# Homepage of 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, Gaussian processes, pattern recognition, medical image processing and patient-specific biophysical predictive models.

My publications are listed below. In case of questions related to my work or if you wish to collaborate, please contact me at contact.hannes@nickisch.org.

# Code

## gpml

### The Gaussian Process for Machine Learning toolbox.

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
```

## glm-ie

### The Generalised Linear Models Inference and Estimation Toolbox.

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

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

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.

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

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

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

**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.

**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.

**Scalable Gaussian Processes for Characterizing Multidimensional Change Surfaces
** [link]
[poster]
[slides]

W. Herlands, A. G. Wilson, H. Nickisch, S. Flaxman, D. Neill, W. van Panhuis, E. Xing, AISTATS, 2016.

**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, 2016.

**SVM-based failure detection of GHT localizations
** [pdf]
[link]

[slides]

T. Blaffert, C. Lorenz, H. Nickisch, J. Peters and J. Weese, SPIE, 2016.

**Can Pretrained Neural Networks Detect Anatomy?** [link]

V. Menkovski, Z. Aleksovski, A. Saalbach, H. Nickisch, NIPS Workshop on Machine Learning in Healthcare, 2015.

**Thoughts on Massively Scalable Gaussian Processes**
[link]

A. G. Wilson, C. Dann and H. Nickisch, arXiv.org, 2015.

## Journal Articles

**12) 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, 2017.

**11) 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) Attribute-Based Classification for Zero Shot Visual Object Categorization
** [link]

C. Lampert, H. Nickisch and S. Harmeling, IEEE Transactions on Pattern
Analysis and Machine Intelligence, 36(3):453-465, 2014.

**9) 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) 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) 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) 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) 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) 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) 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) 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) 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

**16) 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) 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, 2016.

**14) SVM-based failure detection of GHT localizations
** [pdf]
[link]

[slides]

T. Blaffert, C. Lorenz, H. Nickisch, J. Peters and J. Weese, SPIE, 2016.

**13) 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) Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)
** [pdf,
supp]
[slides]
[link]

A. G. Wilson and H. Nickisch, ICML, 2015.

**11) 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) 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, STACOM, 2012.

**9) Additive Gaussian Processes** [pdf]
[link]

D. Duvenaud, H. Nickisch and C. E. Rasmussen, NIPS, 2011.

**8) Regularized Sparse Kernel Slow Feature Analysis** [pdf]
[link]

W. Böhmer and S. Grünewälder, H. Nickisch and K. Obermayer, ECML/PKDD,
2011.

**7) Fast Convergent Algorithms for Expectation Propagation Approximate
Bayesian Inference** [pdf]
[link]

M. W. Seeger and H. Nickisch, AISTATS, 2011.

**6) Learning an interactive segmentation system** [pdf]
[link]

H. Nickisch, C. Rother, C. Rhemann and Pushmeet Kohli, ICVGIP, 2010.

Best paper award.

**5) Gaussian Mixture Modeling with Gaussian Process Latent Variable
Models** [pdf]

H. Nickisch and C. E. Rasmussen, DAGM, 2010.

**4) Convex variational Bayesian inference for large scale generalized
linear models** [pdf]
[link]

H. Nickisch and M. W. Seeger, ICML, 2009.

**3) Learning To Detect Unseen Object Classes by Between-Class Attribute
Transfer** [link]

C. H. Lampert, H. Nickisch and S. Harmeling, CVPR, 2009.

**2) Bayesian Experimental Design of Magnetic Resonance Imaging Sequences**
[pdf] [link]

M. W. Seeger, H. Nickisch, R. Pohmann and B. Schölkopf, NIPS, 2008.

**1) Compressed Sensing and Bayesian Experimental Design**
[pdf] [link]

M. W. Seeger and H. Nickisch, ICML, 2008.

## Abstracts and Posters

**7) 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) 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) 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) Can Pretrained Neural Networks Detect Anatomy?** [link]

V. Menkovski, Z. Aleksovski, A. Saalbach, H. Nickisch, NIPS Workshop on Machine Learning in Healthcare, 2015.

**3) 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) Retrospective blind motion correction of MR images**
[pdf]

A. Loktyushin, H. Nickisch, R. Pohmann and B. Schölkopf, ISMRM, 2009.

**1) 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) Thoughts on Massively Scalable Gaussian Processes**
[link]

A. G. Wilson, C. Dann and H. Nickisch, arXiv.org, 2015.

**3) 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) Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)**
[pdf] [link]

A. G. Wilson and H. Nickisch, arXiv.org, 2015.

**1) Multiple Kernel Learning: A Unifying Probabilistic Viewpoint**
[pdf] [link]

H. Nickisch and M. W. Seeger, arXiv.org, 2011.

## Diploma and PhD Theses

**2) Bayesian Inference and Experimental Design for Large Generalised
Linear Models**
[pdf]
[link]

H. Nickisch, PhD Thesis, Technische Universität Berlin, Berlin, Germany,
2010.

**1) Extraction of visual features from natural video data using
Slow Feature Analysis** [pdf]

H. Nickisch, Diploma Thesis, Technische Universität Berlin, Berlin, Germany,
2006.

## Students (co-)supervised

**4) 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) Deep Learning for Advanced Medical Applications**
[link]

Ivo Baltruschat, Master Thesis, Universität zu Lübeck, Lübeck, Germany, 2016.

**2) Blind Retrospective Motion Correction of MR Images **
[link]
[pdf]

Alexander Loktyushin, PhD Thesis, University of Tübingen, Tübingen, Germany, 2015.

**1) Model Generation for Automatic Myocardium Segmentation.**

Jan Wingerter, Diploma Thesis, Karlsruhe Institute of Technology, Karlsruhe, Germany,
2013.