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

11/14/2017

∙

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 pneumonia detection on both sensitivity and specificity. We extend CheXNet to detect all 14 diseases in ChestX-ray14 and achieve state of the art results on all 14 diseases.

READ FULL TEXT

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

Deep learning classification of chest x-ray images

Context Learning for Bone Shadow Exclusion in CheXNet Accuracy Improvement

Large Scale Automated Reading of Frontal and Lateral Chest X-Rays using Dual Convolutional Neural Networks

PneumoXttention: A CNN compensating for Human Fallibility when Detecting Pneumonia through CXR images with Attention

CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays

Detection of distal radius fractures trained by a small set of X-ray images and Faster R-CNN

Learning what to look in chest X-rays with a recurrent visual attention model

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

Related Research

Deep learning classification of chest x-ray images

Context Learning for Bone Shadow Exclusion in CheXNet Accuracy Improvement

Large Scale Automated Reading of Frontal and Lateral Chest X-Rays using Dual Convolutional Neural Networks

PneumoXttention: A CNN compensating for Human Fallibility when Detecting Pneumonia through CXR images with Attention

CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays

Detection of distal radius fractures trained by a small set of X-ray images and Faster R-CNN

Learning what to look in chest X-rays with a recurrent visual attention model