Margarete Ortner

Bio: Margarete Ortner is an academic researcher from Telecom SudParis. The author has contributed to research in topics: Image segmentation & Segmentation. The author has an hindex of 5, co-authored 8 publications receiving 251 citations.

Extraction of Airways From CT (EXACT'09)

Abstract: This paper describes a framework for establishing a reference airway tree segmentation, which was used to quantitatively evaluate 15 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 20 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.

A morphological-aggregative approach for 3D segmentation of pulmonary airways from generic MSCT acquisitions

Abstract: Three-dimensional segmentation of airways from multi-slice computed tomography (MSCT) is a key point in the development of computer-aided tools for respiratory investigation. The expected benefits are related to diagnosis improvement of airway pathologies, preoperative planning and follow-up. The segmentation issue becomes even more challenging with regard to the high variability of the MSCT image acquisition in clinical practice due to the different CT scanners used and the various protocols (mainly at low dose). This paper develops a generic and automated 3D airway segmentation approach able to deal with a large spectrum of MSCT protocols by exploiting a combined morphologicalaggregative methodology. The proposed method was independently assessed by an external group of medical experts in the context of a segmentation challenge, on a database consisting of 20 thorax MSCT datasets. This database included acquisitions from several clinical centers equipped with different CT scanners and using various protocols. The evaluation results show a good performance of the developed approach in terms of airway segments detection accuracy, in the context of highly variable MSCT input data.

Airway shape assessment with visual feed-back in asthma and obstructive diseases

Abstract: Airway remodeling in asthma patients has been studied in vivo by means of endobronchial biopsies allowing to assess structural and inflammatory changes. However, this technique remains relatively invasive and difficult to use in longitudinal trials. The development of alternative non-invasive tests, namely exploiting high-resolution imaging modalities such as MSCT, is gaining interest in the medical community. This paper develops a fullyautomated airway shape assessment approach based on the 3D segmentation of the airway lumen from MSCT data. The objective is to easily notify the radiologist on bronchus shape variations (stenoses, bronchiectasis) along the airway tree during a simple visual investigation. The visual feed-back is provided by means of a volumerendered color coding of the airway calibers which are robustly defined and computed, based on a specific 3D discrete distance function able to deal with small size structures. The color volume rendering (CVR) information is further on reinforced by the definition and computation of a shape variation index along the airway medial axis enabling to detect specific configurations of stenoses. Such cases often occur near bifurcations (bronchial spurs) and they are either missed in the CVR or difficult to spot due to occlusions by other segments. Consequently, all detected shape variations (stenoses, dilations and thickened spurs) can be additionally displayed on the medial axis and investigated together with the CVR information. The proposed approach was evaluated on a MSCT database including twelve patients with severe or moderate persistent asthma, or severe COPD, by analyzing segmental and subsegmental bronchi of the right lung. The only CVR information provided for a limited number of views allowed to detect 78% of stenoses and bronchial spurs in these patients, whereas the inclusion of the shape variation index enabled to complement the missing information.

Volumetric quantification of airway wall in CT via collision-free active surface model: application to asthma assessment.

Abstract: Emerging idea in asthma phenotyping, incorporating local morphometric information on the airway wall thickness would be able to better account for the process of airway remodeling as indicator of pathology or therapeutic impact. It is thus important that such information be provided uniformly along the airway tree, not on a sparse (cross-section) sampling basis. The volumetric segmentation of the airway wall from CT data is the issue addressed in this paper by exploiting a patient-specific surface active model. An original aspect taken into account in the proposed deformable model is the management of auto-collisions for this complex morphology. The analysis of several solutions ended up with the design of a motion vector field specific to the patient geometry to guide the deformation. The segmentation result, presented as two embedded inner/outer surfaces of the wall, allows the quantification of the tissue thickness based on a locally-defined measure sensitive to even small surface irregularities. The method is validated with respect to several ground truth simulations of pulmonary CT data with different airway geometries and acquisition protocols showing accuracy within the CT resolution range. Results from an ongoing clinical study on moderate and severe asthma are presented and discussed.

3D vector flow guided segmentation of airway wall in MSCT

Abstract: This paper develops a 3D automated approach for airway wall segmentation and quantification inMSCT based on a patient-specific deformable model. The model is explicitly defined as a triangular surface mesh at the level of the airway lumen segmented from the MSCT data. The model evolves according to simplified Lagrangian dynamics, where the deformation force field is defined by a case-specific generalized gradient vector flow. Such force formulation allows locally adaptive time step integration and prevents model self-intersections. The evaluations performed on simulated and clinical MSCT data have shown a good agreement with the radiologist expertise and underlined a higher potential of the proposed 3D approach for the study of airway remodeling versus 2D cross-section techniques.

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Abstract: In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

Robust Brain Extraction Across Datasets and Comparison With Publicly Available Methods

Abstract: Automatic whole-brain extraction from magnetic resonance images (MRI), also known as skull stripping, is a key component in most neuroimage pipelines. As the first element in the chain, its robustness is critical for the overall performance of the system. Many skull stripping methods have been proposed, but the problem is not considered to be completely solved yet. Many systems in the literature have good performance on certain datasets (mostly the datasets they were trained/tuned on), but fail to produce satisfactory results when the acquisition conditions or study populations are different. In this paper we introduce a robust, learning-based brain extraction system (ROBEX). The method combines a discriminative and a generative model to achieve the final result. The discriminative model is a Random Forest classifier trained to detect the brain boundary; the generative model is a point distribution model that ensures that the result is plausible. When a new image is presented to the system, the generative model is explored to find the contour with highest likelihood according to the discriminative model. Because the target shape is in general not perfectly represented by the generative model, the contour is refined using graph cuts to obtain the final segmentation. Both models were trained using 92 scans from a proprietary dataset but they achieve a high degree of robustness on a variety of other datasets. ROBEX was compared with six other popular, publicly available methods (BET, BSE, FreeSurfer, AFNI, BridgeBurner, and GCUT) on three publicly available datasets (IBSR, LPBA40, and OASIS, 137 scans in total) that include a wide range of acquisition hardware and a highly variable population (different age groups, healthy/diseased). The results show that ROBEX provides significantly improved performance measures for almost every method/dataset combination.

CT-Definable Subtypes of Chronic Obstructive Pulmonary Disease: A Statement of the Fleischner Society.

Abstract: Integration of visual characterization of emphysema and airway abnormalities with physiologic and quantitative CT assessment permits categorization of chronic obstructive pulmonary disease into distinct structurally and functionally defined subtypes.

Extraction of Airways From CT (EXACT'09)

Abstract: This paper describes a framework for establishing a reference airway tree segmentation, which was used to quantitatively evaluate 15 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 20 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.