Marc-André Schulz
YOU?
Author Swipe
View article: Brain-age models with lower age prediction accuracy have higher sensitivity for disease detection
Brain-age models with lower age prediction accuracy have higher sensitivity for disease detection Open
This study critically reevaluates the utility of brain-age models within the context of detecting neurological and psychiatric disorders, challenging the conventional emphasis on maximizing chronological age prediction accuracy. Our analys…
View article: Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application.
Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application. Open
Trustworthy interpretation of deep learning models is critical for neuroimaging applications, yet commonly used Explainable AI (XAI) methods lack rigorous validation, risking misinterpretation. We performed the first large-scale, systemati…
View article: Do Transformers and <scp>CNNs</scp> Learn Different Concepts of Brain Age?
Do Transformers and <span>CNNs</span> Learn Different Concepts of Brain Age? Open
“Predicted brain age” refers to a biomarker of structural brain health derived from machine learning analysis of T1‐weighted brain magnetic resonance (MR) images. A range of machine learning methods have been used to predict brain age, wit…
View article: Do transformers and CNNs learn different concepts of brain age?
Do transformers and CNNs learn different concepts of brain age? Open
“Predicted brain age” refers to a biomarker of structural brain health derived from machine learning analysis of T1-weighted brain magnetic resonance (MR) images. A range of machine learning methods have been used to predict brain age, wit…
View article: Brain-age models with lower age prediction accuracy have higher sensitivity for disease detection
Brain-age models with lower age prediction accuracy have higher sensitivity for disease detection Open
This study critically reevaluates the utility of brain-age models within the context of detecting neurological and psychiatric disorders, challenging the conventional emphasis on maximizing chronological age prediction accuracy. Our analys…
View article: Performance reserves in brain-imaging-based phenotype prediction
Performance reserves in brain-imaging-based phenotype prediction Open
This study examines the impact of sample size on predicting cognitive and mental health phenotypes from brain imaging via machine learning. Our analysis shows a 3- to 9-fold improvement in prediction performance when sample size increases …
View article: DeepRepViz: Identifying Confounders in Deep Learning Model Predictions
DeepRepViz: Identifying Confounders in Deep Learning Model Predictions Open
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 confounders such as age, sex, or imaging artif…
View article: Performance reserves in brain-imaging-based phenotype prediction
Performance reserves in brain-imaging-based phenotype prediction Open
Machine learning studies have shown that various phenotypes can be predicted from structural and functional brain images. However, in most such studies, prediction performance ranged from moderate to disappointing. It is unclear whether pr…
View article: Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction
Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction Open
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 specific diseases with notorious data scarcity. W…
View article: FIMAP: Feature Importance by Minimal Adversarial Perturbation
FIMAP: Feature Importance by Minimal Adversarial Perturbation Open
Instance-based model-agnostic feature importance explanations (LIME, SHAP, L2X) are a popular form of algorithmic transparency. These methods generally return either a weighting or subset of input features as an explanation for the classif…
View article: Inferring disease subtypes from clusters in explanation space
Inferring disease subtypes from clusters in explanation space Open
Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional biomedical data is often impossible for humans and …
View article: A Cognitive Fingerprint in Human Random Number Generation
A Cognitive Fingerprint in Human Random Number Generation Open
Most work in the neurosciences collapses data from multiple subjects to obtain robust statistical results. This research agenda ignores that even in healthy subjects brain structure and function are known to be highly variable. Recently, F…
View article: Clusters in Explanation Space: Inferring disease subtypes from model explanations
Clusters in Explanation Space: Inferring disease subtypes from model explanations Open
Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional biomedical data is often impossible for humans and …
View article: EMAP: Explanation by Minimal Adversarial Perturbation
EMAP: Explanation by Minimal Adversarial Perturbation Open
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 return either a weighting or subset of input…
View article: Deep learning for brains?: Different linear and nonlinear scaling in UK Biobank brain images vs. machine-learning datasets
Deep learning for brains?: Different linear and nonlinear scaling in UK Biobank brain images vs. machine-learning datasets Open
In recent years, deep learning has unlocked unprecedented success in various domains, especially in image, text, and speech processing. These breakthroughs may hold promise for neuroscience and especially for brain-imaging investigators wh…
View article: Deep learning for brains?: Different linear and nonlinear scaling in UK Biobank brain images vs. machine-learning datasets
Deep learning for brains?: Different linear and nonlinear scaling in UK Biobank brain images vs. machine-learning datasets Open
In recent years, deep learning has unlocked unprecedented success in various domains, especially in image, text, and speech processing. These breakthroughs may hold promise for neuroscience and especially for brain-imaging investigators wh…