Machine Learning Group

The main focus of our research group is in the development of state-of-the-art methods that solve numerous problems in clinical and biomedical imaging problems. We design Machine Learning algorithms with a special focus on Deep Learning to speed up and improve reliability of clinical decision making. Another aim that we pursue is in creating efficient methods for data analysis in basic and clinical research. Our current projects include automatic tissue and anatomical landmarks localization, learning from limited data using semi- and weakly-supervised learning, robustness enhancements of Deep Learning methods, disease severity assessment and other topics.

If you are interested in joining our group or looking for a topic for Bachelor’s or Master’s thesis, please, contact Aleksei Tiulpin (



Osmo Tervonen, Professor, MD, PhD
Simo Saarakkala, Professor, PhD
Aleksei Tiulpin, MSc


Aleksei Tiulpin, MSc
Neslihan Yalcin Bayramoglu, PhD

PhD Students

Egor Panfilov, MSc
Huy Hoang Nguyen, MSc
Santeri Rytky, MSc
Abu Mohammed Raisuddin, BSc

Research Assistants

Mustafa Al-Rubaye, BSc student


Selected publications:

  • Tiulpin, A., Thevenot, J., Rahtu, E., Lehenkari, P., Saarakkala, S. (2018). Automatic knee osteoarthritis diagnosis from plain radiographs: A deep learning-based approach. Scientific reports8(1), 1727.
  • Tiulpin, A., Melekhov, I., Saarakkala, S. (2019). KNEEL: Knee Anatomical Landmark Localization Using Hourglass Networks. In Proceedings of the IEEE International Conference on Computer Vision Workshops (pp. 0-0). 
  • Panfilov, E., Tiulpin, A., Klein, S., Nieminen, M. T., Saarakkala, S. (2019). Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation. In Proceedings of the IEEE International Conference on Computer Vision Workshops (pp. 0-0).
  • Tiulpin, A., Klein, S., Bierma-Zeinstra, S., Thevenot, J., Rahtu, E., van Meurs, J., ... & Saarakkala, S. (2019). Multimodal Machine Learning-based Knee Osteoarthritis Progression Prediction from Plain Radiographs and Clinical Data. arXiv preprint arXiv:1904.06236
  • Rytky, S. J., Tiulpin, A., Frondelius, T., Finnilä, M. A., Karhula, S. S., Leino, J., ... & Kröger, H. (2019). Automating three-dimensional osteoarthritis histopathological grading of human osteochondral tissue using machine learning on contrast-enhanced micro-computed tomography. bioRxiv, 713800. 
  • Tiulpin, A., Finnilä, M., Lehenkari, P., Nieminen, H. J., Saarakkala, S. (2019). Deep-learning for tidemark segmentation in human osteochondral tissues imaged with micro-computed tomography. arXiv preprint arXiv:1907.05089. (accepted at ACIVS 2020)
  • Solovyev, Roman, et al. "Bayesian Feature Pyramid Networks for Automatic Multi-Label Segmentation of Chest X-rays and Assessment of Cardio-Thoratic Ratio." arXiv preprint arXiv:1908.02924 (2019). (accepted at ACIVS 2020)
We also actively collavorate with multiple domestic and international institutions, including Erasmus Medical Center, Rotterdam (NL), KU Leuven (BE), University of Tampere (FI), University of Helsinki (FI), Aalto University (FI).  Our recent collaboration projects:
  • Wang, Johnny, et al. "Gray matter age prediction as a biomarker for risk of dementia." Proceedings of the National Academy of Sciences 116.42 (2019): 21213-21218.
  • Melekhov, Iaroslav, et al. "Dgc-net: Dense geometric correspondence network." 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2019.
  • Rakhlin, Alexander, et al. "Breast tumor cellularity assessment using deep neural networks." Proceedings of the IEEE International Conference on Computer Vision Workshops. 2019.
  • Tiulpin, Aleksei, and Simo Saarakkala. "Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks." arXiv preprint arXiv:1907.08020 (2019).

Last updated: 24.1.2020