Veronika Cheplygina presents Curious findings about medical image datasets
On 2026-09-17 - 2026-09-17 10:00:00 at G205, Karlovo náměstí 13, Praha 2
It may seem intuitive that we need high quality datasets to ensure for robust
algorithms for medical image classification. With the introduction of openly
available, larger datasets, it might seem that the problem has been solved.
However, this is far from being the case, as it turns out that even these
datasets suffer from issues like label noise and shortcuts or confounders.
Furthermore, there are behaviours in our research community that threaten the
validity of published findings. In this talk I will discuss both types of
issues
with examples from recent papers.
algorithms for medical image classification. With the introduction of openly
available, larger datasets, it might seem that the problem has been solved.
However, this is far from being the case, as it turns out that even these
datasets suffer from issues like label noise and shortcuts or confounders.
Furthermore, there are behaviours in our research community that threaten the
validity of published findings. In this talk I will discuss both types of
issues
with examples from recent papers.