Article

Pretraining Diversity and Clinical Metric Optimization Achieve State-of-the-Art Performance on ChestX-ray14

2025-10-27

Abstract excerpt

We achieved state-of-the-art performance on the NIH ChestX-ray14 multi-label classification task using a simple 3-model ensemble: mean ROC-AUC 0.940, F1 0.821 (95% CI: 0.799–0.845), PR-AUC 0.827, sensitivity 76.0%, and specificity 98.8% across 14 thoracic diseases. Our primary finding challenges current research priorities: pretraining diversity dominates architectural diversity . Systematic evaluation of 255 ens...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 712aa323-f3f3-56d3-8017-8775c7343be9
DOI: 10.1101/2025.10.25.25338784

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Pretraining Diversity and Clinical Metric Optimization Achieve State-of-the-Art Performance on ChestX-ray14DOI 10.1101/2025.10.25.25338784Read

Comparative Analysis of Deep Learning Architectures for Multi-Disease Classification of Chest X-raysSemantic proximity Read

The NLP-to-Expert Gap in Chest X-ray AISemantic proximity Read

Cethraian-Shift is a reproducible medical-imaging research project evaluating the cross-dataset reliability, calibration, label-policy sensitivity, and Grad-CAM++ stability of multi-label chest X-ray classifiers across NIH ChestX-ray14 and VinDr-CXRSemantic proximity Read

Developing Deep Learning Models for Classifying Medical Imaging DataSemantic proximity Read

Holistic AI-Driven Quantification, Staging and Prognosis of COVID-19 PneumoniaSemantic proximity Read

Deep-learning convolutional neural networks with transfer learning accurately classify COVID19 lung infection on portable chest radiographsSemantic proximity Read

COVLIAS 3.0 XEDL : Multicentre, Cloud-Based, Explainable Ensemble Artificial Intelligence Deep Learning System for COVID- 19 in Computed Tomography ScansSemantic proximity Read

COVIDScreen: Explainable deep learning framework for differential diagnosis of COVID-19 using chest X-RaysSemantic proximity Read

AI-Driven Computational Models for Lung Cancer Diagnosis: A Systematic Review and Meta-AnalysisSemantic proximity Read

Explainable Hybrid ConvNeXt–Vision Transformer Model for Pneumonia Detection from Chest X-ray ImagesSemantic proximity Read

Beyond Algorithms: The Impact of Simplified CNN Models and Multifactorial Influences on Radiological Image AnalysisSemantic proximity Read

Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT ScansSemantic proximity Read