An Ordinal Regression Framework for a Deep Learning Based Severity Assessment for Chest Radiographs
This work addresses disease severity assessment in medical imaging, but it is incremental as it focuses on optimizing encoding methods within existing deep learning models.
The study tackled the problem of categorizing disease severity in chest radiographs by proposing an ordinal regression framework, showing that encoding choice significantly impacts performance, with results varying by model architecture and weighting metrics like Cohen's kappa.
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.