T Shi

A personal blog

RANZCR Intelligence 2018

It’s been great attending the Intelligence 2018 seminar, with many great talks and inspiring speakers. Here’s a quick summary of the important points I learned in the day.

Issues with medical data

  • Volume: medical imaging data are abundant compared to other specialties, but it’s still small compared to general data such as road data for automated vehicles, everyday images such as ImageNet.
  • Privacy: already a huge hurdle for many research projects, but another issue lies in the fact that current anonymisation techniques may not be sufficient
  • Source and bias: although we have many promising results from ML with the current data sets, there are always issues with “rubbish in, rubbish out”.
  • Labels and ground truth
  • Rare cases: we simply don’t have enough of rare medical cases to train the machine

A few issues with results

  • clinical significance
  • explainability
  • generalisation
  • false positives

Future of radiology

  • guide treatment
  • participate in machine learning

Future of medical innovation

  • workflow improvement rather than systems innovation
  • infrastructure improvements will offer further higher yield: fax machines, electronic health records