ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases

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. Data download link: https://nihcc.app.box.com/v/ChestXray-NIHCC

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

References in corpus (1)

• Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalities

Cited by in corpus (185)

• The Future of Digital Health with Federated Learning
• Can AI help in screening Viral and COVID-19 pneumonia?
• Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks
• CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images
• Domain Generalization: A Survey
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• Domain Adaptation for Medical Image Analysis: A Survey
• A Unifying Review of Deep and Shallow Anomaly Detection
• Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection using Chest X-ray
• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
• MedViT: A Robust Vision Transformer for Generalized Medical Image Classification
• DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs
• MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
• Extracting possibly representative COVID-19 Biomarkers from X-Ray images with Deep Learning approach and image data related to Pulmonary Diseases
• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• A Review on Deep Learning Techniques for the Diagnosis of Novel Coronavirus (COVID-19)
• Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing
• A Survey of Privacy Attacks in Machine Learning
• Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data
• Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training
• Towards an Effective and Efficient Deep Learning Model for COVID-19 Patterns Detection in X-ray Images
• Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging
• Automatic Lung Cancer Prediction from Chest X-ray Images Using Deep Learning Approach
• Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks
• Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoders
• Deep Learning for Automatic Pneumonia Detection
• Deep Learning with Lung Segmentation and Bone Shadow Exclusion Techniques for Chest X-Ray Analysis of Lung Cancer
• Learning Hierarchical Attention for Weakly-supervised Chest X-Ray Abnormality Localization and Diagnosis
• Computer Vision For COVID-19 Control: A Survey
• Convolutional Sparse Support Estimator Based Covid-19 Recognition from X-ray Images
• Do Gradient Inversion Attacks Make Federated Learning Unsafe?
• Recent Progress in Transformer-based Medical Image Analysis
• Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports
• Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
• Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification
• A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound
• Reinventing 2D Convolutions for 3D Images
• COVID-19 Infection Map Generation and Detection from Chest X-Ray Images
• Chest X-Ray Analysis of Tuberculosis by Deep Learning with Segmentation and Augmentation
• Active label cleaning for improved dataset quality under resource constraints
• Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing
• Ontology-driven weak supervision for clinical entity classification in electronic health records
• A novel framework based on deep learning and ANOVA feature selection method for diagnosis of COVID-19 cases from chest X-ray Images
• OSegNet: Operational Segmentation Network for COVID-19 Detection using Chest X-ray Images
• Learning Deformable Registration of Medical Images with Anatomical Constraints
• Deep Learning-based Patient Re-identification Is able to Exploit the Biometric Nature of Medical Chest X-ray Data
• CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training
• Self-supervised deep convolutional neural network for chest X-ray classification
• Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset
• Automated Radiology Report Generation: A Review of Recent Advances
• XNet: A convolutional neural network (CNN) implementation for medical X-Ray image segmentation suitable for small datasets
• Exploring scalable medical image encoders beyond text supervision
• An Adaptive and Altruistic PSO-based Deep Feature Selection Method for Pneumonia Detection from Chest X-Rays
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
• Manual segmentation versus semi-automated segmentation for quantifying vestibular schwannoma volume on MRI
• Targeted transfer learning to improve performance in small medical physics datasets
• Diagnosis of COVID-19 Using Machine Learning and Deep Learning: A review
• Attention-based Saliency Maps Improve Interpretability of Pneumothorax Classification
• COVID-19 in CXR: from Detection and Severity Scoring to Patient Disease Monitoring
• Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images
• Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• Enhancing Representation in Radiography-Reports Foundation Model: A Granular Alignment Algorithm Using Masked Contrastive Learning
• Advance Warning Methodologies for COVID-19 using Chest X-Ray Images
• Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases
• REFLACX, a dataset of reports and eye-tracking data for localization of abnormalities in chest x-rays
• Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study
• Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges
• Dimensionality Reduction in Deep Learning for Chest X-Ray Analysis of Lung Cancer
• Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays
• Decision and Feature Level Fusion of Deep Features Extracted from Public COVID-19 Data-sets
• Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
• Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering
• CXR-Net: An Encoder-Decoder-Encoder Multitask Deep Neural Network for Explainable and Accurate Diagnosis of COVID-19 pneumonia with Chest X-ray Images
• Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs
• Deep Learning to Quantify Pulmonary Edema in Chest Radiographs
• Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
• CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images
• Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms
• Evaluating the Performance of StyleGAN2-ADA on Medical Images
• Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
• Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
• The Clever Hans Effect in Unsupervised Learning
• Explainable Knowledge Distillation for On-device Chest X-Ray Classification
• Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
• Weakly Supervised Universal Fracture Detection in Pelvic X-rays
• Multi-Label Chest X-Ray Classification via Deep Learning
• Collaborative Training of Medical Artificial Intelligence Models with non-uniform Labels
• Evaluation of GPT-4 for chest X-ray impression generation: A reader study on performance and perception
• Longitudinal detection of radiological abnormalities with time-modulated LSTM
• Detecting Shortcuts in Medical Images -- A Case Study in Chest X-rays
• Lesion Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale
• SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models for Multi-Label Chest X-Ray Classification
• VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels
• Mind the Gap: Federated Learning Broadens Domain Generalization in Diagnostic AI Models
• Improving Representation of High-frequency Components for Medical Visual Foundation Models
• When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks
• Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
• Integration of nested cross-validation, automated hyperparameter optimization, high-performance computing to reduce and quantify the variance of test performance estimation of deep learning models
• Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images
• MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
• LT-ViT: A Vision Transformer for multi-label Chest X-ray classification
• An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation
• PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation
• Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend
• Deep learning classification of chest x-ray images
• ThoraX-PriorNet: A Novel Attention-Based Architecture Using Anatomical Prior Probability Maps for Thoracic Disease Classification
• Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training
• Performance of GAN-based augmentation for deep learning COVID-19 image classification
• In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review
• Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation
• Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels
• Enhancing the vision-language foundation model with key semantic knowledge-emphasized report refinement
• Reliable COVID-19 Detection Using Chest X-ray Images
• COVID-19 detection using chest X-rays: is lung segmentation important for generalization?
• 2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data
• Joint Learning of Localized Representations from Medical Images and Reports
• Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images
• RadEdit: stress-testing biomedical vision models via diffusion image editing
• Adversarial Pulmonary Pathology Translation for Pairwise Chest X-ray Data Augmentation
• Few-shot learning for COVID-19 Chest X-Ray Classification with Imbalanced Data: An Inter vs. Intra Domain Study
• Foundation Ark: Accruing and Reusing Knowledge for Superior and Robust Performance
• An Explainable Contrastive-based Dilated Convolutional Network with Transformer for Pediatric Pneumonia Detection
• CheXternal: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays and External Clinical Settings
• ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning
• Automatic Diagnosis of Pneumothorax from Chest Radiographs: A Systematic Literature Review
• When Federated Learning Meets Quantum Computing: Survey and Research Opportunities
• Treatment Learning Causal Transformer for Noisy Image Classification
• Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification
• Rethinking model prototyping through the MedMNIST+ dataset collection
• Lung segmentation on chest x-ray images in patients with severe abnormal findings using deep learning
• Automated Enriched Medical Concept Generation for Chest X-ray Images
• Lung Structures Enhancement in Chest Radiographs via CT based FCNN Training
• Learning to Generalize towards Unseen Domains via a Content-Aware Style Invariant Model for Disease Detection from Chest X-rays
• How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
• M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation
• Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations
• Adaptive Image-Feature Learning for Disease Classification Using Inductive Graph Networks
• Zero-Shot Pediatric Tuberculosis Detection in Chest X-Rays using Self-Supervised Learning
• Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning
• Tubular Shape Aware Data Generation for Semantic Segmentation in Medical Imaging
• A two-step explainable approach for COVID-19 computer-aided diagnosis from chest x-ray images
• Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods
• Automated Identification of Thoracic Pathology from Chest Radiographs with Enhanced Training Pipeline
• Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation
• R2C-GAN: Restore-to-Classify Generative Adversarial Networks for Blind X-Ray Restoration and COVID-19 Classification
• Using Multiple Instance Learning for Explainable Solar Flare Prediction
• Enhancing medical vision-language contrastive learning via inter-matching relation modelling
• Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling
• Structure Causal Models and LLMs Integration in Medical Visual Question Answering
• EfficientNet Algorithm for Classification of Different Types of Cancer
• Multi-label Ranking: Mining Multi-label and Label Ranking Data
• Domain Adaptation Techniques for Natural and Medical Image Classification
• Improving Image Classification of Knee Radiographs: An Automated Image Labeling Approach
• Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis
• Chest X-Rays Image Classification from beta-Variational Autoencoders Latent Features
• All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images
• Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification
• Explainable Disease Classification via weakly-supervised segmentation
• Learning to diagnose common thorax diseases on chest radiographs from radiology reports in Vietnamese
• Artificially Generated Visual Scanpath Improves Multi-label Thoracic Disease Classification in Chest X-Ray Images
• RadTex: Learning Efficient Radiograph Representations from Text Reports
• An Automated Approach for Timely Diagnosis and Prognosis of Coronavirus Disease
• HyDA: Hypernetworks for Test Time Domain Adaptation in Medical Imaging Analysis
• Using Backbone Foundation Model for Evaluating Fairness in Chest Radiography Without Demographic Data
• VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification
• ISLE: An Intelligent Streaming Framework for High-Throughput AI Inference in Medical Imaging
• Investigating Privacy Leakage in Dimensionality Reduction Methods via Reconstruction Attack
• Classification of Chest Diseases using Wavelet Transforms and Transfer Learning
• Classification of Multiple Diseases on Body CT Scans using Weakly Supervised Deep Learning
• MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference
• CIRCA: comprehensible online system in support of chest X-rays-based COVID-19 diagnosis
• MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matching
• Personalized Semi-Supervised Federated Learning for Human Activity Recognition
• OOOE: Only-One-Object-Exists Assumption to Find Very Small Objects in Chest Radiographs
• DiffusionXRay: A Diffusion and GAN-Based Approach for Enhancing Digitally Reconstructed Chest Radiographs
• Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learning
• Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
• Comparative Analysis of Deep Learning Architectures for Multi-Disease Classification of Single-Label Chest X-rays
• Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs
• Augmenting Chest X-ray Datasets with Non-Expert Annotations