CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning

Abstract

We develop an algorithm that can detect pneumonia from chest X-rays at a level exceeding practicing radiologists. Our algorithm, CheXNet, is a 121-layer convolutional neural network trained on ChestX-ray14, currently the largest publicly available chest X-ray dataset, containing over 100,000 frontal-view X-ray images with 14 diseases. Four practicing academic radiologists annotate a test set, on which we compare the performance of CheXNet to that of radiologists. We find that CheXNet exceeds average radiologist performance on the F1 metric. We extend CheXNet to detect all 14 diseases in ChestX-ray14 and achieve state of the art results on all 14 diseases.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• A systematic study of the class imbalance problem in convolutional neural networks
• Densely Connected Convolutional Networks
• Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
• Learning to diagnose from scratch by exploiting dependencies among labels
• Abnormality Detection and Localization in Chest X-Rays using Deep Convolutional Neural Networks

Cited by in corpus (236)

• Shortcut Learning in Deep Neural Networks
• Confounding variables can degrade generalization performance of radiological deep learning models
• CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images
• COVID-19 Image Data Collection: Prospective Predictions Are the Future
• COVID-CT-Dataset: A CT Scan Dataset about COVID-19
• PadChest: A large chest x-ray image dataset with multi-label annotated reports
• Multitask learning and benchmarking with clinical time series data
• Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization
• Transfusion: Understanding Transfer Learning for Medical Imaging
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
• Weighted boxes fusion: Ensembling boxes from different object detection models
• Development and Validation of a Deep Learning Algorithm for Improving Gleason Scoring of Prostate Cancer
• Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
• Radiological images and machine learning: trends, perspectives, and prospects
• Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning
• What is being transferred in transfer learning?
• An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosis
• Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
• Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoders
• Deep Learning for Automatic Pneumonia Detection
• Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methods
• Clinically Accurate Chest X-Ray Report Generation
• CovidAID: COVID-19 Detection Using Chest X-Ray
• Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors
• Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection
• 3D Self-Supervised Methods for Medical Imaging
• Expert-Augmented Machine Learning
• Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
• Harmony-Search and Otsu based System for Coronavirus Disease (COVID-19) Detection using Lung CT Scan Images
• Adversarial Attacks Against Medical Deep Learning Systems
• ChestNet: A Deep Neural Network for Classification of Thoracic Diseases on Chest Radiography
• Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
• Unsolved Problems in ML Safety
• Split Learning for collaborative deep learning in healthcare
• Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans
• AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation
• Large Scale Automated Reading of Frontal and Lateral Chest X-Rays using Dual Convolutional Neural Networks
• Radiologist-Level COVID-19 Detection Using CT Scans with Detail-Oriented Capsule Networks
• ECOVNet: An Ensemble of Deep Convolutional Neural Networks Based on EfficientNet to Detect COVID-19 From Chest X-rays
• Integrating uncertainty in deep neural networks for MRI based stroke analysis
• SDCT-AuxNet${}^{\theta }$: DCT Augmented Stain Deconvolutional CNN with Auxiliary Classifier for Cancer Diagnosis
• Automatic detection of acute ischemic stroke using non-contrast computed tomography and two-stage deep learning model
• Targeted transfer learning to improve performance in small medical physics datasets
• On the limits of cross-domain generalization in automated X-ray prediction
• Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
• Ensembles of Convolutional Neural Networks models for pediatric pneumonia diagnosis
• Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
• A Survey of Deep Learning for Scientific Discovery
• RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification
• Combinatorial Testing for Deep Learning Systems
• A Review of Predictive and Contrastive Self-supervised Learning for Medical Images
• Defining the scope of AI regulations
• Artificial Intelligence in Glioma Imaging: Challenges and Advances
• Advance Warning Methodologies for COVID-19 using Chest X-Ray Images
• REFLACX, a dataset of reports and eye-tracking data for localization of abnormalities in chest x-rays
• Checklist for responsible deep learning modeling of medical images based on COVID-19 detection studies
• MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models
• Adversarial Examples in Modern Machine Learning: A Review
• Understanding and Improving Information Transfer in Multi-Task Learning
• Early Diagnosis of Pneumonia with Deep Learning
• DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
• Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
• Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks
• Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System
• Stacked Convolutional Neural Network for Diagnosis of COVID-19 Disease from X-ray Images
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art
• Medical Imaging with Deep Learning for COVID- 19 Diagnosis: A Comprehensive Review
• Towards falsifiable interpretability research
• DeepMiner: Discovering Interpretable Representations for Mammogram Classification and Explanation
• The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
• Longitudinal detection of radiological abnormalities with time-modulated LSTM
• A machine learning approach to using Quality-of-Life patient scores in guiding prostate radiation therapy dosing
• Chest X-rays Classification: A Multi-Label and Fine-Grained Problem
• Unsupervised Multimodal Representation Learning across Medical Images and Reports
• COVID-MobileXpert: On-Device COVID-19 Patient Triage and Follow-up using Chest X-rays
• Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia
• Towards Resilient Artificial Intelligence: Survey and Research Issues
• A Performance Comparison of Loss Functions for Deep Face Recognition
• Attention Based Glaucoma Detection: A Large-scale Database and CNN Model
• A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities
• Contrast Enhancement of Medical X-Ray Image Using Morphological Operators with Optimal Structuring Element
• Abnormality Detection in Mammography using Deep Convolutional Neural Networks
• A Deep Q-Network for the Beer Game: A Deep Reinforcement Learning algorithm to Solve Inventory Optimization Problems
• Supervised Transfer Learning at Scale for Medical Imaging
• PaXNet: Dental Caries Detection in Panoramic X-ray using Ensemble Transfer Learning and Capsule Classifier
• Vispi: Automatic Visual Perception and Interpretation of Chest X-rays
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Adversarial regression training for visualizing the progression of chronic obstructive pulmonary disease with chest x-rays
• Lessons from Natural Language Inference in the Clinical Domain
• A Deep Dive into Understanding Tumor Foci Classification using Multiparametric MRI Based on Convolutional Neural Network
• Advances in Deep Space Exploration via Simulators & Deep Learning
• An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
• Justifying Diagnosis Decisions by Deep Neural Networks
• Phronesis of AI in radiology: Superhuman meets natural stupidity
• Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
• CCBlock: An Effective Use of Deep Learning for Automatic Diagnosis of COVID-19 Using X-Ray Images
• Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean
• Transfer Learning for Oral Cancer Detection using Microscopic Images
• COVID-19 detection using chest X-rays: is lung segmentation important for generalization?
• DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images
• Continual Learning for Domain Adaptation in Chest X-ray Classification
• A Survey on Biomedical Image Captioning
• Fine-Tuning and Training of DenseNet for Histopathology Image Representation Using TCGA Diagnostic Slides
• Automatic Diagnosis of Pneumothorax from Chest Radiographs: A Systematic Literature Review
• Using Radiomics as Prior Knowledge for Thorax Disease Classification and Localization in Chest X-rays
• Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
• Quantifying the Value of Lateral Views in Deep Learning for Chest X-rays
• Neuroevolution of Neural Network Architectures Using CoDeepNEAT and Keras
• A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays
• Weakly Supervised Attention Model for RV StrainClassification from volumetric CTPA Scans
• Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
• Evolutionary Neural AutoML for Deep Learning
• Towards Radiologist-Level Accurate Deep Learning System for Pulmonary Screening
• Artificial Intelligence-Based Image Classification for Diagnosis of Skin Cancer: Challenges and Opportunities
• Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification
• Exploring the Effect of Image Enhancement Techniques on COVID-19 Detection using Chest X-rays Images
• Model Selection's Disparate Impact in Real-World Deep Learning Applications
• All Data Inclusive, Deep Learning Models to Predict Critical Events in the Medical Information Mart for Intensive Care III Database (MIMIC III)
• Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs
• Automated Identification of Thoracic Pathology from Chest Radiographs with Enhanced Training Pipeline
• PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain
• Self-Supervised Polyp Re-Identification in Colonoscopy
• Iterative Low-Rank Approximation for CNN Compression
• Classification of COVID-19 in CT Scans using Multi-Source Transfer Learning
• A New Window Loss Function for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation
• A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports
• Local Adaptation Improves Accuracy of Deep Learning Model for Automated X-Ray Thoracic Disease Detection : A Thai Study
• Semi-supervised Learning for Quantification of Pulmonary Edema in Chest X-Ray Images
• XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations
• Deep Mining External Imperfect Data for Chest X-ray Disease Screening
• IVUS-Net: An Intravascular Ultrasound Segmentation Network
• Knowledge Distillation with Adaptive Asymmetric Label Sharpening for Semi-supervised Fracture Detection in Chest X-rays
• Using Deep Networks for Scientific Discovery in Physiological Signals
• Deep Learning for Automated Classification of Tuberculosis-Related Chest X-Ray: Dataset Specificity Limits Diagnostic Performance Generalizability
• Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images
• A clinical validation of VinDr-CXR, an AI system for detecting abnormal chest radiographs
• Bias Field Poses a Threat to DNN-based X-Ray Recognition
• Defending against adversarial attacks on medical imaging AI system, classification or detection?
• Classification of Pneumonia and Tuberculosis from Chest X-rays
• The Utility of Feature Reuse: Transfer Learning in Data-Starved Regimes
• Was there COVID-19 back in 2012? Challenge for AI in Diagnosis with Similar Indications
• Chest X-Rays Image Classification from beta-Variational Autoencoders Latent Features
• Self-transfer learning via patches: A prostate cancer triage approach based on bi-parametric MRI
• Multi-label Ranking: Mining Multi-label and Label Ranking Data
• Pneumonia Detection on Chest X-ray using Radiomic Features and Contrastive Learning
• Evolving Character-level Convolutional Neural Networks for Text Classification
• Explainability Matters: Backdoor Attacks on Medical Imaging
• Abnormality Detection in Musculoskeletal Radiographs with Convolutional Neural Networks(Ensembles) and Performance Optimization
• Flexible Deep Neural Network Processing
• Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
• UMLS-ChestNet: A deep convolutional neural network for radiological findings, differential diagnoses and localizations of COVID-19 in chest x-rays
• MRI Pulse Sequence Integration for Deep-Learning Based Brain Metastasis Segmentation
• Dynamic Routing on Deep Neural Network for Thoracic Disease Classification and Sensitive Area Localization
• HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
• Transgender Community Sentiment Analysis from Social Media Data: A Natural Language Processing Approach
• ContamiNet: Detecting Contamination in Municipal Solid Waste
• Pathology Extraction from Chest X-Ray Radiology Reports: A Performance Study
• Automating Abnormality Detection in Musculoskeletal Radiographs through Deep Learning
• Deformable Gabor Feature Networks for Biomedical Image Classification
• A free web service for fast COVID-19 classification of chest X-Ray images
• Interpretation of Disease Evidence for Medical Images Using Adversarial Deformation Fields
• Learning Image Labels On-the-fly for Training Robust Classification Models
• Uncertainty-driven ensembles of deep architectures for multiclass classification. Application to COVID-19 diagnosis in chest X-ray images
• Predicting Visual Improvement after Macular Hole Surgery: a Cautionary Tale on Deep Learning with Very Limited Data
• Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
• Auditing AI models for Verified Deployment under Semantic Specifications
• Artificial Intelligence for COVID-19 Detection -- A state-of-the-art review
• Reliable Semi-Supervised Learning when Labels are Missing at Random
• Improving Interpretability of Deep Neural Networks in Medical Diagnosis by Investigating the Individual Units
• RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reporting
• RapidRead: Global Deployment of State-of-the-art Radiology AI for a Large Veterinary Teleradiology Practice
• Triple-view Convolutional Neural Networks for COVID-19 Diagnosis with Chest X-ray
• Generalizability of deep learning based fluence map prediction as an inverse planning approach
• Probabilistic combination of eigenlungs-based classifiers for COVID-19 diagnosis in chest CT images
• Deep Learning for Automated Screening of Tuberculosis from Indian Chest X-rays: Analysis and Update
• An Approach to Intelligent Pneumonia Detection and Integration
• Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification
• Predicting Pneumonia and Region Detection from X-Ray Images using Deep Neural Network
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
• Weakly Supervised PET Tumor Detection Using Class Response
• A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
• Artificial Intelligence for Global Health: Learning From a Decade of Digital Transformation in Health Care
• Generalised linear models for prognosis and intervention: Theory, practice, and implications for machine learning
• Extracting and Leveraging Nodule Features with Lung Inpainting for Local Feature Augmentation
• Multi-Task Deep Learning for Legal Document Translation, Summarization and Multi-Label Classification
• Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging
• Semi-supervised learning for medical image classification using imbalanced training data
• Automated Generation of Accurate \& Fluent Medical X-ray Reports
• PZnet: Efficient 3D ConvNet Inference on Manycore CPUs
• MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans
• SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata
• MIINet: An Image Quality Improvement Framework for Supporting Medical Diagnosis
• Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives
• Bimodal network architectures for automatic generation of image annotation from text
• DVNet: A Memory-Efficient Three-Dimensional CNN for Large-Scale Neurovascular Reconstruction
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks
• Studying the Effects of Self-Attention for Medical Image Analysis
• GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps
• EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision
• Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels
• Weighing Features of Lung and Heart Regions for Thoracic Disease Classification
• Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning
• Medical Multimodal Classifiers Under Scarce Data Condition
• Transfer-Learning-Aware Neuro-Evolution for Diseases Detection in Chest X-Ray Images
• Identifying Pediatric Vascular Anomalies With Deep Learning
• Variational Knowledge Distillation for Disease Classification in Chest X-Rays
• End-to-end Generative Zero-shot Learning via Few-shot Learning
• Evaluation of Contemporary Convolutional Neural Network Architectures for Detecting COVID-19 from Chest Radiographs
• Survey of the Detection and Classification of Pulmonary Lesions via CT and X-Ray
• Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies
• Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model
• High resolution weakly supervised localization architectures for medical images
• Extracting and Learning Fine-Grained Labels from Chest Radiographs
• Building a Benchmark Dataset and Classifiers for Sentence-Level Findings in AP Chest X-rays
• Learning to estimate label uncertainty for automatic radiology report parsing
• Classification of COVID-19 from CXR Images in a 15-class Scenario: an Attempt to Avoid Bias in the System
• Learning Visual Context by Comparison
• Pulmonary Disease Classification Using Globally Correlated Maximum Likelihood: an Auxiliary Attention mechanism for Convolutional Neural Networks
• An early prediction of covid-19 associated hospitalization surge using deep learning approach
• Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs
• Convolutional-LSTM for Multi-Image to Single Output Medical Prediction
• Understanding Human Innate Immune System Dependencies using Graph Neural Networks
• Left ventricle segmentation By modelling uncertainty in prediction of deep convolutional neural networks and adaptive thresholding inference
• A Review On Software Defects Prediction Methods
• Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images
• Clustering methods and Bayesian inference for the analysis of the evolution of immune disorders
• FPAENet: Pneumonia Detection Network Based on Feature Pyramid Attention Enhancement
• Informative sample generation using class aware generative adversarial networks for classification of chest Xrays
• A Computer Vision Approach to Combat Lyme Disease
• Pneumothorax and chest tube classification on chest x-rays for detection of missed pneumothorax
• Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning
• OOWL500: Overcoming Dataset Collection Bias in the Wild
• Generalization of Deep Convolutional Neural Networks -- A Case-study on Open-source Chest Radiographs
• Advancement of Deep Learning in Pneumonia and Covid-19 Classification and Localization: A Qualitative and Quantitative Analysis
• Machine Learning for Exam Triage
• Capsule GAN for Prostate MRI Super-Resolution