I am heading the laboratory for Artificial Intelligence in Medical Imaging. I have previously completed post-doctoral training at the Medical Vision Group in the Computer Science and Artificial Intelligence Lab at MIT and the Lab for Computational Neuroimaging, Department of Neurology at Harvard medical school. I received my PhD and Diploma from the Computer Science Department at TU München.
Tel: 089 4400 56900
Email: christian at ai-med dot de
Networks: Research Gate | LinkedIn | ORCID
Publications: Google Scholar | DBLP | arXiv
Code: GitHub
Demo: QuickNAT
Old websites: MIT | TUM
Publications
Gutiérrez-Becker, Benjamin; Gatidis, Sergios; Gutmann, Daniel; Peters, Annette; Schlett, Christopher; Bamberg, Fabian; Wachinger, Christian Deep Shape Analysis on Abdominal Organs for Diabetes Prediction Proceedings Article In: International Workshop on Shape in Medical Imaging, pp. 223–231, Springer 2018. @inproceedings{gutierrez2018deep, |
Roy, Abhijit Guha; Navab, Nassir; Wachinger, Christian Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks Journal Article In: IEEE Transactions on Medical Imaging, 2018. @article{se_tmi_agr2018, |
Gutierrez-Becker, Benjamin; Klein, Tassilo; Wachinger, Christian Deep Multi-Structural Shape Analysis: Application to Neuroanatomy Conference Forthcoming MICCAI 2018, Forthcoming. @conference{Gutierrez-Becker2018, Shape representations are a powerful tool in medical image analysis for its ability to quantify morphological differences. Current approaches are mostly based on hand-engineered representations which are potentially not optimal for specific tasks. In this work we propose the use of a neural network operating directly on point cloud representations to perform shape analysis. Our method is able to perform a joint shape analysis of different structures and since it operates directly on raw point cloud representations does not require feature engineering, image registration, mesh calculations or point correspondences. We showcase the advantages of our method by performing prediction based on the analysis of shape of different brain subcortical structures to perform Alzheimer's disease and Mild Cognitive Impairment classification as well as age regression. |
Roy, Abhijit Guha; Navab, Nassir; Wachinger, Christian Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks Conference Forthcoming Accepted at MICCAI 2018, Forthcoming. @conference{spatial_SE_roy_2018, Fully convolutional neural networks (F-CNNs) have set the state-of-the-art in image segmentation for a plethora of applications. Architectural innovations within F-CNNs have mainly focused on improving spatial encoding or network connectivity to aid gradient flow. In this paper, we explore an alternate direction of recalibrating the feature maps adaptively, to boost meaningful features, while suppressing weak ones. We draw inspiration from the recently proposed squeeze & excitation (SE) module for channel recalibration of feature maps for image classification. Towards this end, we introduce three variants of SE modules for image segmentation, (i) squeezing spatially and exciting channel-wise (cSE), (ii) squeezing channel-wise and exciting spatially (sSE) and (iii) concurrent spatial and channel squeeze & excitation (scSE). We effectively incorporate these SE modules within three different state-of-theart F-CNNs (DenseNet, SD-Net, U-Net) and observe consistent improvement of performance across all architectures, while minimally effecting model complexity. Evaluations are performed on two challenging applications: whole brain segmentation on MRI scans (Multi-Atlas Labelling Challenge Dataset) and organ segmentation on whole body contrast enhanced CT scans (Visceral Dataset). |
Roy, Abhijit Guha; Conjeti, Sailesh; Navab, Nassir; Wachinger, Christian Inherent Brain Segmentation Quality Control from Fully ConvNet Monte Carlo Sampling Conference Forthcoming Accepted at MICCAI 2018, Forthcoming. @conference{qc_brainseg_roy_208, We introduce inherent measures for effective quality control of brain segmentation based on a Bayesian fully convolutional neural network, using model uncertainty. Monte Carlo samples from the posterior distribution are efficiently generated using dropout at test time. Based on these samples, we introduce next to a voxel-wise uncertainty map also three metrics for structure-wise uncertainty. We then incorporate these structure-wise uncertainty in group analyses as a measure of confidence in the observation. Our results show that the metrics are highly correlated to segmentation accuracy and therefore present an inherent measure of segmentation quality. Furthermore, group analysis with uncertainty results in effect sizes closer to that of manual annotations. The introduced uncertainty metrics can not only be very useful in translation to clinical practice but also provide automated quality control and group analyses in processing large data repositories. |
Wachinger, Christian; Nho, Kwangsik; Saykin, Andrew J; Reuter, Martin; Rieckmann, Anna A Longitudinal Imaging Genetics Study of Neuroanatomical Asymmetry in Alzheimer’s Disease Journal Article In: Biological Psychiatry, 2018. @article{wachinger2018longitudinal, |
Gutierrez-Becker, Benjamin; Klein, Tassilo; Wachinger, Christian Gaussian process uncertainty in age estimation as a measure of brain abnormality Journal Article In: NeuroImage, 2018. @article{becker2018gaussian, Multivariate regression models for age estimation are a powerful tool for assessing abnormal brain morphology associated to neuropathology. Age prediction models are built on cohorts of healthy subjects and are built to reflect normal aging patterns. The application of these multivariate models to diseased subjects usually results in high prediction errors, under the hypothesis that neuropathology presents a similar degenerative pattern as that of accelerated aging. In this work, we propose an alternative to the idea that pathology follows a similar trajectory than normal aging. Instead, we propose the use of metrics which measure deviations from the mean aging trajectory. We propose to measure these deviations using two different metrics: uncertainty in a Gaussian process regression model and a newly proposed age weighted uncertainty measure. Consequently, our approach assumes that pathologic brain patterns are different to those of normal aging. We present results for subjects with autism, mild cognitive impairment and Alzheimer's disease to highlight the versatility of the approach to different diseases and age ranges. We evaluate volume, thickness, and VBM features for quantifying brain morphology. Our evaluations are performed on a large number of images obtained from a variety of publicly available neuroimaging databases. Across all features, our uncertainty based measurements yield a better separation between diseased subjects and healthy individuals than the prediction error. Finally, we illustrate differences in the disease pattern to normal aging, supporting the application of uncertainty as a measure of neuropathology. |
Roy, Abhijit Guha; Conjeti, Sailesh; Navab, Nassir; Wachinger, Christian Fast MRI Whole Brain Segmentation with Fully Convolutional Neural Networks Book Section In: Bildverarbeitung für die Medizin 2018, pp. 42–42, Springer, 2018. @incollection{roy2018fast, |
Gutierrez-Becker, Benjamin; Peter, Loic; Klein, Tassilo; Wachinger, Christian A Multi-Armed Bandit to Smartly Select a Training Set from Big Medical Data Conference Proceedings of MICCAI 2017, Elsevier, 2017. @conference{gutierrez2017bandits, With the availability of big medical image data, the selection of an adequate training set is becoming more important to address the heterogeneity of different datasets. Simply including all the data does not only incur high processing costs but can even harm the prediction. We formulate the smart and efficient selection of a training dataset from big medical image data as a multi-armed bandit problem, solved by Thompson sampling. Our method assumes that image features are not available at the time of the selection of the samples, and therefore relies only on meta information associated with the images. Our strategy simultaneously exploits data sources with high chances of yielding useful samples and explores new data regions. For our evaluation, we focus on the application of estimating the age from a brain MRI. Our results on 7,250 subjects from 10 datasets show that our approach leads to higher accuracy while only requiring a fraction of the training data. |
Reuter, Martin; Wachinger, Christian Abtract: Shape Analysis in Human Brain MRI Book Section In: Bildverarbeitung für die Medizin 2017, pp. 358–358, Springer Vieweg, Berlin, Heidelberg, 2017. @incollection{reuter2017abtract, |
Wachinger, Christian; Reuter, Martin; Klein, Tassilo DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy Journal Article In: NeuroImage, 2017. @article{wachinger2017deepnat, |
Guha Roy, Abhijit; Conjeti, Sailesh; Karri, Sri Phani Krishna; Sheet, Debdoot; Katouzian, Amin; Wachinger, Christian; Navab, Nassir ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network Journal Article In: Accepted at Biomedical Optics Express, 2017. @article{roy2017relaynet, |
Guha Roy, Abhijit; Conjeti, Sailesh; Sheet, Debdoot; Katouzian, Amin; Navab, Nassir; Wachinger, Christian Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data Journal Article In: Accepted at MICCAI 2017, 2017. @article{roy2017error, |
Wachinger, Christian; Rieckmann, Anna; Reuter, Martin Latent Processes Governing Neuroanatomical Change in Aging and Dementia Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer 2017. @inproceedings{wachinger2017latent, |
Wachinger, Christian; Volkmer, Susanne; Bublath, Katharina; Bruder, Jennifer; Bartling, Jürgen; Schulte-Körne, Gerd Does the late positive component reflect successful reading acquisition? A longitudinal ERP study Journal Article In: NeuroImage: Clinical, 2017. @article{wachinger2017does, |
Wachinger, Christian; Reuter, Martin Domain adaptation for Alzheimer's disease diagnostics Journal Article In: NeuroImage, 2016. @article{wachinger2016domain, |
Wachinger, C; Brennan, M; Sharp, G; Golland, P Efficient Descriptor-Based Segmentation of Parotid Glands with Non-Local Means. Journal Article In: IEEE transactions on bio-medical engineering, 2016. @article{wachinger2016efficient, |
Wachinger, Christian; Salat, David H; Weiner, Michael; Reuter, Martin; Initiative, Alzheimer’s Disease Neuroimaging; others, Whole-brain analysis reveals increased neuroanatomical asymmetries in dementia for hippocampus and amygdala Journal Article In: Brain, vol. 139, no. 12, pp. 3253–3266, 2016. @article{wachinger2016whole, |
Reuter, Martin; Wachinger, Christian; Lombaert, Herv'e Spectral and Shape Analysis in Medical Imaging: First International Workshop, SeSAMI 2016, Held in Conjunction with MICCAI 2016, Athens, Greece, October 21, 2016, Revised Selected Papers Miscellaneous 2016. @misc{reuter2016spectral, |
Wachinger, Christian; Golland, Polina; Magnain, Caroline; Fischl, Bruce; Reuter, Martin Multi-modal robust inverse-consistent linear registration Journal Article In: Human brain mapping, vol. 36, no. 4, pp. 1365–1380, 2015. @article{wachinger2015multi, |
Wachinger, Christian; Golland, Polina; Kremen, William; Fischl, Bruce; Reuter, Martin; Initiative, Alzheimer's Disease Neuroimaging; others, BrainPrint: A discriminative characterization of brain morphology Journal Article In: NeuroImage, vol. 109, pp. 232–248, 2015. @article{wachinger2015brainprint, |
Wachinger, Christian; Golland, Polina Diverse Landmark Sampling from Determinantal Point Processes for Scalable Manifold Learning Journal Article In: arXiv preprint arXiv:1503.03506, 2015. @article{wachinger2015diverse, |
Toews, Matthew; Wachinger, Christian; Estepar, Raul San Jose; Wells III, William M A Feature-based Approach to Big Data Analysis of Medical Images Proceedings Article In: International Conference on Information Processing in Medical Imaging, pp. 339–350, Springer International Publishing 2015. @inproceedings{toews2015feature, |
Wachinger, Christian; Golland, Polina Sampling from determinantal point processes for scalable manifold learning Journal Article In: Information Processing in Medical Imaging. Lecture Notes in Computer Science, Springer, pp. 687–698, 2015. @article{wachinger2015sampling, |
Wachinger, C; Toews, M; Langs, G; Wells, W; Golland, P Keypoint Transfer Segmentation Proceedings Article In: Information Processing in Medical Imaging, Springer 2015. @inproceedings{wachinger2015keypoint, |
Wachinger, Christian; Fritscher, Karl; Sharp, Greg; Golland, Polina Countour-Driven Atlas-Based Segmenation Journal Article In: Transactions on medical imaging, 2015. @article{wachinger2015countour, |
Magnain, Caroline; Augustinack, Jean C; Reuter, Martin; Wachinger, Christian; Frosch, Matthew P; Ragan, Timothy; Akkin, Taner; Wedeen, Van J; Boas, David A; Fischl, Bruce Blockface histology with optical coherence tomography: A comparison with Nissl staining Journal Article In: NeuroImage, vol. 84, pp. 524–533, 2014. @article{magnain2014blockface, |
Wachinger, Christian; Golland, Polina Atlas-based under-segmentation Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 315–322, Springer International Publishing 2014. @inproceedings{wachinger2014atlas, |
Wachinger, Christian; Golland, Polina; Reuter, Martin BrainPrint: identifying subjects by their brain Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 41–48, Springer International Publishing 2014. @inproceedings{wachinger2014brainprint, |
Wachinger, C; Batmanghelich, K; Golland, P; Reuter, M BrainPrint in the Computer-Aided Diagnosis of Alzheimer’s Disease Proceedings Article In: Proc MICCAI Workshop Challenge on Computer-Aided Diagnosis of Dementia Based on Structural MRI Data, pp. 129–138, 2014. @inproceedings{wachinger2014brainprintb, |
Wachinger, Christian; Brennan, Matthew; Sharp, Greg C; Golland, Polina On the importance of location and features for the patch-based segmentation of parotid glands Proceedings Article In: MICCAI Workshop on Image-Guided Adaptive Radiation Therapy, 2014. @inproceedings{wachinger2014importance, |
Wachinger, C; Batmanghelich, K; Golland, P; Reuter, M BrainPrint in the computer-aided diagnosis of Alzheimer’s disease Proceedings Article In: Proc MICCAI workshop challenge on computer-aided diagnosis of dementia based on structural MRI data, pp. 129–138, 2014. @inproceedings{wachinger2014brainprintb, |
Wachinger, Christian; Navab, Nassir Simultaneous registration of multiple images: similarity metrics and efficient optimization Journal Article In: Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 35, no. 5, pp. 1221–1233, 2013. @article{wachinger2013simultaneous, |
Chen, George H; Wachinger, Christian; Golland, Polina Sparse projections of medical images onto manifolds Proceedings Article In: International Conference on Information Processing in Medical Imaging, pp. 292–303, Springer Berlin Heidelberg 2013. @inproceedings{chen2013sparse, |
Wachinger, Christian; Sharp, Gregory C; Golland, Polina Contour-driven regression for label inference in atlas-based segmentation Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 211–218, Springer Berlin Heidelberg 2013. @inproceedings{wachinger2013contour, |
Wachinger, Christian; Golland, Polina; Fischl, Bruce; Reuter, Martin Robust registration of multi-modal images Journal Article In: Human Brain Mapping, 2013. @article{wachinger2013robust, |
Wachinger, Christian; Navab, Nassir Entropy and Laplacian images: Structural representations for multi-modal registration Journal Article In: Medical Image Analysis, vol. 16, no. 1, pp. 1–17, 2012. @article{wachinger2012entropy, |
Mateus, Diana; Wachinger, Christian; Atasoy, Selen; Schwarz, Loren; Navab, Nassir Learning manifolds: design analysis for medical applications Journal Article In: Machine Learning in Computer-Aided Diagnosis: Medical Imaging Intelligence and Analysis: Medical Imaging Intelligence and Analysis, pp. 374, 2012. @article{mateus2012learning, |
Wachinger, Christian; Klein, Tassilo; Navab, Nassir The 2D analytic signal for envelope detection and feature extraction on ultrasound images Journal Article In: Medical Image Analysis, vol. 16, no. 6, pp. 1073–1084, 2012. @article{wachinger20122d, |
Wachinger, Christian; Klein, Tassilo; Navab, Nassir Locally adaptive Nakagami-based ultrasound similarity measures Journal Article In: Ultrasonics, vol. 52, no. 4, pp. 547–554, 2012. @article{wachinger2012locally, |
Wachinger, Christian; Yigitsoy, Mehmet; Rijkhorst, Erik-Jan; Navab, Nassir Manifold learning for image-based breathing gating in ultrasound and MRI Journal Article In: Medical Image Analysis, vol. 16, no. 4, pp. 806–818, 2012. @article{wachinger2012manifold, |
Wachinger, Christian; Navab, Nassir A contextual maximum likelihood framework for modeling image registration Proceedings Article In: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 1995–2002, IEEE 2012. @inproceedings{wachinger2012contextual, |
Wachinger, Christian; Golland, Polina Spectral label fusion Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 410–417, Springer Berlin Heidelberg 2012. @inproceedings{wachinger2012spectral, |
Moradi, Mehdi; Wachinger, Christian; Fedorov, Andriy; Wells, William M; Kapur, Tina; Wolfsberger, Luciant D; Nguyen, Paul; Tempany, Clare M MRI confirmed prostate tissue classification with Laplacian eigenmaps of ultrasound RF spectra Proceedings Article In: International Workshop on Machine Learning in Medical Imaging, pp. 19–26, Springer Berlin Heidelberg 2012. @inproceedings{moradi2012mri, |
Yigitsoy, Mehmet; Wachinger, Christian; Navab, Nassir Temporal groupwise registration for motion modeling Proceedings Article In: Biennial International Conference on Information Processing in Medical Imaging, pp. 648–659, Springer Berlin Heidelberg 2011. @inproceedings{yigitsoy2011temporal, |
Yigitsoy, Mehmet; Wachinger, Christian; Navab, Nassir Manifold learning for image-based breathing gating in MRI Proceedings Article In: Proceedings of SPIE, pp. 796210, 2011. @inproceedings{yigitsoy2011manifold, |
Demirci, Stefanie; Bigdelou, Ali; Wang, Lejing; Wachinger, Christian; Baust, Maximilian; Tibrewal, Radhika; Ghotbi, Reza; Eckstein, Hans-Henning; Navab, Nassir 3D stent recovery from one x-ray projection Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 178–185, Springer Berlin Heidelberg 2011. @inproceedings{demirci20113d, |
Wachinger, Christian Ultrasound Mosaicing and Motion Modeling: Applications in Medical Image Registration PhD Thesis München, Technische Universität München, Diss., 2011, 2011. @phdthesis{wachinger2011ultrasound, |
Wachinger, Christian; Yigitsoy, Mehmet; Navab, Nassir Manifold learning for image-based breathing gating with application to 4D ultrasound Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 26–33, Springer Berlin Heidelberg 2010. @inproceedings{wachinger2010manifold, |
Wachinger, Christian; Mateus, Diana; Keil, Andreas; Navab, Nassir Manifold learning for patient position detection in MRI Proceedings Article In: 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1353–1356, IEEE 2010. @inproceedings{wachinger2010manifoldb, |
You must be logged in to post a comment.