What You Will Learn

The application uses the inference engine in the Intel Distribution of OpenVINO toolkit. An X-ray image is an input source. A pretrained neural network using an open source dataset detects the probability of pneumonia in preprocessed X-ray images. The inference results are then stored in an output file.

Gain insight into the following solutions:

  • Creating computer vision software applications for healthcare
  • Using computer vision inference for medical image processing

Learn to build and run an application with these capabilities:

Perform an X-ray image classification.

Recognize pneumonia using the pretrained model and predict probability of infection.

Store the probability value in an output file.

How It Works

An open source dataset of labeled chest X-ray images trains a model for pneumonia classification.

X-ray images are preprocessed for input to the inference engine.

The pretrained model uses the inference engine to detect pneumonia within the image and assign a probability value.

The probability value of pneumonia classification is stored in an output file.

flow chart graphic of how the pneumonia classification reference implementation works