Overview / Usage

Radiology mistakes form 4% of medical errors, which cause many dangerous effects on patients health, including deaths. This project aims to develop an Artificial Intelligence tool that will assist doctors and radiologists in reading x-ray images, in order to prevent diagnosis errors, by classifying and detecting the lungs diseases , it is able to :

1. Differentiate between a healthy lung and a sick one (from X-Ray images)
2. Detect the diseased area
3. Make a diagnosis (classification)

​

Methodology / Approach

We use Deep Learning to classify lung diseases, the project will detect the diseased area in the x-ray image of the person and then classify into: Healthy lung , Pneumonia, Tuberculosis (until now)

Technologies Used

Keras , tensorflow , intel OpenVINO, Intel Xeon CPU, Intel AI Analytics Toolkit (Intel OneAPI) , intel optimization Tensorflow , and intel distribution for python

Collaborators