Very experienced fellow

Jussi Tohka

Doctorate from:
Tampere University of Technology, Finland

Department at UC3M:
Bioengineering and Aerospace Engineering

CONEX Fellow from 16/02/15 to 31/10/16

Project

"Machine learning in brain imaging"

Rapid advances in non-invasive neuroimaging methods have increased the possibilities to study changes occurring in human brain across a variety of time-scales ranging from seconds to entire life span. A large part of these advances can be attributed to the development of dedicated computational and mathematical methods, which are essential to extract quantitative information from images. This project develops computational methods for machine learning based analysis of large brain image collections. Machine learning refers to the construction and study of methods that can learn models of example data. These models can then be used to make future predictions, for example, predict an early diagnosis for a patient. With these newly developed methods we hope to aid neuroscientists to study on how brain diseases alter the brain structure and function and this way contribute to the better and earlier diagnosis of brain diseases including Alzheimer’s disease, autism, and schizophrenia.

CV

Jussi Tohka received his PhD degree (with commendation) in Signal Processing from the Tampere University of Technology, Finland, in 2003. He was a post-doctoral fellow in the Laboratory of Neuro Imaging, University of California, Los Angeles, USA in 2004 - 2005, and thereafter held various research positions – including a highly regarded Academy of Finland research fellow position - at the Department of Signal Processing, Tampere University of Technology, Finland until being affiliated with the CONEX programme and UC3M. For over ten years, his research has focused in developing and evaluating data analysis methods for structural and functional brain imaging. He has published over 80 full-length research articles in refereed international journals or conferences and supervised 4 PhD theses to completion. Several software tools developed by him and his team are in wide use in medical imaging laboratories around the world.

Flickr

Dissemination activities

Scientific Publications:

1. J. Tohka , E. Moradi, and H. Huttunen. Comparison of feature selection techniques in machine learning for anatomical brain MRI in dementia. Neuroinfomatics , 14(3):279 - 296, 2016. Available at http://www.cs.tut.fi/~jupeto/MRIfeature_stability_preprint.pdf

2. M. Reason, D. Reynolds, R. Kay, C. Jola, J.-P. Kauppi, M.-H. Grobras, J. Tohka , F.E. Pollick. Spectators' Aesthetic Experience of Sound and Movement in Dance Performance: A Transdisciplinary Investigation, Psychology of Aesthetics, Creativity, and the Arts Vol 10(1):42 - 55, Feb 2016. Preprint available at http://eprints.gla.ac.uk/116597/1/116597.pdf

3. E. Moradi, B Khundrakpam, J. Lewis, A.C. Evans, J. Tohka : Predicting symptom severity in autism spectrum disorder based on cortical thickness measures in agglomerative data, NeuroImage, in press, 2016. Bioxriv preprint: http://dx.doi.org/10.1101/039180

4. J. Tohka , P. Bellec, C. Grova, A. Reilhac. Editorial: Simulation and Validation in Brain Image Analysis. Computational Intelligence and Neuroscience. Article ID 1041058, 2016 (open access).

5. J. Johansson, K. Alakurtti, J. Joutsa, J. Tohka , U. Ruotsalainen, J.O. Rinne. Comparison of manual and automatic techniques for substriatal segmentation in 11C-raclopride high-resolution PET studies. Nuclear Medicine Communications, 37(10):1074-87, 2016. Available from ResearchGate

6. I.P Jääskeläinen*, J. Pajula*, J. Tohka* , H-J Lee, W-J Kuo, F-H. Lin .Brain hemodynamic activity during viewing and re-viewing of comedy movies explained by experienced humor. Scientific Reports 6, article number 27741, 2016 (open access). * Equal contribution.

7. J.Pajula and J. Tohka: How Many Is Enough? Effect of Sample Size in Inter-Subject Correlation Analysis of fMRI.Computational Intelligence and Neuroscience, Volume 2016, January 2016 Article No. 2.

8. A. Herbec, J.-P. Kauppi, C. Jola, J. Tohka , F.E. Pollick: Differences in fMRI intersubject correlation while viewing unedited and edited videos of dance performance.Cortex , 71:341 - 348, 2015.

9.Khundrakpam BS*, Tohka J*, Evans AC: Prediction of brain maturity based on cortical thickness at different spatial resolutions. NeuroImage. Volume 111, 1 May 2015, Pages 350–359.

10. Moradia E.*, Hallikainenb l., Hänninenc T., ohka J.: Rey's Auditory Verbal Learning Test scores can be predicted from whole brain MRI in Alzheimer's disease. NeuroImage: Clinical 13 (2017) 415–427.

Refereed full length articles in international conferences:

11. V. Gomez-Verdojo, E. Parrado-Hernandez, J. Tohka . Voxel importance in classifier ensembles based on sign consistency patterns: Application to sMRI. IEEE International workshop on Pattern Recognition in Neuroimaging 2016. Available at http://www.cs.tut.fi/~jupeto/Verdejo_PRNI16.pdf

Refereed abstracts in international conferences:

12. S Huhtaniska, I Korkala, T Heikka, J Tohka, J Manjon, P Coupe, J Remes, J Moilanen, V Kiviniemi, L Björnholm, M Isohanni, J Veijola, G Murray, E Jääskeläinen, J Miettunen. Lifetime antipsychotic use and brain structures in schizophrenia and other psychoses–43-year study of the Northern Finland Birth Cohort 1966 European Psychiatry 33: S102 - 103, 2016.

13. Jussi Tohka, Elaheh Moradi, Heikki Huttunen. Feature selection stability in machine learning with anatomical brain MRI. 22nd Annual Meeting of the Organisation for Human Brain Mapping, Geneva, Switzerland, 2016.

14. Jussi Tohka, Elaheh Moradi, Heikki Huttunen. Bayesian error estimation for model selection in machine learning for brain imaging. 22nd Annual Meeting of the Organisation for Human Brain Mapping, Geneva, Switzerland, 2016.

15. Antonietta Pepe, Hamed Rabiei Jussi Tohka, Ivo Dinov, Julien Lefèvre. Modelling Growth and Tangential Expansion in the Brain Surface. A Practical Framework. 22nd Annual Meeting of the Organisation for Human Brain Mapping, Geneva, Switzerland, 2016. 6 CONEX Project Report - MACHIMA

Articles in international journals:

16. E. Moradi, I. Hallikainen, T. Hanninen, J. Tohka. Rey’s Auditory Verbal Learning Test scores can be predicted from whole brain MRI in Alzheimer’s disease. Minor revision submitted to NeuroImage: Clinical

17. Jukka-Pekka Kauppi, Juha Pajula, Jari A Niemi, Riitta Hari, Jussi Tohka. Functional brain segmentation using inter-subject correlation in fMRI. Under revision in Human Brain Mapping, 2016. Available at biorxiv http://dx.doi.org/10.1101/057620 Articles in preparation (with UC3M co-authors):

Dissemination Activities:

Project website

www.jussitohka.net

Editorial activities

Associate editor (Computational Intelligence and Neuroscience) Lead guest editor (Special issue: “Simulation and validation in brain image analysis” in Computational Intelligence and Neuroscience)

Reviewer for international journals

1) NeuroImage, 2) IEEE Transactions on Medical Imaging, 3) PNAS, 4) Philosophical Transactions of Royal Society B 5) IEEE Transactions on Pattern Analysis and Machine Intelligence 6) Human Brain Mapping

Workshop organization

Program committee member of Patch MI 2016 workshop in Athens, Greece.

Conference/Workshop Participation

Organization for Human Mapping. Annual Conference, Geneva, Switzerland, June 2016, IEEE International workshop on Pattern Recognition in Neuroimaging, Trento, Italy, June 2016. Medical Imaging and Computer Assisted Intervention (MICCAI 2015), October 5th to 9th 2015 in Munich, Germany; Patch-MI: Patch-based technique in Medical Imaging October 9th 2015 in Munich, Germany.