ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases

2017/05/31 by Xiaosong Wang, Yifan Peng, Le Lu +3 · 10 citations
Computer Science · Medicine · #COVID-19 diagnosis using AI #Contextual image classification #Convolutional neural network #DICOM #Deep learning #Lung Cancer Diagnosis and Treatment #Medical imaging #Radiological weapon #Radiomics and Machine Learning in Medical Imaging #Thoracic diseases #Thorax (insect anatomy) #cs.CL #cs.CV

paper · pdf · doi:10.1109/cvpr.2017.369

published as IEEE CVPR 2017, pp. 2097-2106 (2017) · CVPR 2017 spotlight;V1: CVPR submission+supplementary; V2: Statistics and benchmark results on published ChestX-ray14 dataset are updated in Appendix B V3: Minor correction V4: new data download link upated: https://nihcc.app.box.com/v/ChestXray-NIHCC V5: Update benchmark results on the published data split in the appendix

openalex created_date 2017/05/12 · openalex publication_date 2017/07/01 · arxiv created 2017/12/14 · arxiv updated 2019/02/01 · openalex updated_date 2026/08/05

Abstract

The chest X-ray is one of the most commonly accessible radiological examinations for screening and diagnosis of many lung diseases. A tremendous number of X-ray imaging studies accompanied by radiological reports are accumulated and stored in many modern hospitals Picture Archiving and Communication Systems (PACS). On the other side, it is still an open question how this type of hospital-size knowledge database containing invaluable imaging informatics (i.e., loosely labeled) can be used to facilitate the data-hungry deep learning paradigms in building truly large-scale high precision computer-aided diagnosis (CAD) systems. In this paper, we present a new chest X-ray database, namely ChestX-ray8, which comprises 108,948 frontal-view X-ray images of 32,717 unique patients with the text-mined eight disease image labels (where each image can have multi-labels), from the associated radiological reports using natural language processing. Importantly, we demonstrate that these commonly occurring thoracic diseases can be detected and even spatially-located via a unified weakly-supervised multi-label image classification and disease localization framework, which is validated using our proposed dataset. Although the initial quantitative results are promising as reported, deep convolutional neural network based reading chest X-rays (i.e., recognizing and locating the common disease patterns trained with only image-level labels) remains a strenuous task for fully-automated high precision CAD systems.

Citations

• Show and tell: A neural image caption generator
• ImageNet Large Scale Visual Recognition Challenge
• Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks

Cited by

• Differential privacy representation geometry for medical image analysis
• A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling
• Parameter-efficient Quantum Multi-task Learning
• MedGemma 1.5 Technical Report
• Bayesian Autoencoder for Medical Anomaly Detection: Uncertainty-Aware Approach for Brain 2 MRI Analysis
• CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
• A survey on incorporating domain knowledge into deep learning for medical image analysis
• Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels
• A Multimodal Biomedical Foundation Model Trained from Fifteen Million Image–Text Pairs
• DeepSeeNet: A Deep Learning Model for Automated Classification of Patient-based Age-related Macular Degeneration Severity from Color Fundus Photographs
• Benchmark Evaluation of Federated Learning on Multi-organ Images