Dr. Julia Krüger Profile

Dr. Julia Krüger

Research Scientist at jung diagnostics GmbH

SPIE Involvement:

Author

Publications (10)

Proceedings Article | 3 April 2024 Poster + Paper

Quantitative evaluation of activation maps for weakly-supervised lung nodule segmentation

Finn Behrendt, Suyash Sonawane, Debayan Bhattacharya, Lennart Maack, Julia Krüger, Roland Opfer, Alexander Schlaefer

Proceedings Volume 12927, 129272P (2024) https://doi.org/10.1117/12.3006416

KEYWORDS: Image segmentation, Education and training, Chest imaging, Visualization, Deep learning, Performance modeling, Pathology, Lung, Convolutional neural networks, Artificial intelligence

Read Abstract +

Proceedings Article | 3 April 2024 Poster + Paper

Focused unsupervised image registration for structure-specific population analysis

Jan Ehrhardt, Hristina Uzunova, Paul Kaftan, Julia Krüger, Roland Opfer, Heinz Handels

Proceedings Volume 12927, 129272F (2024) https://doi.org/10.1117/12.3006119

KEYWORDS: Image registration, Image segmentation, Deformation, Image resolution, Image processing, Neuroimaging, Brain, Alzheimer disease

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Unsupervised anomaly detection in 3D brain MRI using deep learning with multi-task brain age prediction

Marcel Bengs, Finn Behrendt, Max-Heinrich Laves, Julia Krüger, Roland Opfer, Alexander Schlaefer

Proceedings Volume 12033, 1203314 (2022) https://doi.org/10.1117/12.2608120

KEYWORDS: Computer aided diagnosis and therapy, Machine learning, Computer vision technology, Pattern recognition, Brain, Magnetic resonance imaging, Neuroimaging, Magnetism, Intelligence systems, Diagnostics, Computer programming, 3D scanning, 3D magnetic resonance imaging

Read Abstract +

Proceedings Article | 15 March 2019 Paper

Bayesian inference for uncertainty quantification in point-based deformable image registration

Sandra Schultz, Julia Krüger, Heinz Handels, Jan Ehrhardt

Proceedings Volume 10949, 109491S (2019) https://doi.org/10.1117/12.2512988

KEYWORDS: Image registration, Medical imaging, Data modeling, Pathology, Bayesian inference, Neuroimaging, Brain, Image processing, Magnetic resonance imaging, Image fusion

Read Abstract +

Proceedings Article | 15 March 2019 Paper

A probabilistic approach for the registration of images with missing correspondences

Julia Krüger, Jan Ehrhardt, Sandra Schultz, Heinz Handels

Proceedings Volume 10949, 1094925 (2019) https://doi.org/10.1117/12.2511121

KEYWORDS: Image registration, Pathology, Expectation maximization algorithms, 3D image processing, Image segmentation, Medical imaging, Brain, Statistical modeling

Read Abstract +

Proceedings Article | 21 March 2016 Paper

Multi-level approach for statistical appearance models with probabilistic correspondences

Julia Krüger, Jan Ehrhardt, Heinz Handels

Proceedings Volume 9784, 978433 (2016) https://doi.org/10.1117/12.2214885

KEYWORDS: Analog electronics, Statistical modeling, Model-based design, Process modeling, Data modeling, Shape analysis, Image analysis, Probability theory, Optimization (mathematics), Image segmentation, Visualization, Mathematical modeling, Krypton, Medical imaging

Read Abstract +

Proceedings Article | 20 March 2015 Paper

Estimation of corresponding locations in ipsilateral mammograms: a comparison of different methods

Matthias Wilms, Julia Krüger, Mirko Marx, Jan Ehrhardt, Arpad Bischof, Heinz Handels

Proceedings Volume 9414, 94142B (2015) https://doi.org/10.1117/12.2081862

KEYWORDS: Breast, Mammography, Nipple, Chest, 3D modeling, Image compression, Data modeling, Breast cancer, Computer aided diagnosis and therapy, Tissues

Read Abstract +

Proceedings Article | 21 March 2014 Paper

Statistical shape and appearance models without one-to-one correspondences

Jan Ehrhardt, Julia Krüger, Heinz Handels

Proceedings Volume 9034, 90340U (2014) https://doi.org/10.1117/12.2043531

KEYWORDS: Image segmentation, Data modeling, Statistical modeling, Process modeling, Lung, Visual process modeling, Shape analysis, Image registration, Expectation maximization algorithms, Optimization (mathematics)

Read Abstract +

Proceedings Article | 13 March 2013 Paper

Breast compression simulation using ICP-based B-spline deformation for correspondence analysis in mammography and MRI datasets

Julia Krüger, Jan Ehrhardt, Arpad Bischof, Heinz Handels

Proceedings Volume 8669, 86691D (2013) https://doi.org/10.1117/12.2006356

KEYWORDS: Breast, Magnetic resonance imaging, Mammography, 3D image processing, Image registration, Tissues, 3D acquisition, Image segmentation, Computer simulations, Image compression

Read Abstract +

Proceedings Article | 14 February 2012 Paper

Automatic correspondence detection in mammogram and breast tomosynthesis images

Jan Ehrhardt, Julia Krüger, Arpad Bischof, Jörg Barkhausen, Heinz Handels

Proceedings Volume 8314, 831421 (2012) https://doi.org/10.1117/12.911305

KEYWORDS: Mammography, Breast, 3D image processing, Image registration, Digital mammography, Acquisition tracking and pointing, Tomography, Tissues, Image acquisition, 3D image reconstruction

Read Abstract +

Two-dimensional mammography is the major imaging modality in breast cancer detection. A disadvantage of mammography is the projective nature of this imaging technique. Tomosynthesis is an attractive modality with the potential to combine the high contrast and high resolution of digital mammography with the advantages of 3D imaging. In order to facilitate diagnostics and treatment in the current clinical work-flow, correspondences between tomosynthesis images and previous mammographic exams of the same women have to be determined. In this paper, we propose a method to detect correspondences in 2D mammograms and 3D tomosynthesis images automatically. In general, this 2D/3D correspondence problem is ill-posed, because a point in the 2D mammogram corresponds to a line in the 3D tomosynthesis image. The goal of our method is to detect the "most probable" 3D position in the tomosynthesis images corresponding to a selected point in the 2D mammogram. We present two alternative approaches to solve this 2D/3D correspondence problem: a 2D/3D registration method and a 2D/2D mapping between mammogram and tomosynthesis projection images with a following back projection. The advantages and limitations of both approaches are discussed and the performance of the methods is evaluated qualitatively and quantitatively using a software phantom and clinical breast image data. Although the proposed 2D/3D registration method can compensate for moderate breast deformations caused by different breast compressions, this approach is not suitable for clinical tomosynthesis data due to the limited resolution and blurring effects perpendicular to the direction of projection. The quantitative results show that the proposed 2D/2D mapping method is capable of detecting corresponding positions in mammograms and tomosynthesis images automatically for 61 out of 65 landmarks. The proposed method can facilitate diagnosis, visual inspection and comparison of 2D mammograms and 3D tomosynthesis images for the physician.

Showing 5 of 10 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years