Using AI to detect fractures

What is Artificial Intelligence?

Artificial Intelligence is the simulation of human intelligence processes by machines, especially computer systems. Specific applications of AI include expert systems, natural language processing (NLP), speech recognition and machine vision.

What is Machine Learning?

Machine Learning is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence. Machine learning algorithms build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to perform the task. Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop a conventional algorithm for effectively performing the task.

My project : Using AI to detect fractures

I want to use Artificial Intelligence and Machine Learning to help radiologists during their daily work.
Thanks to machine learning, we can teach to an Artificial Intelligence to recognize images. So my project is to teach to an Artificial Intelligence how to distinguish a x-ray of a fractured bone from a x-ray of a healthy bone. Thanks to the help of Artificial Intelligence, radiologists could spend less time analyzing x-rays, so they could have more time to help more patients.

1) Explanation :

Firstly, we will give to the Artificial Intelligence many images of x-rays of healthy bones and x-rays of bones with fractures. These images will include x-rays of all bones that a person can fracture, from different points of view. These images will be classified between healthy bones and fractured bones, and then they will be classified according to the type of fracture.

The Artificial Intelligence will learn and keep the images we gave to it in its image database.

Thanks to an algorithm, the AI will be able to compare any image we give to it with all the images that are in its image database. Then, it will be able to distinguish x-rays of healthy bones and x-rays of fractured bones, and to recognize the type of fracture.

Healthy bones // Metacarpus fractured

2) Coding :

We will use ml5.js, a library that provides access to machine learning algorithms and models in the browser. Thanks to the following steps, we can set up ml5.js and MobileNet to classify an image :

CONGRATULATIONS ! NOW YOU CAN CREATE A FRACTURE DETECTOR !

I discovered some interesting articles about the use of Artificial Intelligence to detect fractures :

- A French start-up already created the same kind of Artificial Intelligence : Article : "La startup de la semaine : AZmed, l'intelligence artificielle qui repère les fractures pour les radiologues"

- ScienceDirect also wrote an article about this method : Article : "Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks"