adammiltonbarker / acute-myeloid-leukemia-classifier-2021

A Tensorflow 2 project based on the research outlined in Human-level recognition of blast cells in the Acute myeloid leukemia with convolutional neural networks paper by Christian Matek, Simone Schwarz, Karsten Spiekermann , and Carsten Marr.

Peter Moss Acute Myeloid & Lymphoblastic Leukemia AI Research Project

Acute Myeloid Leukemia Classifier 2021

 

Table Of Contents

• Introduction
• DISCLAIMER
• Getting Started
• Contributing
  • Contributors
• Versioning
• License
• Bugs/Issues

 

Introduction

Acute Myeloid Leukemia (AML) is a cancer of the blood cells in the Myeloid blood cell lineage. AML is caused by abnormal Myeloid Blasts, or Myeloblasts, produced by the Myeloid progenitors in the bone marrow. Myeloblasts normally develop into healthy red and white blood cells, and platelets which help stop bleeding by forming clots.

Early detection of AML remains an unsolved problem. Our first research project began in 2018 due to Acute Myeloid Leukemia being missed in a routine blood test one month before Peter Moss was diagnosed as terminal. Due to the lack of available datasets we have not been able to work on classifiers for AML.

This project will be our first Acute Myeloid Leukemia project with the goals of developing a Convolutional Neural Networks based on the research proposed in Human-level recognition of blast cells in acute myeloid leukemia with convolutional neural networks by Matek, C., Schwarz, S, Spiekermann, K., Marr, C. CapsNets. The project uses the Single-cell Morphological Dataset of Leukocytes from AML Patients and Non-malignant Controls (AML-Cytomorphology_LMU), a dataset comprised of 18,365 single cell images from peripheral blood smears from 100 AML positive patients and 100 AML negative patients.

 

DISCLAIMER

These projects should be used for research purposes only. The purpose of the projects 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 doctors, medical or cancer experts.

Please use this system responsibly.

 

Getting Started

To get started follow the getting started guide to find out how to fork the repository.

 

Contributing

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.

Contributors

• Adam Milton-Barker - Asociación de Investigacion en Inteligencia Artificial Para la Leucemia Peter Moss President/Founder & Lead Developer, Sabadell, Spain

 

Versioning

We use SemVer for versioning.

 

License

This project is licensed under the MIT License - see the LICENSE file for details.

 

Bugs/Issues

We use the repo issues to track bugs and general requests related to using this project. See CONTRIBUTING for more info on how to submit bugs, feature requests and proposals.