Skull-stripping induces shortcut learning in MRI-based Alzheimer's disease classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tinauer, Christian, Sackl, Maximilian, Stollberger, Rudolf, Schmidt, Reinhold, Ropele, Stefan, Langkammer, Christian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914097135616000
author Tinauer, Christian
Sackl, Maximilian
Stollberger, Rudolf
Schmidt, Reinhold
Ropele, Stefan
Langkammer, Christian
author_facet Tinauer, Christian
Sackl, Maximilian
Stollberger, Rudolf
Schmidt, Reinhold
Ropele, Stefan
Langkammer, Christian
contents Objectives: High classification accuracy of Alzheimer's disease (AD) from structural MRI has been achieved using deep neural networks, yet the specific image features contributing to these decisions remain unclear. In this study, the contributions of T1-weighted (T1w) gray-white matter texture, volumetric information, and preprocessing -- particularly skull-stripping -- were systematically assessed. Methods: A dataset of 990 matched T1w MRIs from AD patients and cognitively normal controls from the ADNI database were used. Preprocessing was varied through skull-stripping and intensity binarization to isolate texture and shape contributions. A 3D convolutional neural network was trained on each configuration, and classification performance was compared using exact McNemar tests with discrete Bonferroni-Holm correction. Feature relevance was analyzed using Layer-wise Relevance Propagation, image similarity metrics, and spectral clustering of relevance maps. Results: Despite substantial differences in image content, classification accuracy, sensitivity, and specificity remained stable across preprocessing conditions. Models trained on binarized images preserved performance, indicating minimal reliance on gray-white matter texture. Instead, volumetric features -- particularly brain contours introduced through skull-stripping -- were consistently used by the models. Conclusions: This behavior reflects a shortcut learning phenomenon, where preprocessing artifacts act as potentially unintended cues. The resulting Clever Hans effect emphasizes the critical importance of interpretability tools to reveal hidden biases and to ensure robust and trustworthy deep learning in medical imaging.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15831
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skull-stripping induces shortcut learning in MRI-based Alzheimer's disease classification
Tinauer, Christian
Sackl, Maximilian
Stollberger, Rudolf
Schmidt, Reinhold
Ropele, Stefan
Langkammer, Christian
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Objectives: High classification accuracy of Alzheimer's disease (AD) from structural MRI has been achieved using deep neural networks, yet the specific image features contributing to these decisions remain unclear. In this study, the contributions of T1-weighted (T1w) gray-white matter texture, volumetric information, and preprocessing -- particularly skull-stripping -- were systematically assessed. Methods: A dataset of 990 matched T1w MRIs from AD patients and cognitively normal controls from the ADNI database were used. Preprocessing was varied through skull-stripping and intensity binarization to isolate texture and shape contributions. A 3D convolutional neural network was trained on each configuration, and classification performance was compared using exact McNemar tests with discrete Bonferroni-Holm correction. Feature relevance was analyzed using Layer-wise Relevance Propagation, image similarity metrics, and spectral clustering of relevance maps. Results: Despite substantial differences in image content, classification accuracy, sensitivity, and specificity remained stable across preprocessing conditions. Models trained on binarized images preserved performance, indicating minimal reliance on gray-white matter texture. Instead, volumetric features -- particularly brain contours introduced through skull-stripping -- were consistently used by the models. Conclusions: This behavior reflects a shortcut learning phenomenon, where preprocessing artifacts act as potentially unintended cues. The resulting Clever Hans effect emphasizes the critical importance of interpretability tools to reveal hidden biases and to ensure robust and trustworthy deep learning in medical imaging.
title Skull-stripping induces shortcut learning in MRI-based Alzheimer's disease classification
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2501.15831