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

TL;DR

CheXNet is a deep learning model that surpasses radiologists in pneumonia detection on chest X-rays and achieves state-of-the-art results across 14 diseases using a large dataset.

Contribution

The paper introduces CheXNet, a 121-layer CNN trained on the largest chest X-ray dataset, achieving radiologist-level performance and state-of-the-art results for multiple diseases.

Findings

CheXNet exceeds radiologist performance on pneumonia detection.

Achieves state-of-the-art results on all 14 diseases in ChestX-ray14.

Uses a large dataset of over 100,000 images for training.

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.