Welcome to Combinostics

We enable objective and confident diagnostics in complex diseases

Company Background

Combinostics was founded in August 2014 with the goal to develop and market advanced tools for data-driven diagnostics. The founders have unique know-how in clinical decision support with strong expertise on biomarker discovery. The technology builds on software and innovations that have been developed over many years at VTT Technical Research Centre of Finland.

The Board

Harry Brade – Chairman of the Board

Jyrki Lötjönen – Board member, Founders representative

Toni Mattila – Board member, Investor representative

Tero Weckroth – Board member, joint representative

The Team

Lennart Thurfjell, CEO

Lennart has worked for more than twenty-five years in in development and management roles in healthcare industry. He has a PhD in medical image processing from Uppsala University (Sweden) and he holds a part-time position as professor in neuroimaging at the Institute of Neuroscience and Physiology at the University of Gothenburg (Sweden).

Jyrki Lötjönen, CSO

Jyrki has Ph.D. degrees from Helsinki University of Technology (Finland) and INSA of Lyon (France) in 2000. He is a principal scientist in the ICT for health research area at VTT Technical Research Centre of Finland, CSO at Combinostics Ltd and adjunct professor at Aalto University (Finland). His research interests are in medical image analysis, data mining and decision support systems. He has co-authored more than 100 international peer-reviewed scientific papers.

Jussi Mattila, Research & Development

Jussi received his Ph.D. degree from Tampere University of Technology (Finland) in 2014. His has vast experience in designing and implementing clinical decision support systems and software engineering in general. He was a developer of the PredictAD software that is extended to support differential diagnostics of dementia in VPH-DARE@IT.

Juha Koikkalainen, Imaging Scientist

Juha received his Ph.D. degree from Helsinki University of Technology (Finland) in 2006. He manages image analysis development at Combinostics Ltd and he also has a position as adjunct professor in Medical image processing at University of Eastern Finland. He has extensive experience in medical image quantification and clinical decision support systems. He has co-authored over 50 international peer-reviewed papers.

Markus Niiranen, Software Engineer

Markus has an MSc, Electrical Engineering (Signal Processing) from the University of Oulu (Finland). He has more than fifteen years professional software development experience.

cNeuro cMRI

cNeuro is Combinostics’ suite of tools for quantitative assessment of brain images and for providing clinical decision support in neurological disorders. Our first module, cMRI, provides fully automated quantification of MR brain scans.


  • Cloud-based – software runs in a standard web browser.
  • Compute volumes of 98 cortical parcellations and 38 subcortical structures from T1 images.
  • Computation of gray matter concentration from T1 images.
  • Computation of vascular burden from FLAIR images.
  • Visualization of gray-matter concentration map supporting assessment of brain atrophy.
  • Quantitative information corrected for age, gender and head size.
  • Summary report for streamlined communication with referring physicians.

Diagnostic Services

Combinostics’ goal is to provide tools that bring a disruptive change to clinical decision making, enabling objective and confident diagnostics in complex diseases. Combinostics’ solution combines all available information and replaces silos of data with a holistic view of the patient’s disease state. Moreover, decision support is provided by contrasting the data from an individual patient with the corresponding data from previously diagnosed patients, where outcome is known through longitudinal follow-up.

Combinostics’ technology is generic and can be applied in several disease areas but our initial focus is on clinical decision support in neurodegenerative diseases (see publications).

Imaging Biomarkers

Our suite of tools includes fast and robust methods for extraction of imaging biomarkers. The methods have been rigorously validated and results have been published in leading scientific journals (see publications). Our main focus is on tools for MR image processing, but methods for PET and CT image analysis are also available. MR image processing tools include methods for skull stripping, fast non-linear image registration, hippocampal segmentation and segmentation of general cortical and subcortical structures. Tools for voxel-based and tensor-based morphometry are also available as well as for quantifying vascular burden.

Our imaging quantification tools are an important part of our clinical decision support system but we also provide services around integration of our tools into 3rd party products.

List of Publications

Selected publications relevant to Combinostics’ tools and services
  • J. Lötjönen et al. Fast and robust multi-atlas segmentation of brain magnetic resonance images. NeuroImage 49: 2352-2365, 2010.
  • J. Koikkalainen et al. Multi-Template Tensor-Based Morphometry: Application to Analysis of Alzheimer's Disease, NeuroImage 56: 1134-1144, 2011. 
  • R. Wolz et al. Multi-Method Analysis of MRI Images in Early Diagnostics of Alzheimer's Disease. PLoS One 6(10):e25446, 2011.
  • J. Lötjönen et al. Fast and robust extraction of hippocampus from MR images for diagnostics of Alzheimer’s disease. NeuroImage 56: 185-196, 2011.
  • J. Mattila et al. Disease State Fingerprint for Evaluating the State of Alzheimer’s Disease in Patients. Journal of Alzheimer’s Disease 27: 163-176, 2011.
  • J. Mattila et al. Optimizing the diagnosis of early Alzheimer’s disease in mild cognitive impairment subjects. Journal of Alzheimer’s Disease 32: 969-979, 2012.
  • A. Simonsen et al. Application of the PredictAD software tool to patients with mild cognitive impairment. Dementia and Geriatric Cognitive Disorders 34: 344-450, 2012.
  • Y. Liu et al. Predicting AD conversion: comparison between prodromal AD guidelines and computer assisted PredictAD tool. PLoSOne 8(2): e55246, 2013.
  • M. Muñoz-Ruiz et al. Disease state fingerprint in frontotemporal degeneration with reference to Alzheimer’s disease and mild cognitive impairment. Journal of Alzheimer’s Disease 35(4): 727-739, 2013.
  • H. Runtti et al. Quantitative evaluation of disease progression in longitudinal mild cognitive impairment cohort. Journal of Alzheimer’s Disease, 39: 49-61 2014.
  • A. Hall et al. Generalizability of the Disease State Index prediction model for identifying Patients progressing from mild cognitive impairment to Alzheimer’s disease. Journal of Alzheimer’s Disease: in press 2014.
  • A. Hall et al. Predicting progression from cognitive impairment to Alzheimer’s disease with the Disease State Index. Current Alzheimer Research, 12: 69-79, 2015.

Contact Us

Our Office
Combinostics Oy
Hatanpään valtatie 24
33100 Tampere
+46 730 699 057