Poster + Paper
3 April 2024 Algorithmic shortcutting in medical image analysis
Author Affiliations +
Conference Poster
Abstract
As deep learning (DL) gains prominence in medical image analysis, its applications in orthopedics and broader medical contexts have expanded significantly. While machine learning algorithms show potential in using X-ray images for predicting outcomes, biases may arise due to insufficient preprocessing. One such source of bias is algorithmic shortcutting, a phenomenon wherein DL models inadvertently train on patterns within training data unrelated to the intended diagnostic content. Leveraging the Osteoarthritis Initiative (OAI) dataset and ResNet18, our convolutional neural network (CNN) could predict the clinical center from which X-rays originated with over 95% accuracy. Moreover, our investigation unveiled significant variations in patient demographics and outcomes between clinical centers, implying that discerning the originating clinical center could be a potential shortcut in predicting patient outcomes from X-rays. These findings underscore the importance of careful X-ray image preparation and analysis. More broadly, as deep learning models increasingly influence clinical decision-making, this work underscores the importance of addressing model shortcutting to enhance the transparency, interpretability, and efficacy of deep learning research across orthopedics and other medical domains.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Frances Koback, Brandon Hill, Travis Byrum, and Peter Schilling "Algorithmic shortcutting in medical image analysis", Proc. SPIE 12927, Medical Imaging 2024: Computer-Aided Diagnosis, 129272W (3 April 2024); https://doi.org/10.1117/12.3005269
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
X-rays

X-ray imaging

Data modeling

Education and training

Medical imaging

Deep learning

Machine learning

Back to Top