Martin Urschler, see also personal ICG website.

Christian Payer is a PhD student at the Institute for Computer Graphics and Vision at Graz University of Technology, funded by the FWF project FAME. He is interested in applications of deep learning in medical image analysis and currently focuses on automatic landmark localization algorithms.

Christian Bauer was a research assistant at the Institute for Computer Graphics and Vision at Graz University of Technology. He finished his PhD-Thesis focused on Tubular Structures in Medical Image Analysis in 2009.

Quantitative CT-derived vessel metrics in idiopathic pulmonary fibrosis: A structure function study

Knowledge of the lung vessel morphology in healthy subjects is necessary to improve our understanding about the functional network of the lung and to recognize pathologic deviations beyond the normal inter-subject variation. In order to determine morphologic readouts from a large number of healthy subjects, computed tomography pulmonary angiography (CTPA) datasets, negative for pulmonary embolism, and other thoracic pathologies, were analyzed using a fully-automatic, in-house developed artery/vein separation algorithm. Our fully-automatic artery/vein separation algorithm provided reliable measures of pulmonary arteries and veins with respect to age and gender. There was a large variation between subjects in all readouts. No relevant dependence on age, gender, or vessel type was observed. These data may provide reference values for morphometric analysis of lung vessels.

Jacob J, Pienn M, Payer C, Urschler M, Kokosi M, Devaraj A, Wells A W, Olschewski H: Published in Respirology 24(5): 445-452, 2019. DOI

Healthy Lung Vessel Morphology Derived From Thoracic Computed Tomography Knowledge of the lung vessel morphology in healthy subjects is necessary to improve our understanding about the functional network of the lung and to recognize pathologic deviations beyond the normal inter-subject variation. In order to determine morphologic readouts from a large number of healthy subjects, computed tomography pulmonary angiography (CTPA) datasets, negative for pulmonary embolism, and other thoracic pathologies, were analyzed using a fully-automatic, in-house developed artery/vein separation algorithm. Our fully-automatic artery/vein separation algorithm provided reliable measures of pulmonary arteries and veins with respect to age and gender. There was a large variation between subjects in all readouts. No relevant dependence on age, gender, or vessel type was observed. These data may provide reference values for morphometric analysis of lung vessels. Pienn M, Burgard C, Payer C, Avian A, Urschler M, Stollberger R, Olschewski A, Olschewski H, Johnson T, Meinel FG, Balint Z: Published in Frontiers in Physiology 9: 346, 2018. PDF,DOI

Pulmonary Lobe Segmentation in CT Images using Alpha-Expansion Fully-automatic lung lobe segmentation in pathological lungs is still a challenging task. A new approach for automatic lung lobe segmentation is presented based on airways, vessels, fissures and prior knowledge on lobar shape. The anatomical information and prior knowledge are combined into an energy equation, which is minimized via graph cuts to yield an optimal segmentation. The algorithm is quantitatively validated on an in-house dataset of 25 scans and on the LObe and Lung Analysis 2011 (LOLA11) dataset, which contains a range of different challenging lungs (total of 55) with respect to lobe segmentation. Giuliani N, Payer C, Pienn M, Olschewski H, Urschler M: In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP, Funchal - Madeira, Portugal, pages 387-394, Jan 2018. PDF, DOI.

Automated Integer Programming Based Separation of Arteries and Veins from Thoracic CT Images Automated computer-aided analysis of lung vessels has shown to yield promising results for non-invasive diagnosis of lung diseases. To detect vascular changes which affect pulmonary arteries and veins differently, both compartments need to be identified. We present a novel, fully automatic method that separates arteries and veins in thoracic computed tomography images, by combining local as well as global properties of pulmonary vessels. Payer C, Pienn M, Balint Z, Shekhovtsov A, Talakic E, Nagy E, Olschewski A, Olschewski H, Urschler M: Published in Medical Image Analysis 34: 109-122, 2016. PDF,DOI

Automatic Artery-Vein Separation from Thoracic CT Images Using Integer Programming Automated computer-aided analysis of lung vessels has shown to yield promising results for non-invasive diagnosis of lung diseases. In order to detect vascular changes affecting arteries and veins differently, an algorithm capable of identifying these two compartments is needed. We propose a fully automatic algorithm that separates arteries and veins in thoracic computed tomography (CT) images based on two integer programs. Payer C, Pienn M, Balint Z, Olschewski A, Olschewski H, Urschler M: Presented at International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Munich, GE. PDF, Received a Runners up Mentioning on the short list for the Young Scientist Award.

Increased tortuosity of pulmonary arteries in patients with pulmonary hypertension in the arteries Pulmonary hypertension (PH) is a chronic disorder of the pulmonary circulation, marked by an elevated vascular resistance and pressure. We hypothesised that, in patients with increased pressure in the arteries only, vessel tortuosity is more elevated in arteries than in veins. We present an automatic pulmonary vessel tree extraction algorithm, which identifies individual vessel trees. We conclude that tortuosity is indeed a measure for the pressure in the respective vessels and might be a useful readout for non-invasive diagnosis of PH. Pienn M, Payer C, Olschewski A, Olschewski H, Urschler M, Balint Z: Presented at Medical Image Understanding and Analysis (MIUA) 2015, Lincoln, UK. PDF, Received a Best Oral Presentation Award.

Quantification of Tortuosity and Fractal Dimension of the Lung Vessels in Pulmonary Hypertension Patients Pulmonary hypertension (PH) can result in vascular pruning and increased tortuosity of the blood vessels. In this study we examined whether automatic extraction of lung vessels from contrast-enhanced thoracic computed tomography (CT) scans and calculation of tortuosity as well as 3D fractal dimension of the segmented lung vessels results in measures associated with PH. Helmberger M, Pienn M, Urschler M, Kullnig P, Stollberger R, Kovacs G, Olschewski A, Olschewski H, Balint Z: Published in PLOS One 9(1): e87515, 2014. PDF,DOI

Tortuosity of Pulmonary Vessels Correlates with Pulmonary Hypertension Pulmonary hypertension (PH) is a chronic disorder of the pulmonary circulation, marked by an elevated vascular resistence and pressure. Our objective is to find an automatic, non invasive method for estimating the pulmonary pressure based on the analysis of lung vessels from contrast enhanced CT images. We present a pulmonary vessel extraction algorithm which is fast, fully automatic and robust. Helmberger M, Urschler M, Balint Z, Pienn M, Olschewski A, Bischof H: Presented at Medical Image Understanding and Analysis (MIUA) 2013, Birmingham, UK. PDF, Received a Best Paper Award.

Pulmonary Vascular Tree Segmentation from Contrast-Enhanced CT Images We present a pulmonary vessel segmentation algorithm, which is fast, fully automatic and robust. It uses a coarse segmentation of the airway tree and a left and right lung labeled volume to restrict a vessel enhancement filter, based on an offset medialness function, to the lungs. Helmberger M, Urschler M, Pienn M, Balint Z, Bischof H: Presented at 37th Workshop of the Austrian Association for Pattern Recognition (OAGM) 2013, Innsbruck, Austria. PDF

Segmentation of interwoven 3d tubular tree structures utilizing shape priors and graph cuts We present and evaluate a general approach for robust segmentation of tubular tree structures in 3d medical images. Bauer C, Pock T, Sorantin E, Bischof H, Beichel R: Published in Medical Image Analysis 14(2):172-184, 2010. PDF

Airway Tree Reconstruction Based on Tube Detection We present an automated approach for airway tree reconstruction that utilizing a tube detection filter in combination with prior knowledge about the structure of airway trees such that a high robustness against disturbances can be achieved. Bauer C, Pock T, Bischof H, Beichel R: Presented at Medical Image Computing and Computer Assisted Intervention: The Second International Workshop on Pulmonary Image Analysis 2009. PDF

Segmentation of Airways Based on Gradient Vector Flow The Gradient Vector Flow (GVF) based tube detection presented earlier is extended for segmentation of the associated tubular objects by utilizing properties of the GVF. The method is applied to airway tree segmentation. Bauer C, Bischof H, Beichel R: Presented at Medical Image Computing and Computer Assisted Intervention: The Second International Workshop on Pulmonary Image Analysis 2009. PDF

Extracting Curve Skeletons from Gray Value Images for Virtual Endoscopy The Gradient Vector Flow (GVF) based tube detection presented earlier is extended for extraction of complete curve skeletons. By utilizing a medialness property of the GVF and an efficient height-ridge traversal procedure centered curve-skeletons are extracted in non-tubular regions connecting the disconnected tubular parts. Bauer C, Bischof H: Presented at 4th International Workshop on Medical Imaging and Augmented Reality (MIAR) 2008. PDF

A Novel Approach for Detection of Tubular Objects and Its Application to Medical Image Analysis To address scale space related issues of typical tube detection filters, we replaced the conventionally applied multi-scale gradient vector computation by the Gradient Vector Flow (GVF). In combination with standard techniques tubular objects are identified in the resulting vector field without being influenced by other nearby image structures. Bauer C, Bischof H: Presented at 30th DAGM Symposium on Pattern Recognition (DAGM) 2008. PDF

Edge Based Tube Detection for Coronary Artery Centerline Extraction The extraction of the coronary artery central lumen lines from CTA datasets is a necessary prerequisite for the computerized assessment of heart related disease. In this work, we present an automatic approach for this task that consists of generic methods for detection of tubular objects, extraction of their centerlines, grouping of the single centerlines into complete tree structures, and some application specific adaptions for the identification of the coronary arteries. Bauer C, Bischof H: Presented at MICCAI 2008 Workshop: Grand Challenge Coronary Artery Tracking (The MIDAS Journal). PDF

A Novel Robust Tube Detection Filter for 3D Centerline Extraction Centerline extraction of tubular structures such as blood vessels and airways in 3D volume data is of vital interest for applications involving registration, segmentation and surgical planing. In this paper, we propose a robust method for 3D centerline extraction of tubular structures. The method is based on a novel multiscale medialness function and additionally provides an accurate estimate of tubular radius. Pock T, Beichel R, Bischof H: Presented at Scandinavian Conference on Image Analysis (SCIA) 2005. PDF