Computational medical imaging and machine learning – methods, infrastructure and applications

– A collaboration between the Department of Biomedicine, UiB, and the Department of Computing, Mathematics and Physics, HVL

Over the past few years there has been a surge of interest in areas associated to machine learning and artificial intelligence. This is caused by breakthroughs in what’s called “deep learning”, a collection of techniques that enable computers to uncover complicated patterns and connections in large data sets. Increased access to data (“big data”) and increased computational power has made so-called deep neural networks useful for real-world, practical problems, and they have become the state-of-the-art approach to many key challenges in computer vision, language modelling and robotics.

These developments have a huge potential for medical imaging technology, medical data analysis, medical diagnostics and healthcare in general, slowly being realized. That’s not only true for deep learning methods, but also for the wider field of machine learning and data analysis, as part of computational medicine.

Our project develop, implement, disseminate and evaluate machine learning techniques in the analysis of medical images and image-related data.

To successfully incorporate machine learning in medicine, doctors and medical specialists have to take a leading role in both research and development. Our project, initiated from the Department of Biomedicine at UiB and the Department of Computing, Mathematics and Physics at HVL, is therefore tightly connected with departments at the hospital where data is collected and decisions are made.

It involves many researchers in Bergen, both clinical and methodological, in addition to national and international collaborators from world-class research institutions in the USA (Mayo Clinic), Switzerland (ETH), Germany (Zuse Institute), France (ISIMA), Luxembourg (LIH) and Poland (TUL).

In addition to research, we also offer interdisciplinary courses for medical students, engineers and natural science students, and put considerable emphasis on dissemination and discussion of methods and results with a wide audience. 

Our main ambition is to contribute to an increased degree of personalized medicine and better decision support for diagnosis, prognosis and therapy in diseases and conditions where images are an important source of information.

 

News

MMIV at Christiekonferansen

MMIV is proud about its active participation in this year’s Christiekonferansen on Monday, 29th of April, in the University Aula in Bergen: In the “Forsking i front’ session from 11:30-12:00, Kristine Eldevik Fasmer talks about "Kan vi lære maskiner å finne kreft i...

Debate: ‘Artificial Intelligence in health care’

Today two members of the MMIV centre team, Arvid and Alexander Lundervold are featuring in a panel discussion at the Bergen public library on 'Artificial Intelligence in health care'. The discussion starts at 18:00, and more information can be found on the event...

Publications

2018

  • A. S. Lundervold and A. Lundervold, "An overview of deep learning in medical imaging focusing on MRI," Zeitschrift für Medizinische Physik, 2018. doi:10.1016/j.zemedi.2018.11.002
    [BibTeX] [Download PDF]
    @article{lundervold2018overview,
      title={An overview of deep learning in medical imaging focusing on {MRI}},
      author={Lundervold, Alexander Selvikv{\aa}g and Lundervold, Arvid},
      journal={Zeitschrift f{\"u}r Medizinische Physik},
      year={2018},
      publisher={Elsevier},
      doi = "10.1016/j.zemedi.2018.11.002",
      url = {https://www.sciencedirect.com/science/article/pii/S0939388918301181/pdfft?md5=6e22b45c6dbeba3aa00650d064732800&pid=1-s2.0-S0939388918301181-main.pdf"}
    }
  • A. Losnegård, L. Reisæter, O. J. Halvorsen, C. Beisland, A. Castilho, L. P. Muren, J. Rørvik, and A. Lundervold, "Intensity-based volumetric registration of magnetic resonance images and whole-mount sections of the prostate," Computerized Medical Imaging and Graphics, vol. 63, pp. 24-30, 2018. doi:10.1016/j.compmedimag.2017.12.002
    [BibTeX] [Download PDF]
    @article{losnegaard2018intensity,
      title={Intensity-based volumetric registration of magnetic resonance images and whole-mount sections of the prostate},
      author={Losneg{\aa}rd, Are and Reis{\ae}ter, Lars and Halvorsen, Ole J and Beisland, Christian and Castilho, Aurea and Muren, Ludvig P and R{{\o{}}}rvik, Jarle and Lundervold, Arvid},
      journal={Computerized Medical Imaging and Graphics},
      volume={63},
      pages={24--30},
      year={2018},
      publisher={Elsevier},
      url = {https://www.ncbi.nlm.nih.gov/pubmed/29276002},
      doi = "10.1016/j.compmedimag.2017.12.002"
    }
  • S. Ytre-Hauge, J. A. Dybvik, A. Lundervold, Ø. O. Salvesen, C. Krakstad, K. E. Fasmer, H. M. Werner, B. Ganeshan, E. Høivik, L. Bjørge, J. Trovik, and I. Haldorsen, "Preoperative tumor texture analysis on MRI predicts high-risk disease and reduced survival in endometrial cancer," Journal of Magnetic Resonance Imaging, vol. 48, iss. 6, pp. 1637-1647, 2018. doi:10.1002/jmri.26184
    [BibTeX] [Download PDF]
    @article{ytre2018preoperative,
      title={Preoperative tumor texture analysis on MRI predicts high-risk disease and reduced survival in endometrial cancer},
      author={Ytre-Hauge, Sigmund and Dybvik, Julie A and Lundervold, Arvid and Salvesen, {{\O}}yvind O and Krakstad, Camilla and Fasmer, Kristine E and Werner, Henrica M and Ganeshan, Balaji and H{{\o{}}}ivik, Erling and Bj\orge, Line and Trovik, J and Haldorsen, IS},
      journal={Journal of Magnetic Resonance Imaging},
      volume={48},
      number={6},
      pages={1637--1647},
      year={2018},
      publisher={Wiley Online Library},
      url = {https://www.ncbi.nlm.nih.gov/pubmed/30102441},
      doi = "10.1002/jmri.26184"
    }
  • E. A. Hanson, C. Sandmann, A. Malyshev, A. Lundervold, J. Modersitzki, and E. Hodneland, "Estimating the discretization dependent accuracy of perfusion in coupled capillary flow measurements," PloS one, vol. 13, iss. 7, p. e0200521, 2018. doi:10.1371/journal.pone.0200521
    [BibTeX] [Download PDF]
    @article{hanson2018estimating,
      title={Estimating the discretization dependent accuracy of perfusion in coupled capillary flow measurements},
      author={Hanson, Erik A and Sandmann, Constantin and Malyshev, Alexander and Lundervold, Arvid and Modersitzki, Jan and Hodneland, Erlend},
      journal={PloS one},
      volume={13},
      number={7},
      pages={e0200521},
      year={2018},
      publisher={Public Library of Science},
      url = {https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0200521},
      doi = "10.1371/journal.pone.0200521"
    }
  • E. Hodneland, E. Keilegavlen, E. A. Hanson, E. Andersen, J. A. Monssen, J. T. Rorvik, S. Leh, H. Marti, A. Lundervold, E. Svarstad, and J. Nordbotten, "In vivo detection of chronic kidney disease using tissue deformation fields from dynamic MR imaging," IEEE Transactions on Biomedical Engineering, 2018. doi:10.1109/TBME.2018.2879362
    [BibTeX] [Download PDF]
    @article{hodneland2018vivo,
      title={In vivo detection of chronic kidney disease using tissue deformation fields from dynamic MR imaging},
      author={Hodneland, Erlend and Keilegavlen, Eirik and Hanson, Erik A and Andersen, Erling and Monssen, Jan Ankar and Rorvik, Jarle Tor and Leh, Sabine and Marti, Hans-Peter and Lundervold, Arvid and Svarstad, Einar and Nordbotten, JM},
      journal={IEEE Transactions on Biomedical Engineering},
      year={2018},
      publisher={IEEE},
      url = {https://www.ncbi.nlm.nih.gov/pubmed/30403617},
      doi = "10.1109/TBME.2018.2879362"
    }
  • A. J. Lundervold, A. Vik, and A. Lundervold, "Lateral ventricle volume trajectories predict response inhibition in older age-a longitudinal brain imaging and machine learning approach," BioRxiv, p. 468678, 2018. doi:10.1101/468678
    [BibTeX] [Download PDF]
    @article{lundervold2018lateral,
      title={Lateral ventricle volume trajectories predict response inhibition in older age-a longitudinal brain imaging and machine learning approach},
      author={Lundervold, Astri J and Vik, Alexandra and Lundervold, Arvid},
      journal={BioRxiv},
      pages={468678},
      year={2018},
      publisher={Cold Spring Harbor Laboratory},
      url = {https://www.biorxiv.org/content/10.1101/468678v1?rss=1},
      doi = "10.1101/468678"
    }

2017

  • A. J. Lundervold, T. Bøe, and A. Lundervold, "Inattention in primary school is not good for your future school achievement—A pattern classification study," PloS one, vol. 12, iss. 11, p. e0188310, 2017. doi:10.1371/journal.pone.0188310
    [BibTeX] [Download PDF]
    @article{lundervold2017inattention,
      title={Inattention in primary school is not good for your future school achievement—A pattern classification study},
      author={Lundervold, Astri J and B{{\o{}}}e, Tormod and Lundervold, Arvid},
      journal={PloS one},
      volume={12},
      number={11},
      pages={e0188310},
      year={2017},
      publisher={Public Library of Science},
      url = {https://www.ncbi.nlm.nih.gov/pubmed/29182663},
      doi = "10.1371/journal.pone.0188310"
    }

Project members

Principal investigators

Arvid Lundervold

PI. Professor – Department of Biomedicine, University of Bergen. Homepage.

Alexander Selvikvåg Lundervold

PI. Associate Professor –  Department of Computing, Mathematics and Physics, Western Norway University of Applied Sciences. Homepage.

PhD candidates

Saruar Alam

Department of Biomedicine, University of Bergen

Samaneh Abolpour Mofrad

Dept. of Computing, Mathematics and Physics, Western Norway University of Applied Sciences.

Geir Kjetil Nilsen

Department of Mathematics

Alexandra Vik

Department of Biological and Medical Psychology

Postdoctoral researchers

TBA

TBA

TBA

MSc and MD research track students

Sindre Eik de Lange, HVL

Viola Hansen, HVL

Sondre Fossen-Romsaas, HVL

Stian Heilund, HVL

Lionel Giriteka, UiB

Sathiesh Kaliyugarasan, HVL

Peder Lillebostad, UiB

Sivert Stavland, HVL

Adrian Storm-Johannessen, HVL

Former PhD and MSc students

Sean Murray, UiB