- Introduction
- DISCLAIMER
- Intel® DevMesh AI Spotlight Award
- Projects
- Intel® Technologies
- Related Events
- Related Team Publications
- Contributing
- Versioning
- License
- Bugs/Issues
The Peter Moss Acute Myeloid & Lymphoblastic Leukemia Detection System is an opensource classifier with a locally hosted, database driven UI for data management, training, and running inference on Convolutional Neural Networks on the edge. This project was our official demo for 2019 and leverages Intel® technologies such as the UP2/UP2 AI Vision Dev Kit and Movidius NCS.
This project is made up of a number of components which work together to provide a locally hosted management system. Follow the completed tutorials below in the provided order. A full system setup requires Server, Facial-Auth, Data Augmentation, NCS1 Tensorflow Classifier, and Chatbot.
This project should be used for research purposes only. The purpose of the project is to show the potential of Artificial Intelligence for medical support systems such as diagnosis systems.
Although the classifier is accurate and shows good results both on paper and in real world testing, it is not meant to be an alternative to professional medical diagnosis.
Developers that have contributed to this repository have experience in using Artificial Intelligence for detecting certain types of cancer. They are not a doctors, medical or cancer experts.
Please use these systems responsibly.
In 2019 the Acute Lymphoblastic Leukemia Detection System 2019 was awarded the Intel® Devmesh AI Spotlight Award. Our project was one of 4 projects, and 1st from Europe, awarded the then new designation granted by Intel recognizing inspiring and breakthrough Artificial Intelligence projects in development from the Intel software community.
| Project | Description | Status |
|---|---|---|
| Server | A local PHP/MySQL server hosting a web based UI for managing and classifying data. Based on the GeniSysAI Server. | Complete |
| Facial-Auth | Siamese Neural Networks used for facial authentication. Hosts a REST API endpoint that exposes the model for remote classification. | Complete |
| Augmentation | Applies filters to the original dataset and increases the amount of training data used for the NCS1 Tensorflow Classifier. | Complete |
| NCS1 Tensorflow Classifier | The Acute Lyphoblastic Leukemia Detection System 2019 Tensorflow NCS1 Classifier, using NCS & NCSDK. Hosts a REST API endpoint that exposes the model for remote classification. | Complete |
| Chatbot | A Tensorflow Natural Language Understanding Engine trained with basic knowledge of AML. Hosts a REST API endpoint that exposes the model for remote classification | Complete |
UP Squared & Movidius NCS1.
This project uses various Intel® technologies such as UP2, Intel® Movidius Neural Compute Stick 1 and Intel® AI DevCloud to enhance the training process and combine powerful CNNs with edge technologies for Internet of Things networks.
A number of our team members are Intel® Software Innovators, part of an Intel® program that supports independent developers with the latest Intel® hardware/software, speakerships & event opportunities, as well as technical advice and support through the various on and offline communities.
| Event | Description |
|---|---|
| Embedded World in Nuremberg Germany | In February 2019, team members Adam Milton-Barker and Estela Cabezas demonstrated the Peter Moss Acute Lymphoblastic Leukemia Detection System 2019 at Embedded World at the Intel®'s booths area. |
| Intel® Developer Affinity Day in Munich Germany | In May 2019 Estela Cabezas represented the team and presented our project an invite only event at Intel® GmbH in Munich Germany. |
-
Applied Analytics for clinical decision support (Bachelor Thesis) - Estela Cabezas
-
Acute Myeloid/Lymphoblastic Leukemia Data Augmentation (Intel® AI Developer Program) - Adam Milton-Barker
-
Inception V3 Deep Convolutional Architecture For Classifying Acute Myeloid/Lymphoblastic Leukemia (Intel® AI Developer Program) - Adam Milton-Barker
The Peter Moss Acute Myeloid & Lymphoblastic Leukemia AI Research project encourages and welcomes code contributions, bug fixes and enhancements from the Github.
Please read the CONTRIBUTING document for a full guide to forking our repositories and submitting your pull requests. You will also find information about our code of conduct on this page.
- Adam Milton-Barker - Asociacion De Investigation En Inteligencia Artificial Para La Leucemia Peter Moss President & Lead Developer, Sabadell, Spain
We use SemVer for versioning. For the versions available, see Releases.
This project is licensed under the MIT License - see the LICENSE file for details.
We use the repo issues to track bugs and general requests related to using this project.