Reproducing and Improving CheXNet: Deep Learning for Chest X-ray Disease Classification

Daniel J. Strick, Carlos Garcia, Anthony Huang, Thomas Gardos
5/10/2025
eess.IVcs.CVcs.LG

No official code found. Best implementation: dstrick17/DacNet (18 stars, MIT, last commit 2026-03-24).

Abstract

Deep learning for radiologic image analysis is a rapidly growing field in biomedical research and is likely to become a standard practice in modern medicine. On the publicly available NIH ChestX-ray14 dataset, containing X-ray images that are classified by the presence or absence of 14 different diseases, we reproduced an algorithm known as CheXNet, as well as explored other algorithms that outperform CheXNet's baseline metrics. Model performance was primarily evaluated using the F1 score and AUC-ROC, both of which are critical metrics for imbalanced, multi-label classification tasks in medical imaging. The best model achieved an average AUC-ROC score of 0.85 and an average F1 score of 0.39 across all 14 disease classifications present in the dataset.

View on arXivView PDF

Code Implementations(1)

dstrick17/DacNetCommunity100%
MIT

Reproducing and Improving CheXNet: Deep Learning for Chest X-ray Disease Classification

1811Python, Jupyter NotebookJan 30, 20257 months agoMIT
chestxray14deep-learningdisease-classificationmacro-f1medical-imaging

Similar Papers

Chest Disease Detection In X-Ray Images Using Deep Learning Classification Method

87% match2025

Explainable Knowledge Distillation for On-device Chest X-Ray Classification

86% match2023

SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models for Multi-Label Chest X-Ray Classification

86% match1 repo72023

Machine learning and machine learned prediction in chest X-ray images

86% match2025

Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance

85% match2025

Comparative Evaluation of Radiomics and Deep Learning Models for Disease Detection in Chest Radiography

85% match2025

Cite this paper

@article{strick2025reproducing,
  title  = {Reproducing and Improving CheXNet: Deep Learning for Chest X-ray Disease Classification},
  author = {Daniel J. Strick and Carlos Garcia and Anthony Huang and Thomas Gardos},
  year   = {2025},
  eprint = {2505.06646},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.06646v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.06646.svg)](https://codeofpaper.com/paper/2505.06646)

Discussion