AI replaces radiologist doctors on diagnosing pneumonia

A group of Artificial Intelligence researchers at Stanford AI Lab used Deep Learning to create an algorithm that can detect pneumonia from chest X-rays at a level exceeding practicing radiologists.

Pneumonia Detection on Chest X-Rays with Artificial Intelligence

An x-ray (radiograph) is a noninvasive medical test that helps physicians diagnose and treat medical conditions. A chest x-ray is an x-ray of the chest showing the shadows of lungs, heart, large arteries, ribs, diaphragm, etc. 

They trained their Deep Learning (AI) algorithm, named CheXNet, using the dataset provided by National Institutes of Health, which contained 112,120 frontal-view X-ray images of 30,805 unique patients, annotated with up to 14 different diseases of the lungs. CheXNet is a convolutional neural network. A convolutional neural network is a type of Deep Learning algorithm which is used to detect and classify images such as photo tagging, face detection, etc.

Their algorithm is a Deep Learning model which inputs a chest X-ray image and outputs the probability of pneumonia along with a heatmap localizing the areas of the image most indicative of pneumonia. Their algorithm is able to detect all 14 diseases in Chest X-ray14 and achieve state of the art results on all 14 diseases.

AI replaces radiologists

They compared the performance of their algorithm to that of radiologist doctors in the detection of pneumonia and their algorithm outperformed doctors as shown in the above image. This is not just the first time that an Artificial Algorithm outperformed a specialist doctor. AI has outperformed dermatologists at diagnosing skin cancer already.

Read their full research paper at 


  1. Amazing world of ML and AI will outperform every human thought..
    Smart docs in the making


Post a Comment

Popular posts from this blog

A simple explanation of Artificial Intelligence for people not belonging to the tech sector.

The best way to deal with depression and anxiety