Research

BrainPrint

BrainPrint is a compact and discriminative representation of brain morphology. BrainPrint captures shape information of an ensemble of cortical and subcortical structures by solving the eigenvalue problem of the 2D and 3D Laplace-Beltrami operator on triangular and tetrahedral meshes. This discriminative characterization permits new ways of studying the similarity between brains; the focus can either be set on a specific brain structure of interest or on the overall brain similarity.


Brain-Zebras: Eigenfunctions of the Laplace Beltrami operator visualized on inflated cortical surface.
Selected Papers
C. Wachinger, P. Golland, W. Kremen, B. Fischl, M. Reuter,
BrainPrint: A Discriminative Characterization of Brain Morphology,
NeuroImage, Volume 109, Pages 232-248, 2015 (Cover).

C. Wachinger, K. Batmanghelich, P. Golland, M. Reuter,
BrainPrint in the Computer-Aided Diagnosis of Alzheimer's Disease (Presentation),
Challenge on Computer-Aided Diagnosis of Dementia, MICCAI, 2014.
Second prize in classification challenge.

C. Wachinger, P. Golland, M. Reuter, W. Wells,
Gaussian Process Interpolation for Uncertainty Estimation in Image Registration (Presentation),
Medical Image Computing and Computer Assisted Intervention (MICCAI), 2014.

Spectral Analysis and Clustering

The spectral decomposition of kernel matrices is required for many methods in clustering and manifold learning. My work shows the potential of such techniques in medical imaging, including segmentation, respiratory gating, registration, and position detection.
Selected Papers
C. Wachinger, P. Golland,
Spectral Label Fusion,
MICCAI, Nice, 2012

C. Wachinger, M. Yigitsoy, E. Rijkhorst, N. Navab,
Manifold Learning for Image-Based Breathing Gating in Ultrasound and MRI,
Medical Image Analysis, Volume 16, Issue 4, May 2012, Pages 806-818.

C. Wachinger, M. Yigitsoy, N. Navab,
Manifold Learning for Image-Based Breathing Gating with Application to 4D Ultrasound,
Medical Image Computing and Computer Assisted Intervention (MICCAI), vol. 2, pp. 26-33, 2010.

C. Wachinger, N. Navab,
Manifold Learning for Multi-Modal Image Registration,
21st British Machine Vision Conference (BMVC), pp. 82.1-82.12, 2010.

C. Wachinger, D. Mateus, A. Keil, N. Navab,
Manifold Learning for Patient Position Detection in MRI,
IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1353 - 1356, 2010.

Image Registration: Probabilistic Modeling with Latent Layers

Probabilistic models present a mathematical framework to describe image registration. In contrast to existing approaches, I try to incorporate local context information, which provide a more reliable description of images than single pixels. The introduction of layers of latent random variables into the graphical model helps to clearly arrange relationships. These layers form representations of the original images, where we proposed structural representations for multi-modal registration.
Selected Papers
C. Wachinger, N. Navab,
A Contextual Maximum Likelihood Framework for Modeling Image Registration,
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island (USA), June 2012.

C. Wachinger, N. Navab,
Entropy and Laplacian Images: Structural Representations for Multi-Modal Registration,
Medical Image Analysis, Volume 16, Issue 1, January 2012, Pages 1-17.

C. Wachinger, N. Navab,
Manifold Learning for Multi-Modal Image Registration,
21st British Machine Vision Conference (BMVC), pp. 82.1-82.12, 2010.

C. Wachinger, N. Navab,
Structural Image Representation for Image Registration,
IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA), pp. 23-30, 2010.

Simultaneous Registration

Atlas construction, longitudinal studies, and ultrasound mosaicing are examples for applications where not only two but a group of images has to be registered. In my work on simultaneous registration, we move all images at the same time without the previous selection of a template image. Contributions mainly concern similarity measures and optimization strategies, with extensions to 4D motion modeling.
Selected Papers
C. Wachinger, N. Navab,
Simultaneous Registration of Multiple Images: Similarity Metrics and Efficient Optimization,
IEEE Transactions on Pattern Analysis and Maschine Intelligence (TPAMI)

M. Yigitsoy, C. Wachinger, N. Navab,
Temporal Groupwise Registration for Motion Modeling,
Information Processing in Medical Imaging (IPMI), July 3-8 2011.

C. Wachinger, N. Navab,
Similarity Metrics and Efficient Optimization for Simultaneous Registration,
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-786, 2009.

C. Wachinger, B. Glocker, J. Zeltner, N. Paragios, N. Komodakis, M. S. Hansen, N. Navab,
Deformable Mosaicing for Whole-Body MRI,
Medical Image Computing and Computer Assisted Intervention (MICCAI), vol. 2, pp. 113-121, 2008.

C. Wachinger, W. Wein, N. Navab,
Three-Dimensional Ultrasound Mosaicing,
Medical Image Computing and Computer Assisted Intervention (MICCAI), vol. 2, pp. 327-335, 2007.

Ultrasound Imaging

My work on ultrasound imaging focused on multi-view ultrasound and the conversion from radio frequency (RF) to B-mode images. For multi-view ultrasound or ultrasound mosaicing, we worked on the correct automatic alignment and reconstruction of images, including research in ultrasound specific similarity measures, optimization strategies, and simultaneous registration. For the RF to B-mode conversion, we integrated a 2D envelope detection and Nakagami noise models for the validation.
Selected Papers
C. Wachinger, N. Navab,
Simultaneous Registration of Multiple Images: Similarity Metrics and Efficient Optimization,
IEEE Transactions on Pattern Analysis and Maschine Intelligence (TPAMI)

C. Wachinger, T. Klein, N. Navab,
The 2D Analytic Signal for Envelope Detection and Feature Extraction on Ultrasound Images,
Medical Image Analysis, Volume 16, Issue 6, August 2012, Pages 1073-1084, 10.1016/j.media.2012.05.001.

C. Wachinger, T. Klein, N. Navab,
Locally adaptive Nakagami-based ultrasound similarity measures,
Ultrasonics, Volume 52, Issue 4, April 2012, Pages 547-554.

C. Wachinger, T. Klein, N. Navab,
The 2D Analytic Signal on RF and B-mode Ultrasound Images,
Information Processing in Medical Imaging (IPMI), July 3-8 2011.

C. Wachinger, N. Navab,
Alignment of Viewing-Angle Dependent Ultrasound Images,
Medical Image Computing and Computer Assisted Intervention (MICCAI), vol. 1, pp. 667-674, 2009.

C. Wachinger, N. Navab,
Similarity Metrics and Efficient Optimization for Simultaneous Registration,
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-786, 2009.

C. Wachinger, R. Shams, N. Navab,
Estimation of Acoustic Impedance from Multiple Ultrasound Images with Application to Spatial Compounding,
IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA), pp. 1-8, 2008.

C. Wachinger, N. Navab,
Ultrasound Specific Similarity Measures for Three-Dimensional Mosaicing,
SPIE Medical Imaging, pp. 69140F.1-69140F.9, 2008.

C. Wachinger, W. Wein, N. Navab,
Three-Dimensional Ultrasound Mosaicing,
Medical Image Computing and Computer Assisted Intervention (MICCAI), vol. 2, pp. 327-335, 2007.