Aleksei Tiulpin

Aleksei Tiulpin

MSc.

Doctoral student
Biomedical Engineering

10 peer reviewed publications in international journals. The publications have been cited 79 times, of which the most cited publication accounts for 46 citations. The author has a h-index of 4.00. (Google Scholar)

Biography

I conduct research on Deep Learning for Medical Imaging. I am interested in learning with limited data, noisy labels, self-supervised learning and anomaly detection.

Research interests

  • Machine Learning
  • Computer Vision
  • Medicine
  • Muskuloskeletal Radiology
  • Osteoarthritis

Social media

Research groups

  • Doctoral Student, Research Unit of Medical Imaging Physics and Technology

Selected publications

  • Tiulpin, Aleksei; Thevenot, Jérôme; Rahtu, Esa; Lehenkari, Petri; Saarakkala, Simo (2018) Automatic knee osteoarthritis diagnosis from plain radiographs : a deep learning-based approach. - Scientific Reports 8, 1727 . [Original] [Self-archived]
  • Tiulpin, A.; Thevenot, J.; Rahtu, E.; Saarakkala, S. (2017) A novel method for automatic localization of joint area on knee plain radiographs. (Artikkeli tieteellisessä konferenssijulkaisussa). - Proceedings of the 20th Scandinavian Conference on Image Analysis, SCIA 2017; Tromso; Norway; 12 -14 June 2017. Lecture Notes in Computer Science 10270. 290-301. [Original]
  • Melekhov, I.; Tiulpin, A.; Sattler, T.; Pollefeys, M.; Rahtu, E.; Kannala, J. (2019) DGC-Net: Dense geometric correspondence network. (Artikkeli tieteellisessä konferenssijulkaisussa). - 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019. IEEE Winter Conference on Applications of Computer Vision. 1034-1042, 8658868. [Original] [Self-archived]

Research visits

  • Erasmus MC, Rotterdam, The Netherlands
    1.3.2018 to 1.6.2018

Projects

Prediction and decision support systems for knee osteoarthritis

Strategic research project of the University of OuluFocus institute: Infotech OuluFaculty: Faculty of Medicine (FoM)  

Future Artificial Intelligence-tailored Hospital (FAITH)

Current Artificial Intelligence (AI)-based diagnostic tools are developed using curated and clean datasets, therefore their applicability to the re