This study investigates the application of ordinal regression methods for categorizing disease severity in chest radiographs. We propose a framework that divides the ordinal regression problem into three parts: a model, a target function, and a classification function. Different encoding methods, including one-hot, Gaussian, progress-bar, and our soft-progress-bar, are applied using ResNet50 and ViT-B-16 deep learning models. We show that the choice of encoding has a strong impact on performance and that the best encoding depends on the chosen weighting of Cohen's kappa and also on the model architecture used. We make our code publicly available on GitHub.
@article{arxiv.2402.05685,
title = {An Ordinal Regression Framework for a Deep Learning Based Severity Assessment for Chest Radiographs},
author = {Patrick Wienholt and Alexander Hermans and Firas Khader and Behrus Puladi and Bastian Leibe and Christiane Kuhl and Sven Nebelung and Daniel Truhn},
journal= {arXiv preprint arXiv:2402.05685},
year = {2024}
}
Comments
17 pages, 3 figures, the code is available at: https://github.com/paddyOnGithub/ordinal_regression