• Anglesey, Wales

Acute Lymphoblastic Leukaemia Detection System For Magic Leap 1

Community Project

The Magic Leap Acute Lymphoblastic Leukaemia (ALL) Detection System is a Mixed Reality application for Magic Leap that interfaces with a Convolutional Neural Network to provide real-time detection of ALL in a Mixed Reality Environment.

project-image
project-image
project-image
project-image

 

About this project

Mixed Reality diagnostics system including integration with open-source classifier for Acute Lymphoblastic Leukaemia.

The Magic Leap Acute Lymphoblastic Leukaemia (ALL) Detection System uses the Magic Leap 1 headset to display microscopic images of blood samples containing ALL positive and negative samples in Mixed Reality. The project combines Mixed Reality with Artificial Intelligence to provide a real-time detection system capable of detecting ALL positive and negative samples.

The classifier is developed using Intel® Distribution for Python* and Intel® Optimization for TensorFlow*, and deployed to a Raspberry Pi 4 using Intel® Distribution of OpenVINO™ Toolkit. Inference is carried out using the Intel® Neural Compute Stick 2 (Intel® NCS2)

The classifier is connected to the HIAS iotJumpWay MQTT broker, requests are authenticated using the HIAS private blockchain via the MQTT IoT Agent, and classifications are stored in the historical database along with a hash of the classification for data integrity. The IoT Agent stores contextual data of the classifier in the HIASCDI Context Broker.

Technologies Used

  • Intel® Distribution for Python*
  • Intel® Optimization for TensorFlow*
  • Intel® Distribution of OpenVINO™ Toolkit
  • Intel® Neural Compute Stick 2
  • Raspberry Pi 4
  • Magic Leap 1
  • Unity