kdercksen
  • About me
  • Misc
  • Papers
  • Tutorials

REL: An Entity Linker Standing on the Shoulders of Giants

This work was published as a demo paper at SIGIR2020.

Read the paper here.

Abstract

Entity linking is a standard component in modern retrieval systems that is often performed by third-party toolkits. Despite the plethora of open source options, it is difficult to find a single system that has a …

more ...

Robust multi-vendor breast region segmentation using deep learning

This work was published as an extended abstract for the IWBI2020 workshop. It was carried out during a three month MSc internship at Screenpoint Medical under supervision of Jaap Kroes and Michiel Kallenberg.

Read the paper here. See the presentation here (2nd presentation in session).

Abstract

Semantic segmentation of breast …

more ...

First Steps Towards Patient-Friendly Presentation of Dutch Radiology Reports

This work was published as a full paper for the SIIRH2020 workshop at ECIR2020.

Read the paper here. See the presentation here.

Abstract

Nowadays, clinical patients are often free to access their own electronic health records (EHRs) online. Medical records are however not written with the patient in mind -- the …

more ...

Dealing with label scarcity in computational pathology: a use case in prostate cancer classification

This is work done during my MSc thesis internship at Radboudumc, together with Wouter Bulten and Geert Litjens. Our paper was published at MIDL2019 as an extended abstract.

Read the paper here.

Abstract

Large amounts of unlabelled data are commonplace for many applications in computational pathology, whereas labelled data is …

more ...

  • Social

    • github
    • linkedin
    • stack-overflow
    • email

© 2020 Koen Dercksen · Powered by pelican-bootstrap3, Pelican, Bootstrap

Back to top