CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 21 Pith papers
-
Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis
CT-Lite combines Feature Attention Style Transfer (FAST) and Structured Factorized Projections (SFP) with contrastive learning to reach AUROC within 5-7% of uncompressed baselines on compressed CT volumes across three...
-
Capabilities of GPT-4 on Medical Challenge Problems
GPT-4 exceeds the USMLE passing score by more than 20 points and outperforms both GPT-3.5 and the medically fine-tuned Med-PaLM on the MultiMedQA benchmarks.
-
Building a Benchmark Dataset and Classifiers for Sentence-Level Findings in AP Chest X-rays
The paper introduces a new benchmark dataset with 73 sentence-level descriptors for AP chest X-ray findings obtained via crowdsourcing and demonstrates deep learning classifiers trained on them.
-
Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
Scaling vision models by depth and parameter count does not consistently improve localisation-based explanation quality across architectures, datasets, and post-hoc methods; smaller models often perform comparably or better.
-
JDCNet: Confidence-Gated Privileged-Modality Distillation for Cost-Preserving X-ray Inference
JDCNet improves X-ray classification by gating CT distillation to high-confidence samples, beating the supervised baseline and other distillation methods on a 510-patient paired cohort with 5-fold CV.
-
Deep Learning for MRI Slice Interpolation: The Critical Role of Problem Formulation
Reformulating the input to adjacent slices for deep learning MRI interpolation yields 58% SSIM gains and 10.1% improvement over linear baseline, with problem formulation outweighing architecture choice.
-
Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
Higher-resolution observations with global-average-pooling encoders improve RL performance and generalization by enabling more localized visual attention, yielding up to 28% gains over standard Impala encoders.
-
A Unified Open-Set Framework for Scalable PUF-Based Authentication of Heterogeneous IoT Devices
A scalable helper-data-free open-set PUF authentication framework using OpenGAN unifies heterogeneous PUF responses for 100% closed-set accuracy and near-zero open-set errors with up to 45 devices.
-
Grounded Multimodal Retrieval-Augmented Drafting of Radiology Impressions Using Case-Based Similarity Search
A case-based multimodal RAG system for chest radiograph impressions achieves Recall@5 above 0.95 and produces citation-traceable drafts.
-
Justifying Diagnosis Decisions by Deep Neural Networks
A multi-task deep learning model maps frontal X-rays to continuous text for producing diagnoses, textual justifications, and alternative images, with expert study showing better justification than saliency maps.
-
On-Device Continual Learning with Dual-Stage Buffer and Dynamic Loss for Point-of-Care Pneumonia Diagnosis
PneumoNet uses a lightweight CNN, dual-stage balanced buffer, and dynamic class-weighted loss for domain-incremental learning on simulated PneumoniaMNIST shifts, reporting 86.6% accuracy and 1.4% forgetting.
-
Domain Incremental Learning for Pandemic-Resilient Chest X-Ray Analysis
A class-aware replay method for domain-incremental learning reaches 88.66% average accuracy on five simulated domain shifts in PneumoniaMNIST, beating standard replay, fine-tuning, and joint training.
-
Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings
The study shows clinical AI accuracy collapsing from 89% to 62% on X-rays under imperceptible adversarial perturbations and from 85% to 55% on clinical cases in Nigerian Pidgin and Yoruba-inflected English.
-
Explanation-Aware Learning for Enhanced Interpretability in Biomedical Imaging
Adding explanation supervision to training improves spatial alignment of saliency maps with clinical annotations on chest X-rays while keeping predictive accuracy comparable.
-
Improving Imbalanced Multi-Label Chest X-Ray Diagnosis via CBAM-Enhanced CNN Backbones
CBAM-enhanced CNN backbones reach a mean AUC of 0.8695 on the ChestXray14 dataset for imbalanced multi-label chest X-ray pathology classification, outperforming listed baselines.
-
Momentum-Anchored Multi-Scale Fusion Model for Long-Tailed Chest X-Ray Classification
A new neural network stabilizes features for rare chest X-ray diseases via momentum anchoring and multi-scale fusion on EfficientNet, achieving 0.8682 AUC on ChestX-ray14.
-
Advance Warning Methodologies for COVID-19 using Chest X-Ray Images
Introduces the Early-QaTa-COV19 dataset and reports that CSEN reaches over 97% sensitivity and over 95.5% specificity for early COVID-19 detection from X-rays.
-
Convolutional Sparse Support Estimator Based Covid-19 Recognition from X-ray Images
Introduces CSEN, a non-iterative network bridging sparse representation and deep learning, for Covid-19 detection from X-ray images with limited training data.
-
CBAM-Enhanced DenseNet121 for Multi-Class Chest X-Ray Classification with Grad-CAM Explainability
CBAM-DenseNet121 reaches 84.29% mean test accuracy on three-class chest X-ray classification with Grad-CAM visualizations showing plausible lung regions.
-
The Paradox of Professional Input: How Expert Collaboration with AI Systems Shapes Their Future Value
Expert collaboration with AI risks automating professional roles through knowledge externalization but simultaneously enables evolution of expertise and emergence of new professional value forms.
-
Developing an App to interpret Chest X-rays to support the diagnosis of respiratory pathology with Artificial Intelligence
Development of a mobile app using an ANN to interpret chest X-rays for respiratory pathology diagnosis.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.