Homepage of Hannes Nickisch

Hannes Nickisch After doing a PhD at the Max Planck Institute for Biological Cybernetics and a PostDoc at the Max Planck Institue for Intelligent Systems, I'm using machine learning for medical imaging applications as a Senior Scientist at Philips Research, Hamburg, Germany.

During my study times at the Technical University Berlin and the Université de Nantes I did internships with Microsoft Research in Cambridge, Siemens Corporate Research in Princeton and Siemens Medical Systems in Erlangen.

My research interests lie in probabilistic machine learning, computer vision and pattern recognition, medical image processing and predictive patient-specific biophysical models based on Gaussian processes and neural networks.

My work is listed below, on ResearchGate IconGoogle Scholar and ResearchGate IconResearchGate. In case you wish to collaborate or have questions related to my work, please contact me at contact.hannes@nickisch.org.


Code/Data

gpml

GP The Gaussian Process for Machine Learning toolbox.

gpml A library for Gaussian process regression and classification for Octave/Matlab containing a variety of approximate inference schemes ranging from Laplace's method over expectation propagation to variational Bayes. We furthermore support large scale approximate inference via the FITC approximation and MCMC sampling.
See the mloss.org project, the JMLR paper and the gpml page.


    cov = {@covSEiso}; sf = 1; ell = 0.4; hyp.cov = log([ell;sf]);
    lik = 'likLaplace'; sn = 0.2; hyp.lik = log(sn);
    mean = @meanZero;                   % set up GP (cov,lik,mean)
    nlZ = gp(hyp, 'infEP', mean, cov, lik, X, y);      % inference
      

AwA - Animals with Attributes

CV A dataset for Attribute-Based Classification.

gpml A dataset for benchmarking transfer-learning or zero-shot learning algorithms. The dataset contains 30475 images in 50 animal classes aligned with Osherson's well-known class/attribute matrix with 85 numerical attributes per class.
See the download website, the download website of the free successor dataset, the CVPR paper and the IEEE-TPAMI paper.


glm-ie

ML The Generalised Linear Models Inference and Estimation Toolbox.

glm-ie A library for large scale matrix vector multiplication (MVM) based computations in generalised linear models for Octave/Matlab. We support variational Bayes, factorial mean field and expectation propagation as well as MAP estimation using a wide range of penalised least squares solvers for sparse estimation. A dedicated matrix class provides computational primitives and a wide range of regularisers are supported.
See the mloss.org project, the JMLR paper and the glm-ie page.


    X = matConv2(f, su, 'circ');        % convolution matrix
    B = matFD2(su, 'circ');       % finite difference matrix
    pot = @potLaplace; s2 = 1e-4; tau = 15;
    [m,ga,b,z,nlZ] = dli(X,y,s2,B,pot,tau,opts); % inference
    pen = @(s) penAbs(s);                       % l1-penalty
    [u,phi]  = plsTN(u0,X,y,B,opt,s2,pen);      % estimation
      

gmm

GP Gaussian mixture modeling with Gaussian process latent variable models and others.

dgplvm The toolbox contains code for density estimation using mixtures of Gaussians. Starting from simple kernel density estimation using spherical and diagonal Gaussian kernels over manifold Parzen window until mixtures of penalised full Gaussians with only a few components, the toolbox covers many Gaussian mixture model parametrisation from the recent literature. Most prominently, the package contains code to use the Gaussian process latent variable model for density estimation.
See the mloss.org project and the corresponding DAGM paper or get the code here.


    [lp,lpte] = dkde(z,zte);      % diagonal kernel density estimation
    [lp,lpte] = mpar(z,zte,d,k);  % manifold Parzen windows
    [lp,lpte] = pgau(z,zte);      % penalised Gaussian
      

fwtn

The fast wavelet transformation for tensor data.

fwtn The code contains a standalone light-weight implementation of the orthonormal wavelet transform using quadrature mirror filters in C including a Matlab/MEX wrapper. We fully support D-dimensional data in L levels. The algorithm has a computational complexity linear in the size of the input.
See the mloss.org project or get the code here.


    qmf = [1,1]/sqrt(2); % Haar wavelet
    L   = 3;             % # levels in the pyramid
    W   = fwtn(X,L,qmf); % apply FWT, inverse: X = fwtn(W,L,qmf,1);
      

approxXX

GP A variety of approximate inference methods for Gaussian process prediction.

gpml The code comprises expectation propagation, Laplace's method, the informative vector machine, Gaussian variational mean field, factorial mean field, on-line expectation propagation, TAP and variational bounding. Note that is numerically much less robust than the code in gpml. The implementations are meant to illustrate the algorithms as such and not for use as a black box system in an applied setting. The functions use the gpml v2.0 Octave/Matlab interface.
See the corresponding JMLR paper or get the code here.


    hyp = [1; 1];       % ell,sig - GP parameters
    cov = {'covSEiso'}; % covariance function
    lik = 'cumGauss';   % logistic or cumGauss likelihood
    apx = 'LA';         % EP,FV,IVM,KL,LA,LR,OLEP,SO,TAP,TAPnaive or VB
    p = binaryGP(hyp, ['approx',apx], cov, lik, x, y, xt); % prediction
      

Recent Work

GP Scalable Log Determinants for Gaussian Process Kernel Learning [link] [poster] [code]
K. Dong, D. Eriksson, H. Nickisch, D. Bindel, A. Wilson, NIPS, 2017.

Med NN Deep-Learning-Based CT Motion Artifact Recognition in Coronary Arteries
T. Elss, H. Nickisch, T. Wissel, H. Schmitt, M. Vembar, M. Morlock, M. Grass, SPIE (oral), 2018.

Med NN Orientation Regression in Hand Radiographs: A Transfer Learning Approach
I. Baltruschat, A. Saalbach, M. Heinrich, H. Nickisch, S. Jockel, SPIE, 2018.

Med Nearest Neighbor 3D Segmentation with Context Features
E. Hristova, H. Schulz, T. Brosch, M. Heinrich, H. Nickisch, SPIE (oral), 2018.

Med Improved On-Site FFR-CT Accuracy by Coronary Tree Standardization [link, p.362]
H. Nickisch, M. Freiman, S. Prevrhal, M. Vembar, P. Donnelly, P. Maurovich-Horvat, L. Goshen, H. Schmitt, ECR (European Congress of Radiology), SS 1003, 2017.

GP Is Gun Violence Contagious? Descriptive Spatio-Temporal Testing and Modeling with Large-Scale Point Process [link]
C. Loeffler, S Flaxman, W. Herlands, H. Nickisch, JSM (Methods for Massive Spatial Data, Statistics and the Environment), 2016.

GP Thoughts on Massively Scalable Gaussian Processes [link]
A. G. Wilson, C. Dann and H. Nickisch, arXiv.org, 2015.


Papers

Journal Articles

12) Med Improving CCTA based lesions’ hemodynamic significance assessment by accounting for partial volume modeling in automatic coronary lumen segmentation [pdf]
M. Freiman, H. Nickisch, S. Prevrhal, H. Schmitt, M. Vembar, P. Maurovich-Horvat, P. Donnelly and L. Goshen, Medical Physics, 44(3):1040-1049, 2017.

11) Med Blind Multi-Rigid Retrospective Motion Correction of MR Images [pdf] [link]
A. Loktyushin, H. Nickisch, R. Pohmann and B. Schölkopf, Magnetic Resonance in Medicine, 73(4):1457-1468, 2015.

10) CV Attribute-Based Classification for Zero Shot Visual Object Categorization [pdf] [link]
C. Lampert, H. Nickisch and S. Harmeling, IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3):453-465, 2014.

9) Med Bio Generating Anatomical Models of the Heart and the Aorta from Medical Images for Personalized Physiological Simulations [pdf] [link]
J. Weese, A. Groth, H. Nickisch, H. Barschdorf, F.M. Weber, J. Velut, M. Castro, C. Toumoulin, J.L. Coatrieux, M. De Craene, G. Piella, C. Tobón-Gomez, A.F. Frangi, D.C. Barber, I. Valverde, Y. Shi, C. Staicu, A. Brown, P. Beerbaum and D.R. Hose, Medical and Biological Engineering and Computing, 51(11):1209-1219, 2013.

8) Med Blind Retrospective Motion Correction of MR Images [pdf] [link]
A. Loktyushin, H. Nickisch, R. Pohmann and B. Schölkopf, Magnetic Resonance in Medicine, 70(6):1608-1618, 2013.

7) CV User-centric Learning and Evaluation of Interactive Segmentation Systems [pdf] [link]
P. Kohli, H. Nickisch, C. Rother and C. Rhemann, International Journal of Computer Vision, 100(3):261-274, 2012.

6) ML Generating Feature Spaces for Linear Algorithms with Regularized Sparse Kernel Slow Feature Analysis [pdf] [link]
W. Böhmer, S. Grünewälder, H. Nickisch, K. Obermayer, Machine Learning, 89(1):67-86, 2012.

5) ML glm-ie: The Generalised Linear Models Inference and Estimation Toolbox [pdf] [link] [web]
H. Nickisch, Journal of Machine Learning Research, 13:1699-1703, 2012.

4) ML Large Scale Bayesian Inference and Experimental Design for Sparse Linear Models [pdf] [link]
M. W. Seeger and H. Nickisch, SIAM Journal on Imaging Sciences, 4(1):166-199, 2011.

3) GP Gaussian Processes for Machine Learning (GPML) Toolbox [pdf] [link] [web]
C. E. Rasmussen and H. Nickisch, Journal of Machine Learning Research, 11:3011-3015, 2010.

2) Med Optimization of k-Space Trajectories for Compressed Sensing by Bayesian Experimental Design [pdf] [link]
M. W. Seeger, H. Nickisch, R. Pohmann and B. Schölkopf, Magnetic Resonance in Medicine, 63(1):116-126, 2010.

1) GP Approximations for Binary Gaussian Process Classification [pdf] [link]
H. Nickisch and C. E. Rasmussen, Journal of Machine Learning Research, 9:2035-2078, 2008.

 

Peer-Reviewed Conference Papers

21) Med NN Deep-Learning-Based CT Motion Artifact Recognition in Coronary Arteries
T. Elss, H. Nickisch, T. Wissel, H. Schmitt, M. Vembar, M. Morlock, M. Grass, SPIE (oral), 2018.

20) Med NN Orientation Regression in Hand Radiographs: A Transfer Learning Approach
I. Baltruschata, A. Saalbach, M. Heinrich, H. Nickisch, S. Jockel, SPIE, 2018.

19) Med Nearest Neighbor 3D Segmentation with Context Features
E. Hristova, H. Schulz, T. Brosch, M. Heinrich, H. Nickisch, SPIE (oral), 2018.

18) GP Scalable Log Determinants for Gaussian Process Kernel Learning [link] [poster] [code]
K. Dong, D. Eriksson, H. Nickisch, D. Bindel, A. Wilson, NIPS, 2017.

17) Med Learning a sparse database for patch-based medical image segmentation [paper]
M. Freiman, H. Nickisch, H. Schmitt, P. Maurovich-Horvat, P. Donnelly, M. Vembar, L. Goshen, MICCAI PatchMI, 2017.

16) GP Scalable Gaussian Processes for Characterizing Multidimensional Change Surfaces [link] [paper] [poster] [slides]
W. Herlands, A. G. Wilson, H. Nickisch, S. Flaxman, D. Neill, W. van Panhuis, E. Xing, AISTATS, 2016.

15) Med Automatic coronary lumen segmentation with partial volume modeling improves hemodynamic significance assessment [pdf] [link]
[slides]
M. Freiman, Y. Lamash, G. Gilboa, H. Nickisch, S. Prevrhal, H. Schmitt, M. Vembar and L. Goshen, SPIE (oral), 2016.

14) Med SVM-based failure detection of GHT localizations [pdf] [link]
[slides]
T. Blaffert, C. Lorenz, H. Nickisch, J. Peters and J. Weese, SPIE (oral), 2016.

13) Med Bio Learning Patient-Specific Lumped Models for Interactive Coronary Blood Flow Simulations [pdf] [talk] [slides]
H. Nickisch, Y. Lamash, S. Prevrhal, M. Freiman, M. Vembar, L. Goshen and H. Schmitt, MICCAI (oral), 2015.

12) GP Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP) [pdf, supp] [slides] [link]
A. G. Wilson and H. Nickisch, ICML, 2015.

11) GP Fast Kronecker Inference in Gaussian Processes with non-Gaussian Likelihoods [pdf] [link]
S. Flaxman, A. G. Wilson, D. Neill, H. Nickisch, and A. Smola, ICML, 2015.

10) Med From Image to Personalized Cardiac Simulation: Encoding Anatomical Structures into a Model-Based Segmentation Framework [pdf] [link] [poster]
H. Nickisch, H. Barschdorf, F. M. Weber, M. W. Krueger, O. Dössel and J. Weese, MICCAI STACOM, 2012.

9) GP Additive Gaussian Processes [pdf] [link]
D. Duvenaud, H. Nickisch and C. E. Rasmussen, NIPS, 2011.

8) ML Regularized Sparse Kernel Slow Feature Analysis [pdf] [link]
W. Böhmer and S. Grünewälder, H. Nickisch and K. Obermayer, ECML/PKDD, 2011.

7) ML Fast Convergent Algorithms for Expectation Propagation Approximate Bayesian Inference [pdf] [link]
M. W. Seeger and H. Nickisch, AISTATS, 2011.

6) CV Learning an interactive segmentation system [pdf] [link]
H. Nickisch, C. Rother, C. Rhemann and Pushmeet Kohli, ICVGIP, 2010.
Best paper award.

5) GP Gaussian Mixture Modeling with Gaussian Process Latent Variable Models [pdf] [link]
H. Nickisch and C. E. Rasmussen, DAGM, 2010.

4) ML Convex variational Bayesian inference for large scale generalized linear models [pdf] [link]
H. Nickisch and M. W. Seeger, ICML, 2009.

3) CV Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer [pdf] [link]
C. H. Lampert, H. Nickisch and S. Harmeling, CVPR, 2009.

2) Med Bayesian Experimental Design of Magnetic Resonance Imaging Sequences [pdf] [link]
M. W. Seeger, H. Nickisch, R. Pohmann and B. Schölkopf, NIPS, 2008.

1) ML Compressed Sensing and Bayesian Experimental Design [pdf] [link]
M. W. Seeger and H. Nickisch, ICML, 2008.

 

Abstracts and Posters

7) GP Med Dual Compartment Regression for the Generation of Pseudo-CT Images
A. Schnurr, E. Orasanu, H. Schulz, H. Nickisch, S. Renisch, AAPM (American Association of Physicists in Medicine), SU-K-601, 2017.

6) Med Improved On-Site FFR-CT Accuracy by Coronary Tree Standardization [link, p.362]
H. Nickisch, M. Freiman, S. Prevrhal, M. Vembar, P. Donnelly, P. Maurovich-Horvat, L. Goshen, H. Schmitt, ECR (European Congress of Radiology), SS 1003, 2017.

5) GP Is Gun Violence Contagious? Descriptive Spatio-Temporal Testing and Modeling with Large-Scale Point Process [link]
C. Loeffler, S Flaxman, W. Herlands, H. Nickisch, JSM (Methods for Massive Spatial Data, Statistics and the Environment), 2016.

4) Med NN Can Pretrained Neural Networks Detect Anatomy? [link]
V. Menkovski, Z. Aleksovski, A. Saalbach, H. Nickisch, NIPS Workshop on Machine Learning in Healthcare, 2015.

3) Med FID-guided retrospective motion correction based on autofocusing
M. Babayeva, A. Loktyushin, T. Kober, C. Granziera, H. Nickisch, R. Gruetter, G. Krueger, ISMRM-ESMRMB, 2014.

2) Med Retrospective blind motion correction of MR images [pdf]
A. Loktyushin, H. Nickisch, R. Pohmann and B. Schölkopf, ISMRM, 2009.

1) Med Optimization of k-Space Trajectories by Bayesian Experimental Design [pdf]
M. W. Seeger, H. Nickisch, R. Pohmann and B. Schölkopf, ISMRM, 2009.

 

Technical Reports

4) GP Thoughts on Massively Scalable Gaussian Processes [link]
A. G. Wilson, C. Dann and H. Nickisch, arXiv.org, 2015.

3) GP Scalable Gaussian Processes for Characterizing Multidimensional Change Surfaces [link]
W. Herlands, A. Wilson, H. Nickisch, S. Flaxman, D. Neill, W. van Panhuis, E. Xing, arXiv.org, 2015.

2) GP Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP) [pdf] [link]
A. G. Wilson and H. Nickisch, arXiv.org, 2015.

1) GP Multiple Kernel Learning: A Unifying Probabilistic Viewpoint [pdf] [link]
H. Nickisch and M. W. Seeger, arXiv.org, 2011.

 

Patents

12) Med SEGMENTATION APPARATUS FOR INTERACTIVELY SEGMENTING BLOOD VESSELS IN ANGIOGRAPHIC IMAGE DATA [link]
S. Prevrhal, H. Nickisch, H. Schmitt, US9842401 (B2), 2017-12-12.

11) Med PROCESSING APPARATUS FOR PROCESSING CARDIAC DATA [link]
H. Schmitt, H. Nickisch, S. Prevrhal, US9788807 (B2), 2017-10-17.

10) Med PROCESSING APPARATUS AND METHOD FOR PROCESSING CARDIAC DATA OF A LIVING BEING [link]
H. Schmitt, S. Prevrhal, H. Nickisch, US2017245824 (A1), 2017-08-31.

9) Med HEART MODEL GUIDED CORONARY ARTERY SEGMENTATION [link]
C. Lorenz, T. Klinder, H. Schmitt, H. Nickisch, WO2017109662 (A1), 2017-06-29.

8) Med CT PERFUSION PROTOCOL TARGETING [link]
S. Prevrhal, H. Schmitt, H. Nickisch, WO2017108779 (A1), 2017-06-29.

7) Med APPARATUS FOR DETERMINING A FRACTIONAL FLOW RESERVE VALUE [link]
M. Grass, Y. Lamash, L. Goshen, H. Schmitt, M. Freiman, H. Nickisch, S. Prevrhal, US20170105694 (A1), 2017-05-10.

6) Med MOBILE FFR SIMULATION [link]
H. Schmitt, C. Haase, H. Nickisch, S. Prevrhal, WO2017060106 (A1), 2017-04-13.

5) Med MODEL-BASED SEGMENTATION OF AN ANATOMICAL STRUCTURE [link] [link]
A. Groth, H. Nickisch, F. Weber, J. Weese, H. Barschdorf, EP3080777 (B1), US2016379372 (A1), 2016-12-29.

4) Med LOCAL FFR ESTIMATION AND VISUALISATION FOR IMPROVED FUNCTIONAL STENOSIS ANALYSIS [link]
H. Nickisch, M. Grass, H. Schmitt, J. Timmer, US2016302750 (A1), 2016-10-20.

3) Med PROCESSING APPARATUS FOR PROCESSING CARDIAC DATA [link]
H. Schmitt, H. Nickisch, S. Prevrhal, US2016206265 (A1), 2016-07-21.

2) Med FRACTIONAL FLOW RESERVE DETERMINATION [link]
H. Homann, M. Grass, R. Florent, H. Schmitt, O. Bonnefous, H. Nickisch, WO2016087396 (A1), 2016-06-09.

1) Med METHOD OF DETERMINING THE BLOOD FLOW THROUGH CORONARY ARTERIES [link]
M. Grass, H.Schmitt, H. Nickisch, US2015297161 (A1), 2015-10-22.

 

Diploma and PhD Theses

2) GP ML Bayesian Inference and Experimental Design for Large Generalised Linear Models [pdf] [link]
H. Nickisch, PhD Thesis, Technische Universität Berlin, Berlin, Germany, 2010.

1) ML Extraction of visual features from natural video data using Slow Feature Analysis [pdf]
H. Nickisch, Diploma Thesis, Technische Universität Berlin, Berlin, Germany, 2006.


Students/Reviewing

Students (co-)supervised

4) Med 3D Medical Image Segmentation with Vantage Point Forests and Binary Context Features
Evelin Hristova, Master Thesis, Hamburg University of Applied Sciences, Hamburg, Germany, 2017.

3) Med NN Deep Learning for Advanced Medical Applications [link]
Ivo Baltruschat, Master Thesis, Universität zu Lübeck, Lübeck, Germany, 2016.

2) Med Blind Retrospective Motion Correction of MR Images [link] [pdf]
Alexander Loktyushin, PhD Thesis, University of Tübingen, Tübingen, Germany, 2015.

1) Med Model Generation for Automatic Myocardium Segmentation.
Jan Wingerter, Diploma Thesis, Karlsruhe Institute of Technology, Karlsruhe, Germany, 2013.

Reviewing

Machine Learning Conferences
AAAI (2018), ICML (2009, 2011, 2016-2017), NIPS (2009-2011, 2013-2017), AISTATS (2009-2012), COLT (2010), DAGM (2009)
(Medical) Image Processing Conferences
MICCAI (2013), ICCV (2009)
Machine Learning Journals
JMLR, IEEE-TPAMI, IEEE-TNNLS, Neurocomputing, Machine Learning
(Medical) Image Processing Journals
IEEE-TIP, SIIMS, PMB, MBEC


© 2011-2017 Hannes Nickisch

XHTML | CSS | Design by FullAhead