1 code implementation • 12 Feb 2020 • Christian Wachinger, Anna Rieckmann, Sebastian Pölsterl
Given such evidence, we take a closer look at confounding bias, which is often viewed as the main shortcoming in observational studies.
no code implementations • 9 Jul 2019 • Christian Wachinger, Benjamin Gutierrez Becker, Anna Rieckmann, Sebastian Pölsterl
In this work, we combine 12, 207 MRI scans from 15 studies and show that simple pooling is often ill-advised due to introducing various types of biases in the training data.
no code implementations • 28 Apr 2018 • Christian Wachinger, Benjamin Gutierrez Becker, Anna Rieckmann
Next, we introduce metrics to quantify the compatibility across datasets and to create embeddings of neuroimaging sites.