Search

Your search keyword '"Alexander Brost"' showing total 117 results
Start Over Author "Alexander Brost"
117 results on '"Alexander Brost"'

1. Machine Learning Prediction of Treatment Response to Biological Disease-Modifying Antirheumatic Drugs in Rheumatoid Arthritis

Author

Fatemeh Salehi, Luis I. Lopera Gonzalez, Sara Bayat, Arnd Kleyer, Dario Zanca, Alexander Brost, Georg Schett, and Bjoern M. Eskofier

Subjects
bDMARDs, machine learning predictive model, rheumatoid arthritis, treatment response, prediction, Medicine
Abstract

Background: Disease-modifying antirheumatic drugs (bDMARDs) have shown efficacy in treating Rheumatoid Arthritis (RA). Predicting treatment outcomes for RA is crucial as approximately 30% of patients do not respond to bDMARDs and only half achieve a sustained response. This study aims to leverage machine learning to predict both initial response at 6 months and sustained response at 12 months using baseline clinical data. Methods: Baseline clinical data were collected from 154 RA patients treated at the University Hospital in Erlangen, Germany. Five machine learning models were compared: Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), K-nearest neighbors (KNN), Support Vector Machines (SVM), and Random Forest. Nested cross-validation was employed to ensure robustness and avoid overfitting, integrating hyperparameter tuning within its process. Results: XGBoost achieved the highest accuracy for predicting initial response (AUC-ROC of 0.91), while AdaBoost was the most effective for sustained response (AUC-ROC of 0.84). Key predictors included the Disease Activity Score-28 using erythrocyte sedimentation rate (DAS28-ESR), with higher scores at baseline associated with lower response chances at 6 and 12 months. Shapley additive explanations (SHAP) identified the most important baseline features and visualized their directional effects on treatment response and sustained response. Conclusions: These findings can enhance RA treatment plans and support clinical decision-making, ultimately improving patient outcomes by predicting response before starting medication.

Published
2024
Full Text
View/download PDF

2. Rapid Interactive and Intuitive Segmentation of 3D Medical Images Using Radial Basis Function Interpolation

Author

Tanja Kurzendorfer, Peter Fischer, Negar Mirshahzadeh, Thomas Pohl, Alexander Brost, Stefan Steidl, and Andreas Maier

Subjects
smart brush, segmentation, 3D interpolation, Hermite radial basis function, Photography, TR1-1050, Computer applications to medicine. Medical informatics, R858-859.7, Electronic computers. Computer science, QA75.5-76.95
Abstract

Segmentation is one of the most important parts of medical image analysis. Manual segmentation is very cumbersome, time-consuming, and prone to inter-observer variability. Fully automatic segmentation approaches require a large amount of labeled training data and may fail in difficult or abnormal cases. In this work, we propose a new method for 2D segmentation of individual slices and 3D interpolation of the segmented slices. The Smart Brush functionality quickly segments the region of interest in a few 2D slices. Given these annotated slices, our adapted formulation of Hermite radial basis functions reconstructs the 3D surface. Effective interactions with less number of equations accelerate the performance and, therefore, a real-time and an intuitive, interactive segmentation of 3D objects can be supported effectively. The proposed method is evaluated on 12 clinical 3D magnetic resonance imaging data sets and are compared to gold standard annotations of the left ventricle from a clinical expert. The automatic evaluation of the 2D Smart Brush resulted in an average Dice coefficient of 0.88 ± 0.09 for the individual slices. For the 3D interpolation using Hermite radial basis functions, an average Dice coefficient of 0.94 ± 0.02 is achieved.

Published
2017
Full Text
View/download PDF

47. Left Ventricle Segmentation in LGE-MRI: Filter Based vs. Learning Based

Author

Andreas Maier, Tanja Kurzendorfer, Christoph Forman, Alexander Brost, Stefan Steidl, and Katharina Breininger

Subjects
medicine.medical_specialty, Ejection fraction, medicine.diagnostic_test, business.industry, medicine.medical_treatment, Cardiac resynchronization therapy, Magnetic resonance imaging, Gold standard (test), 030204 cardiovascular system & hematology, medicine.disease, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, medicine.anatomical_structure, Ventricle, Heart failure, medicine, Segmentation, Radiology, business, Endocardium
Abstract

Ischaemic heart disease is the number one cause of death world wide, which is in close relation with heart failure. If patients suffer from drug-refractory heart failure with a reduced ejection fraction, cardiac resynchronization therapy is a treatment option. For planning the procedure, precise information about the left ventricle’s anatomy and scar distribution is required. The clinical gold standard to visualize scar is late gadolinium enhanced magnetic resonance imaging (LGE-MRI). The challenge arises in the myocardium segmentation of these sequences which is a pre-requisite for an accurate scar quantification. In this work, we compare a filter based approach against a learning based approach for LGE-MRI segmentation. For both approaches the segmentation workflow consists of four major steps. First, the left ventricle is detected. Second, the blood pool is estimated. Third, the endocardium is refined using scar information. Fourth, the epicardium is extracted.The proposed methods were evaluated on 100 clinical LGE-MRI data sets. For the learning based approach a 5-fold nested cross-validation is applied to evaluate the hyper-parameters. The learning based segmentation achieves slightly better results, with a Dice score of 0.82 ± 0.09 for the endocard and 0.81 ± 0.08 for the epicard.

Published
2018

48. ORAL AB AGORA1362Cardiac Involvement in Patients With Different Rheumatic Disorders1366Gender differences in the development of cardiac complications: a multicentric prospective study in a large cohort of thalassemia major patients1646Comparison of T1-mapping, T2-weighted and contrast-enhanced cine imaging at 3.0T CMR for diagnostic oedema assessment in ST-segment elevation myocardial infarction1375Evaluation of Tissue Changes in Remote Noninfarcted Myocardium after Acute Myocardial Infarction using T1-mapping1377Right ventricular long axis strain – The prognostic value of a novel parameter in non-ischemic dilated cardiomyopathy using standard cardiac magnetic resonance imaging1389The role of the right ventricular insertion point in heart failure patients with preserved ejection fraction: Insights from a cardiovascular magnetic resonance study1398Myocardial fibrosis associates with B-type natriuretic peptide levels and outcomes more than wall stress1478Prognostic Value of Pulmonary Blood Volume by Contrast-Enhanced Magnetic Resonance Imaging in Heart Failure Outpatients – The PROVE-HF Study1370Magnetic Resonance Adenosine Perfusion Imaging as Gatekeeper of Invasive Coronary1509Influence of non-invasive hemodynamic CMR parameters on maximal exercise capacity in surgically untreated patients with Ebstein's anomaly1356Proximal aortic stiffening in Turner patients is more pronounced in the presence of a bicuspid valve. A segmental functional MRI study1503Flow pattern and vascular distensibility of the pulmonary arteries in patients after repair of tetralogy of Fallot. Insights from 4D flow CMR1516Myocardial deformation characteristics of the systemic right ventricle after atrial switch operation for transposition of the great arteries1633Three-dimensional vortex formation in patients with a Fontan circulation: evaluation with 4D flow CMR1483Mitral valve prolapse: arrhythmogenic substrates by cardiac magnetic imaging1596Increased local wall shear stress after coarctation repair is associated with descending aorta pulse wave velocity: evaluation with CMR and 4D flow1636Three-dimensional wall shear stress assessed by 4Dflow CMR in bicuspid aortic valve disease1464Cardiac Amyloidosis and Aortic Stenosis – The Convergence of Two Aging Processes1630Blood T1 variability explained in healthy volunteers: an analysis on MOLLI, ShMOLLI and SASHA1408Myocardial deformation on CMR predicts adverse outcomes in carcinoid heart disease - a new marker of risk1492Myocardial Perfusion Reserve and Global Longitudinal Strain in Early Rheumatoid Arthritis1500Exercise CMR to differentiate athlete's heart from patients with early dilated cardiomyopathy1559Real-Time, x-mri guidance to optimise left ventricular lead placement for delivery of cardiac resynchronisation therapy1560The role of Cardiac magnetic resonance imaging in patients undergoing ablation for ventricular tachycardia- Defining the substrate and visualizing the outcome1590Impact of cardiovascular magnetic resonance on clinical management and decision-making of out of hospital cardiac arrest survivors with inconclusive coronary angiogram1561Detection of coronary stenosis at rest using Oxygenation-Sensitive Magnetic Resonance Imaging

Author

J. Ranjit Arnold, A. Baritussio, S. Oebel, Jonathan Behar, G. Claessen, G.J. Fent, B. Liu, Stefania Rosmini, João L. Cavalcante, Lydia Dux-Santoy, I. Nederend, Manuel De Lazzari, Vivian P. Kamphuis, B.E.U. Burkhardt, Beate Ruecker, Daniel G.H. Devos, Christian Meierhofer, Peter Bernhardt, F. Ricci, Aatif Sayeed, Andreas A. Kammerlander, Nisha Arenja, P. Stefan Biesbroek, Sheraz A. Nazir, A. Meloni, S. Greulich, D. Kitterer, J. Latus, J. Henes, R. Kurmann, S. Gloekler, A. Wahl, S. Buss, H. Katus, M. Bobbo, M. Lombardi, N. Braun, M.D. Alscher, U. Sechtem, H. Mahrholdt, M.G. Neri, P. Preziosi, E. Grassedonio, N. Schicchi, P. Keilberg, S. Pulini, E. Facchini, V. Positano, A. Pepe, Abhishek Shetye, Jamal N. Khan, Anvesha Singh, Prathap Kanagala, Daniel Swarbrick, Gaurav Gulsin, Matthew Graham-Brown, Iain Squire, Anthony Gershlick, Gerry P. McCann, Raquel P. Amier, Paul F.A. Teunissen, Lourens F.H.J. Robbers, Aernout M. Beek, Albert C. van Rossum, Mark B.M. Hofman, Niels van Royen, Robin Nijveldt, Johannes H Riffel, Charly Noel Djiokou, Florian Andre, Thomas Fritz, Manuel Halder, Zelniker Thomas, Grigorios Korosoglou, Hugo A Katus, Sebastian J Buss, Marianne L. Schwaiger, Franz Duca, Stefan Aschauer, Beatrice A. Marzluf, Caroline Zotter-Tufaro, Daniel Dalos, Stefan Pfaffenberger, Diana Bonderman, Julia Mascherbauer, Yaron Fridman, Brianne Hackman, Ajay Kadakkal, Maren Maanja, Hussein Abu Daya, Timothy C. Wong, Erik B. Schelbert, A. Barison, G. Todiere, R. Gaeta, S. Galllina, M. Emdin, R. De Caterina, G.D. Aquaro, Dominik Buckert, Nils Dyckmanns, Wolfgang Rottbauer, Andreas Kühn, Nerejda Shehu, Jan Müller, Heiko Stern, Peter Ewert, Sohrab Fratz, Manfred Vogt, Katya De Groote, Danilo Babin, Laurent Demulier, Yves Taeymans, Jos J. Westenberg, Luc Van Bortel, Patrick Segers, Eric Achten, Jean De Schepper, Ernst Rietzschel, Julia Geiger, Malek Makki, Barbara Burkhardt, Christian J. Kellenberger, Emanuela R. Valsangiacomo Buechel, C.J. Kellenberger, J. Geiger, B. Ruecker, E.R. Valsangiacomo Buechel, Mohammed S.M. Elbaz, Lucia J.M. Kroft, Rob J. van der Geest, Albert de Roos, Nico A. Blom, Jos J.M. Westenberg, Arno A.W. Roest, Alberto Cipriani, Angela Susana, Stefania Rizzo, Benedetta Giorgi, Lacognata Carmelo, Emanuele Bertaglia, Barbara Bauce, Domenico Corrado, Gaetano Thiene, Martina Perazzolo Marra, Cristina Basso, Sabino Iliceto, A.A.W. Roest, P.J. van den Boogaard, A.D.J. ten Harkel, J.C.N. de Geus, L.J.M. Kroft, A. de Roos, J.J.M. Westenberg, Raquel Kale, Gisela Teixido-Tura, Giuliana Maldonado, Marina Huguet, David Garcia-Dorado, Artur Evangelista, Jose Rodriguez-Palomares, Shasank Rijal, John T. Schindler, Thomas G. Gleason, Joon S. Lee, Heerajnarain Bulluck, Thomas A Treibel, Anish Bhuva, Amna Abdel-Gadir, Veronica Culotta, Ahmed Merghani, Viviana Maestrini, Anna S Herrey, Peter Kellman, Charlotte Manisty, James C Moon, M.K. Hayer, S. Baig, T. Shah, S.J. Rooney, N.C. Edwards, R.P. Steeds, P. Garg, P. Swoboda, L.E. Dobson, T.A. Musa, J.F. Foley, P. Haaf, J.P. Greenwood, S. Plein, F. Schnell, J. Bogaert, S. Dymarkowski, N. Pattyn, P. Claus, J. Van Cleemput, A. La Gerche, H. Heidbuchel, Daniel Toth, Sabrina Reiml, Maria Panayiotou, Simon Claridge, Tom Jackson, Manav Sohal, Jessica Webb, Mark O'Neill, Alexander Brost, Peter Mountney, Reza Razavi, Kawal Rhode, Christopher Aldo Rinaldi, A. Arya, S. Hilbert, A. Bollmann, G. Hindricks, C. Jahnke, I. Paetsch, B. Dinov, M. Perazzolo Marra, A. Ghosh Dastidar, J. Rodrigues, A. Zorzi, A. Susana, A. Scatteia, E. De Garate, G. Mattesi, J. Strange, D. Corrado, C. Bucciarelli-Ducci, Michael Jerosch-Herold, Theodoros D. Karamitsos, Jane M. Francis, Paul Bhamra-Ariza, Rizwan Sarwar, Robin Choudhury, Joseph B. Selvanayagam, and Stefan Neubauer

Subjects
medicine.medical_specialty, business.industry, Bicuspid valve, Internal medicine, Cardiology, Medicine, Radiology, Nuclear Medicine and imaging, General Medicine, Cardiology and Cardiovascular Medicine, business, Stiffening
Published
2016

49. Electrophysiology Catheter Detection and Reconstruction From Two Views in Fluoroscopic Images

Author

Norbert Strobel, Matthias Hoffmann, Martin Koch, Felix Bourier, Andreas Maier, Joachim Hornegger, Klaus Kurzidim, and Alexander Brost

Subjects
Computer science, medicine.medical_treatment, Initialization, Catheter ablation, Iterative reconstruction, 030204 cardiovascular system & hematology, 030218 nuclear medicine & medical imaging, Electrocardiography, 03 medical and health sciences, Imaging, Three-Dimensional, 0302 clinical medicine, medicine, Humans, Computer vision, Electrical and Electronic Engineering, Radiological and Ultrasound Technology, Phantoms, Imaging, business.industry, Image (category theory), Triangulation (computer vision), Coupling (probability), Computer Science Applications, Catheter, Surgery, Computer-Assisted, Fluoroscopy, Catheter Ablation, Artificial intelligence, business, Algorithms, Software
Abstract

Electrophysiology (EP) studies and catheter ablation have become important treatment options for several types of cardiac arrhythmias. We present a novel image-based approach for automatic detection and 3-D reconstruction of EP catheters where the physician marks the catheter to be reconstructed by a single click in each image. The result can be used to provide 3-D information for enhanced navigation throughout EP procedures. Our approach involves two X-ray projections acquired from different angles, and it is based on two steps: First, we detect the catheter in each view after manual initialization using a graph-search method. Then, the detection results are used to reconstruct a full 3-D model of the catheter based on automatically determined point pairs for triangulation. An evaluation on 176 different clinical fluoroscopic images yielded a detection rate of 83.4%. For measuring the error, we used the coupling distance which is a more accurate quality measure than the average point-wise distance to a reference. For successful outcomes, the 2-D detection error was $1.7\ {\rm mm} \pm 1.2$ mm. Using successfully detected catheters for reconstruction, we obtained a reconstruction error of $1.8\ {\rm mm} \pm 1.1$ mm on phantom data. On clinical data, our method yielded a reconstruction error of $2.2\ {\rm mm} \pm 2.2$ mm.

Published
2016

50. Myocardial Scar Segmentation in LGE-MRI using Fractal Analysis and Random Forest Classification

Author

Alexander Brost, Andreas Maier, Katharina Breininger, Tanja Kurzendorfer, Christoph Forman, and Stefan Steidl

Subjects
Binary Object, Computer science, Feature vector, Feature extraction, Scar tissue, 030204 cardiovascular system & hematology, Fractal dimension, 030218 nuclear medicine & medical imaging, Gadolinium-based Contrast Agent, 03 medical and health sciences, 0302 clinical medicine, Fractal, Myocardial scarring, medicine, Segmentation, medicine.diagnostic_test, business.industry, Binary image, Magnetic resonance imaging, Pattern recognition, Image segmentation, Fractal analysis, Random forest, Artificial intelligence, medicine.symptom, business
Abstract

Late-gadolinium enhanced magnetic resonance imaging (LGE-MRI) is the clinical gold standard to visualize myocardial scarring. The gadolinium based contrast agent accumulates in the damaged cells and leads to various enhancements in the LGE-MRI scan. The quantification of the scar tissue is very important for diagnosis, treatment planning, and guidance during the procedure. In clinical routine, the scar is often segmented manually. However, manual segmentation is prone to inter- and intra-observer variability and very time consuming. In this work a new texture based scar quantification is proposed. For texture characterization, segmentation based fractal analysis is used. First, the image is decomposed into a set of binary images by applying a two-threshold binary decomposition. Second, a set of features are extracted for each of the binary images, namely the fractal dimension, the mean gray value, and the size of the binary object. In addition, the local and global intensity of each patch is added to the feature vector. In the next step, the features are classified using a random forest classifier. The scar quantification is evaluated on 30 clinical LGE-MRI data sets. In addition, the results are compared to the $x$ -fold standard deviation approach and the full-width-at-half-max method, which are implemented in a fully automatic manner. The proposed scar quantification achieved a mean Dice coefficient of $0.64\pm 0.17$ and outperforms the x-fold standard deviation approach.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results