HIAS Acute Lymphoblastic Leukemia Detection System
Community Project
A Convolutional Neural Network developed using the Intel® Distribution for Python* and Intel® Optimization for TensorFlow*. The model is deployed on a Raspberry 4 using Intel® Distribution of OpenVINO™ Toolkit and inference is carried out using the Intel® Neural Compute Stick 2 (Intel® NCS2).
-
Category
About this project
A web based diagnostics system including integration with open-source classifier for Acute Lymphoblastic Leukaemia.
The HIAS Acute Lymphoblastic Leukemia Detection System (CNN) is based on the oneAPI Acute Lymphoblastic Leukemia Classifier, following the proposed architecture in the Acute Leukemia Classification Using Convolution Neural Network In Clinical Decision Support System paper and using the Acute Lymphoblastic Leukemia Image Database for Image Processing dataset. The classifier achieves 98% accuracy at detecting Acute Lymphoblastic Leukemia in unseen data.
The model 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 project is an addon for the HIAS Network, one of the core Peter Moss Leukaemia MedTech Research projects. The project can be provisioned using the HIAS UI and data can be sent from the UI to the classifier for classification.
Technologies Used
- Intel® Distribution for Python*
- Intel® Optimization for TensorFlow*
- Intel® Distribution of OpenVINO™ Toolkit
- Intel® Neural Compute Stick 2
- Raspberry Pi 4
