Clinically-Inspired Hierarchical Multi-Label Classification of Chest X-rays with a Penalty-Based Loss Function

TL;DR

This paper introduces a hierarchical multi-label classification method for chest X-rays that uses a novel penalty-based loss function to improve clinical interpretability and model performance, achieving an AUROC of 0.903.

Contribution

The work presents a new hierarchical binary cross-entropy loss function that enforces label dependencies, enhancing interpretability and clinical relevance in chest X-ray classification.

Findings

Achieved a mean AUROC of 0.903 on the test set.

Incorporated hierarchical label groupings for better clinical relevance.

Provided visual explanations and uncertainty estimations.

Abstract

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.