Prof. Julia A. Schnabel Profile

Prof. Julia A. Schnabel

Univ. Lecturer (Medical Imaging) at Technische Univ München

SPIE Involvement:

Author

Publications (18)

Proceedings Article | 2 April 2024 Poster + Paper

Learning physics-inspired regularization for medical image registration with hypernetworks

Anna Reithmeir, Julia Schnabel, Veronika Zimmer

Proceedings Volume 12926, 129262K (2024) https://doi.org/10.1117/12.3006539

KEYWORDS: Elasticity, Image registration, Machine learning, Medical imaging, Materials properties, Lung

Read Abstract +

Medical image registration aims to identify the spatial deformation between images of the same anatomical region and is fundamental to image-based diagnostics and therapy. To date, the majority of the deep learning-based registration methods employ regularizers that enforce global spatial smoothness, e.g., the diffusion regularizer. However, such regularizers are not tailored to the data and might not be capable of reflecting the complex underlying deformation. In contrast, physics-inspired regularizers promote physically plausible deformations. One such regularizer is the linear elastic regularizer, which models the deformation of elastic material. These regularizers are driven by parameters that define the material’s physical properties. For biological tissue, a wide range of estimations of such parameters can be found in the literature, and it remains an open challenge to identify suitable parameter values for successful registration. To overcome this problem and to incorporate physical properties into learning-based registration, we propose to use a hypernetwork that learns the effect of the physical parameters of a physics-inspired regularizer on the resulting spatial deformation field. In particular, we adapt the HyperMorph framework to learn the effect of the two elasticity parameters of the linear elastic regularizer. Our approach enables the efficient discovery of suitable, data-specific physical parameters at test time. To the best of our knowledge, we are the first to use a hypernetwork to learn physics-inspired regularization for medical image registration. We evaluate our approach on 3D intrapatient lung CT images. The results show that the linear elastic regularizer can yield comparable results to the diffusion regularizer in unsupervised learning-based registration while predicting deformations with fewer foldings. With our method, the adaptation of the physical parameters to the data can successfully be performed at test time. Our code is available at https://github.com/annareithmeir/elastic-regularization-hypermorph.

SPIE Journal Paper | 4 April 2018 Open Access

GIFTed Demons: deformable image registration with local structure-preserving regularization using supervoxels for liver applications

Bartłomiej Papież, James Franklin, Mattias Heinrich, Fergus Gleeson, Michael Brady, Julia Schnabel

JMI, Vol. 5, Issue 02, 024001, (April 2018) https://doi.org/10.1117/12.10.1117/1.JMI.5.2.024001

KEYWORDS: Image filtering, Liver, Image registration, Lung, Gaussian filters, Computed tomography, Image segmentation, Motion estimation, Medical imaging, Diffusion

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 13 March 2018 Presentation + Paper

Regional lung ventilation estimation based on supervoxel tracking

Adam Szmul, Bartlomiej Papiez, Tahreema Matin, Fergus Gleeson, Julia Schnabel, Vicente Grau

Proceedings Volume 10576, 105761E (2018) https://doi.org/10.1117/12.2293833

KEYWORDS: Lung, Image registration, Image analysis, Radiotherapy, Visualization, Lung cancer, Computed tomography, Magnetic resonance imaging, Biomedical engineering, Cancer

Read Abstract +

Proceedings Article | 27 February 2018 Paper

Dense volumetric detection and segmentation of mediastinal lymph nodes in chest CT images

Hirohisa Oda, Holger Roth, Kanwal Bhatia, Masahiro Oda, Takayuki Kitasaka, Shingo Iwano, Hirotoshi Homma, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori, Julia Schnabel, Kensaku Mori

Proceedings Volume 10575, 1057502 (2018) https://doi.org/10.1117/12.2287066

KEYWORDS: Lymphatic system, Image segmentation, Chest, Computed tomography, Lung, Lung cancer, Arteries, 3D image processing, Target detection

Read Abstract +

SPIE Journal Paper | 9 November 2017 Open Access

Automated mediastinal lymph node detection from CT volumes based on intensity targeted radial structure tensor analysis

Hirohisa Oda, Kanwal K. Bhatia, Masahiro Oda, Takayuki Kitasaka, Shingo Iwano, Hirotoshi Homma, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori, Julia Schnabel, Kensaku Mori

JMI, Vol. 4, Issue 04, 044502, (November 2017) https://doi.org/10.1117/12.10.1117/1.JMI.4.4.044502

KEYWORDS: Lymphatic system, Target detection, Detection and tracking algorithms, Computed tomography, Optical spheres, Lung, Digital filtering, Image segmentation, Chest, Lung cancer

Read Abstract +

DOWNLOAD PAPER

SPIE Journal Paper | 4 October 2017

Supervoxels for graph cuts-based deformable image registration using guided image filtering

Adam Szmul, Bartlomiej Papież, Andre Hallack, Vicente Grau, Julia Schnabel

JEI, Vol. 26, Issue 06, 061607, (October 2017) https://doi.org/10.1117/12.10.1117/1.JEI.26.6.061607

KEYWORDS: Image registration, Image filtering, Lung, Roentgenium, Gaussian filters, 3D image processing, Computed tomography, Image segmentation, Image processing, Motion models

Read Abstract +

Proceedings Article | 3 March 2017 Presentation + Paper

Hessian-assisted supervoxel: structure-oriented voxel clustering and application to mediastinal lymph node detection from CT volumes

Hirohisa Oda, Kanwal Bhatia, Masahiro Oda, Takayuki Kitasaka, Shingo Iwano, Hirotoshi Homma, Hirotsugu Takabatake, Masaki Mori, Hiroshi Natori, Julia Schnabel, Kensaku Mori

Proceedings Volume 10134, 101341D (2017) https://doi.org/10.1117/12.2254782

KEYWORDS: Lymphatic system, Image segmentation, Feature extraction, Chest, Computer-aided diagnosis, Lung cancer, Lung, Image processing algorithms and systems, Blood vessels, Esophagus, Target detection, Information science, Computer aided diagnosis and therapy

Read Abstract +

Proceedings Article | 13 March 2013 Paper

pCT derived arterial input function for improved pharmacokinetic analysis of longitudinal dceMRI for colorectal cancer

Monica Enescu, Manav Bhushan, Esme Hill, Jamie Franklin, Ewan Anderson, Ricky Sharma, Julia Schnabel

Proceedings Volume 8669, 86690L (2013) https://doi.org/10.1117/12.2007036

KEYWORDS: Magnetic resonance imaging, Tissues, Modeling, Computed tomography, Cancer, Motion estimation, Image registration, Blood, Temporal resolution, Colorectal cancer

Read Abstract +

Proceedings Article | 14 February 2012 Paper

Joint estimation of subject motion and tracer kinetic parameters of dynamic PET data in an EM framework

Jieqing Jiao, Cristian Salinas, Graham Searle, Roger Gunn, Julia Schnabel

Proceedings Volume 8314, 83140A (2012) https://doi.org/10.1117/12.911497

KEYWORDS: Positron emission tomography, Image registration, Monte Carlo methods, Motion models, Data modeling, Head, Motion estimation, Motion measurement, Brain, Plasma

Read Abstract +

Proceedings Article | 9 March 2010 Paper

The reconstruction of microcalcification clusters in digital breast tomosynthesis

Candy P. Ho, Chris Tromans, Julia Schnabel, Sir Michael Brady

Proceedings Volume 7624, 76241E (2010) https://doi.org/10.1117/12.841205

KEYWORDS: Digital breast tomosynthesis, Breast, Detection and tracking algorithms, Sensors, Mammography, X-rays, Reconstruction algorithms, 3D image reconstruction, Image sensors, 3D image processing

Read Abstract +

Proceedings Article | 27 March 2009 Paper

Overlap invariance of cumulative residual entropy measures for multimodal image alignment

Nathan Cahill, Julia Schnabel, J. Alison Noble, David Hawkes

Proceedings Volume 7259, 72590I (2009) https://doi.org/10.1117/12.811585

KEYWORDS: Image registration, Computed tomography, Positron emission tomography, Magnetic resonance imaging, Medical imaging, Brain, Neuroimaging, Rigid registration, Image resolution, Image information entropy

Read Abstract +

Proceedings Article | 11 March 2008 Paper

Fusion of rat brain histology and MRI using weighted multi-image mutual information

Christoph Palm, Graeme Penney, William Crum, Julia Schnabel, Uwe Pietrzyk, David Hawkes

Proceedings Volume 6914, 69140M (2008) https://doi.org/10.1117/12.770605

KEYWORDS: Magnetic resonance imaging, Image registration, Brain, Image fusion, 3D image processing, In vitro testing, In vivo imaging, Spatial resolution, Medical imaging, Image resolution

Read Abstract +

Proceedings Article | 12 May 2004 Paper

Slice-to-volume registration using mutual information between probabilistic image classifications

Adam Chandler, Thomas Netsch, Chris Cocosco, Julia Schnabel, David Hawkes

Proceedings Volume 5370, (2004) https://doi.org/10.1117/12.534966

KEYWORDS: Image registration, Magnetic resonance imaging, 3D image processing, Brain, Image classification, Fuzzy logic, Image restoration, 3D acquisition, Medical imaging, Rigid registration

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Comparison of biomechanical breast models: a case study

Christine Tanner, Andreas Degenhard, Julia Schnabel, Andrew Castellano-Smith, Carmel Hayes, Luke Sonoda, Martin Leach, D. Hose, Derek Hill, David Hawkes

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467155

KEYWORDS: Breast, Tissues, Finite element methods, 3D modeling, Image registration, 3D image processing, Image compression, Magnetic resonance imaging, Natural surfaces, Skin

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Finite-element based validation of nonrigid registration using single- and multilevel free-form deformations: application to contrast-enhanced MR mammography

Julia Schnabel, Christine Tanner, Andrew Castellano-Smith, Andreas Degenhard, Carmel Hayes, Martin Leach, D. Hose, Derek Hill, David Hawkes

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467197

KEYWORDS: Image registration, Finite element methods, Tissues, Mammography, Breast, Computer simulations, Tumor growth modeling, 3D image processing, Chemical elements, Algorithm development

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Registration-based mesh construction technique for finite-element models of brains

Andrew Castellano-Smith, Thomas Hartkens, Julia Schnabel, D. Hose, Haiying Liu, Walter Hall, Charles Truwit, David Hawkes, Derek Hill

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467196

KEYWORDS: Brain, Finite element methods, Neuroimaging, Surgery, Image registration, Tissues, Magnetic resonance imaging, Chemical elements, Electrodes, Natural surfaces

Read Abstract +

Proceedings Article | 21 May 1999 Paper

Measurement of hippocampal volume changes in serial MRI scans

Julia Schnabel, Louis Lemieux, U. Wieshmann, Simon Arridge

Proceedings Volume 3661, (1999) https://doi.org/10.1117/12.348535

KEYWORDS: Epilepsy, Magnetic resonance imaging, Image registration, Image processing, Image segmentation, Brain, Optimization (mathematics), Neuroimaging, Tissues, Diffusion

Read Abstract +

Proceedings Article | 16 April 1996 Paper

Multiscale shape description of MR brain images using active contour models

Julia Schnabel, Simon Arridge

Proceedings Volume 2710, (1996) https://doi.org/10.1117/12.237962

KEYWORDS: Shape analysis, Image processing, Magnetic resonance imaging, Brain, Image segmentation, Neuroimaging, Fractal analysis, Optimization (mathematics), Data modeling, Image resolution

Read Abstract +