Saved in:
Bibliographic Details
Main Authors: Asadi, Mehrdad, Sodoké, Komi, Gerard, Ian J., Kersten-Oertel, Marta
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.03591
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915141304451072
author Asadi, Mehrdad
Sodoké, Komi
Gerard, Ian J.
Kersten-Oertel, Marta
author_facet Asadi, Mehrdad
Sodoké, Komi
Gerard, Ian J.
Kersten-Oertel, Marta
contents In this work, we present a novel approach to multi-label chest X-ray (CXR) image classification that enhances clinical interpretability while maintaining a streamlined, single-model, single-run training pipeline. Leveraging the CheXpert dataset and VisualCheXbert-derived labels, we incorporate hierarchical label groupings to capture clinically meaningful relationships between diagnoses. To achieve this, we designed a custom hierarchical binary cross-entropy (HBCE) loss function that enforces label dependencies using either fixed or data-driven penalty types. Our model achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.903 on the test set. Additionally, we provide visual explanations and uncertainty estimations to further enhance model interpretability. All code, model configurations, and experiment details are made available.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Clinically-Inspired Hierarchical Multi-Label Classification of Chest X-rays with a Penalty-Based Loss Function
Asadi, Mehrdad
Sodoké, Komi
Gerard, Ian J.
Kersten-Oertel, Marta
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
In this work, we present a novel approach to multi-label chest X-ray (CXR) image classification that enhances clinical interpretability while maintaining a streamlined, single-model, single-run training pipeline. Leveraging the CheXpert dataset and VisualCheXbert-derived labels, we incorporate hierarchical label groupings to capture clinically meaningful relationships between diagnoses. To achieve this, we designed a custom hierarchical binary cross-entropy (HBCE) loss function that enforces label dependencies using either fixed or data-driven penalty types. Our model achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.903 on the test set. Additionally, we provide visual explanations and uncertainty estimations to further enhance model interpretability. All code, model configurations, and experiment details are made available.
title Clinically-Inspired Hierarchical Multi-Label Classification of Chest X-rays with a Penalty-Based Loss Function
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.03591