Article

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-CXR

2026-08-06

Abstract excerpt

<title>Abstract</title> <p>Background Cross-dataset evaluation can expose changes in discrimination, calibration, label-policy sensitivity, and post-hoc localization that are not visible in internal validation alone. Methods Three ImageNet-initialized DenseNet-121 classifiers were trained only on the NIH ChestX-ray14 development partition for six findings using seeds 42, 1337, and 2026. Frozen checkpoints were...

Topics

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

Identifiers and source

Literature Corpus work: d6a5345b-e7f8-5bd4-bc48-3771124f8325
DOI: 10.21203/rs.3.rs-10552860/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

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-CXRDOI 10.21203/rs.3.rs-10552860/v1Read

Pretraining Diversity and Clinical Metric Optimization Achieve State-of-the-Art Performance on ChestX-ray14Semantic proximity Read

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

Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic DataSemantic proximity Read

AI-Assisted Pneumonia Detection, Localisation and Report Generation from Chest X-raysSemantic proximity Read

HybridNet-XR: Efficient Teacher-Free Self-Supervised Learning for Autonomous Medical Diagnostic Systems in Resource-Constrained EnvironmentsSemantic proximity Read

The Challenge Dataset – simple evaluation for safe, transparent healthcare AI deploymentSemantic proximity Read

Validation of expert system enhanced deep learning algorithm for automated screening for COVID-Pneumonia on chest X-raysSemantic proximity Read

MedSAM2-CXR: A Box-Latent Framework for Chest X-ray Classification and Report GenerationSemantic proximity Read

COVID-19 detection and disease progression visualization: Deep learning on chest X-rays for classification and coarse localizationSemantic proximity Read

Integrating multi-scale cross-attention and graph-guided label reasoning for multi-label chest X-ray classificationSemantic proximity Read

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

Algorithmic encoding of protected characteristics in chest X-ray disease detection modelsSemantic proximity Read