in medical image understanding. Medical experts make use of context to detect and differentiate pathologies in medical images, especially when interpreting difficult cases. The majority of computer-aided diagnosis (CAD) systems, however, employ only local information to classify candidates, without taking into account global image information or the relation of a candidate with neighboring structures. In this paper, we present a generic system for including contextual information in a CAD system. Context is described by means of high-level features based on the spatial relation between lesion candidates and surrounding anatomical landmarks and lesions of different classes (static contextual features) and lesions of the same type (dynamic contextual features). We demonstrate the added value of contextual CAD for two real-world CAD tasks: the identification of exudates and drusen in 2D retinal images and coronary calcifications in 3D comp...
The objective of this study was to investigate the association of spirometry and pulmonary CT bio... more The objective of this study was to investigate the association of spirometry and pulmonary CT biomarkers with cardiovascular events. In this lung cancer screening trial 3,080 male participants without a prior cardiovascular event were analysed. Fatal and non-fatal cardiovascular events were included. Spirometry included forced expiratory volume measured in units of one-second percent predicted (FEV1%predicted) and FEV1 divided by forced vital capacity (FVC; FEV1/FVC). CT examinations were quantified for coronary artery calcium volume, pulmonary emphysema (perc15) and bronchial wall thickness (pi10). Data were analysed via a Cox proportional hazard analysis, net reclassification improvement (NRI) and C-indices. 184 participants experienced a cardiovascular event during a median follow-up of 2.9 years. Age, pack-years and smoking status adjusted hazard ratios were 0.992 (95% confidence interval (CI) 0.985-0.999) for FEV1%predicted, 1.000 (95%CI 0.986-1.015) for FEV1/FVC, 1.014 (95%CI ...
A novel atlas-based segmentation approach based on the combination of multiple registrations is p... more A novel atlas-based segmentation approach based on the combination of multiple registrations is presented. Multiple atlases are registered to a target image. To obtain a segmentation of the target, labels of the atlas images are propagated to it. The propagated labels are combined by spatially varying decision fusion weights. These weights are derived from local assessment of the registration success.
To retrospectively evaluate the effect of a small variation of scan starting position on coronary... more To retrospectively evaluate the effect of a small variation of scan starting position on coronary artery calcium scores based on nonoverlapping 3-mm multidetector computed tomographic (CT) data sets.
Background: Current smokers have an increased cardiovascular disease (CVD) risk compared to ex-sm... more Background: Current smokers have an increased cardiovascular disease (CVD) risk compared to ex-smokers due to reversible as well as irreversible effects of smoking. We investigated if current smokers remain to have an increased CVD risk compared to ex-smokers in subjects with a long and intense smoking history. We in addition studied if the effect of smoking continuation on CVD risk is independent of or modified by the presence of cardiovascular calcifications.
A fully automated method for coronary calcification detection from non-contrast-enhanced, ECG-gat... more A fully automated method for coronary calcification detection from non-contrast-enhanced, ECG-gated multi-slice computed tomography (CT) data is presented. Candidates for coronary calcifications are extracted by thresholding and component labeling. These candidates include coronary calcifications, calcifications in the aorta and in the heart, and other high-density structures such as noise and bone. A dedicated set of 64 features is calculated for each candidate object. They characterize the object's spatial position relative to the heart and the aorta, for which an automatic segmentation scheme was developed, its size and shape, and its appearance, which is described by a set of approximated Gaussian derivatives for which an efficient computational scheme is presented. Three classification strategies were designed. The first one tested direct classification without feature selection. The second approach also utilized direct classification, but with feature selection. Finally, the third scheme employed two-stage classification. In a computationally inexpensive first stage, the most easily recognizable false positives were discarded. The second stage discriminated between more difficult to separate coronary calcium and other candidates. Performance of linear, quadratic, nearest neighbor, and support vector machine classifiers was compared. The method was tested on 76 scans containing 275 calcifications in the coronary arteries and 335 calcifications in the heart and aorta. The best performance was obtained employing a two-stage classification system with a k-nearest neighbor (k-NN) classifier and a feature selection scheme. The method detected 73.8% of coronary calcifications at the expense of on average 0.1 false positives per scan. A calcium score was computed for each scan and subjects were assigned one of four risk categories based on this score. The method assigned the correct risk category to 93.4% of all scans.
Uploads
Papers by Ivana Isgum