Sophia Stöcklein

Improving the fairness and robustness of deep learning classification models through bias mitigation and post hoc calibration

Abstract Purpose: The goal of this study was to enhance the fairness and clinical applicability of deep learning models for classifying Alzheimer’s disease from structural MRI scans. To achieve this, we addressed two key challenges: age-related bias and unreliable probability est...

Investigating changes in the blood-brain barrier in schizophrenia spectrum disorders: design and methodology of a longitudinal dynamic contrast-enhanced MRI study

Schizophrenia spectrum disorders (SSDs) are clinically and biologically heterogeneous and lack reliable biomarkers for stratification, treatment response and course prediction. Evidence from postmortem, fluid biomarker, and neuroimaging studies suggests that changes in the blood-...