Marc-Andre Schulz

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical...

DeepRepViz: Identifying Confounders in Deep Learning Model Predictions

Deep Learning (DL) models have gained popularity in neuroimaging studies for predicting psychological behaviors, cognitive traits, and brain pathologies. However, these models can be biased by...

Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction

High-quality data accumulation is now becoming ubiquitous in the health domain. There is increasing opportunity to exploit rich data from normal subjects to improve supervised estimators in...

EMAP: Explanation by Minimal Adversarial Perturbation

Modern instance-based model-agnostic explanation methods (LIME, SHAP, L2X) are of great use in data-heavy industries for model diagnostics, and for end-user explanations. These methods generally...

Clusters in Explanation Space: Inferring disease subtypes from model explanations

Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional...

TLIMB - A Transfer Learning Framework for IMage Analysis of the Brain

Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model

Data Augmentation via Partial Nonlinear Registration for Brain-Age Prediction

FIMAP: Feature Importance by Minimal Adversarial Perturbation

Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers

Normative age models are trained to predict chronological age in a nominally healthy cohort. Applied to patients, they deviate, and the gap between predicted and chronological age is read as...

ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on

Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Before deployment, models should therefore be audited for reliance on concepts such as acquisition...

Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction

On biomedical tabular data, flexible models such as deep networks, gradient-boosted trees, and kernel methods are repeatedly matched or beaten by linear and logistic regression given the same...

Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics

Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distribution contexts. Yet generative models of...

Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model

The development of foundation models for functional magnetic resonance imaging (fMRI) time series holds significant promise for predicting phenotypes related to disease and cognition. Current...

Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application

Trustworthy interpretation of deep learning models is critical for neuroimaging applications, yet commonly used Explainable AI (XAI) methods lack rigorous validation, risking misinterpretation. We...