Giter Club home page Giter Club logo

amlresearchproject / all-classifiers-2019 Goto Github PK

View Code? Open in Web Editor NEW
31.0 8.0 18.0 184.79 MB

A collection of computer vision projects for Acute Lymphoblastic Leukemia classification/early detection.

Home Page: https://www.petermossamlallresearch.com/research/

License: MIT License

Python 3.47% Jupyter Notebook 96.51% Shell 0.02%
artificial-intelligence artificial-neural-networks artificial-intelligence-algorithms computer-vision convolutional-neural-networks deep-neural-networks lymphoblastic-leukemia-classifiers intel-movidius caffe fastai data-augmentation python-classifiers openvino

all-classifiers-2019's Introduction

Peter Moss Acute Myeloid & Lymphoblastic Leukemia AI Research Project

Acute Lymphoblastic Leukemia Classifiers 2019

Peter Moss Acute Myeloid & Lymphoblastic Leukemia AI Research Project

CURRENT RELEASE UPCOMING RELEASE Issues Welcome! Issues LICENSE

 

Table Of Contents

 

Introduction

The Peter Moss Acute Lymphoblastic Leukemia classifiers are a collection of projects that use computer vision to classify Acute Lymphoblastic Leukemia (ALL) in unseen images.

This repository includes classifier projects made with Tensorflow, Caffe, Keras, FastAI & Intel Movidius (NCS).

 

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 classifiers are accurate and show good results both on paper and in real world testing, they are 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.

Salvatore Raieli is a bioinformatician researcher and PhD in Immunology, but does not work in medical diagnosis.

Dr Amita Kapoor is Associate Professor at SRCASW, University of Delhi, and teaches Neural Networks, Artificial Intelligence, Operating system, Embedded system, Computer Communication and Networking.

Please use these systems responsibly.

 

Projects

This repository hosts a collection of classifiers that have been developed by the team using the Python programming language. These classifiers include Caffe, FastAI, Movidius NCS1 and Keras classifiers, each project may have multiple classifiers.

Projects Description Status Author
Data Augmentation Applies filters to datasets and increases the amount of training / test data. Complete Adam Milton-Barker
AllCNN Caffe Classifier Acute Lymphoblastic Leukemia classifier created using the Caffe framework. Ongoing Adam Milton-Barker
Movidius NCS Classifier Acute Lymphoblastic Leukemia classifier created using the Intel Movidius NCS. Complete Adam Milton-Barker
FastAI Resnet50 Classifier Acute Lymphoblastic Leukemia classifier created using FastAI & Resnet50. Complete Salvatore Raieli
FastAI Resnet50(a) Classifier Acute Lymphoblastic Leukemia classifier created using FastAI & Resnet50. Complete Adam Milton-Barker
FastAI Resnet34 Classifier Acute Lymphoblastic Leukemia classifier created using FastAI & Resnet34. Complete Salvatore Raieli
FastAI Resnet18 Classifier Acute Lymphoblastic Leukemia classifier created using FastAI & Resnet18. Complete Salvatore Raieli
QuantisedCode Acute Lymphoblastic Leukemia classifier created using Keras with Tensorflow Backend, Paper 1 and the original Dataset 2. Complete Dr Amita Kapoor & Taru Jain
AllCNN Acute Lymphoblastic Leukemia classifier created using Keras with Tensorflow Backend, Paper 1 and the original Dataset 1. Complete Adam Milton-Barker
AllCNN Acute Lymphoblastic Leukemia classifier created using Keras with Tensorflow Backend, Paper 1 and the original Dataset 2. Ongoing Adam Milton-Barker

 

Team Publications

A series of articles / tutorials by Adam Milton-Barker that take you through attempting to replicate the work carried out in the Acute Myeloid Leukemia Classification Using Convolution Neural Network In Clinical Decision Support System paper.

 

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

Students Contributors

 

Versioning

We use SemVer for versioning. For the versions available.

 

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.

all-classifiers-2019's People

Contributors

adammiltonbarker avatar salvatorera avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

all-classifiers-2019's Issues

KeyError: 'layerFile' issue

Describe the bug
While following the steps as mentioned in the article- https://software.intel.com/en-us/articles/detecting-acute-lymphoblastic-leukemia-using-caffe-openvino-neural-compute-stick-2-part-1?fbclid=IwAR15wmR-qw10GfVuaswuLV6RGcPqx3PLyXY8x1gLEv_ijdyxjkfwOHcapQA , I tried running the command to check the Network configuration using python Info.py NetworkInfo, and that's when I got the error. Logs provided in later section.

To Reproduce
Steps to reproduce the behavior:

  1. Follow the steps up till installing any requirements using Setup.sh and then check the network config.
  2. See error

Expected behavior
Should have worked as intended,i.e. show the network being created properly.

Actual behavior
python Info.py NetworkInfo
2019-03-20 23:31:51|allCNN|Status: Init complete
Traceback (most recent call last):
File "Info.py", line 177, in
main(sys.argv[1:])
File "Info.py", line 155, in main
allCNN.loadCaffeNet()
File "Info.py", line 62, in loadCaffeNet
self.net = caffe.Net(self.confs["Settings"]["Classifier"]["layerFile"], caffe.TEST)

Desktop (please complete the following information):

  • OS: [Ubuntu 16.04 LTS]
  • Hardware: [UP2 Board]

Change contributors section in page footers

Is your feature proposal related to a problem? Please describe.
Currently no place for Student Program contributors in the page footers.

Describe the solution you'd like to submit

  • Split the contributors section at the bottom of pages in the footer into two categories:
    -- Team
    -- Students & Research Interns

  • Add Taru to Students & Research Intern contributors

Describe alternatives you've considered (If any)
NA

Additional context
NA

Augmentation upgrade

  • Update augmentation to latest version.
  • Change background color of augmented images (rotated and translated)
  • Update augmentation banner to show new augmentations

Movidius Inception Classifier

Trainer, classifier and tutorial using the dataset from the Python Data Augmentation tutorial, Intel AI DevCloud for training and Movidius / UP2 for inference.

Keras model based on the ACUTE LEUKEMIA CLASSIFICATION USING CONVOLUTION NEURAL NETWORK IN CLINICAL DECISION SUPPORT SYSTEM paper

Is your feature proposal related to a problem? Please describe.
No

Describe the solution you'd like to submit
Create a Keras classifier based on the ACUTE LEUKEMIA CLASSIFICATION USING CONVOLUTION NEURAL NETWORK IN CLINICAL DECISION SUPPORT SYSTEM paper.

Create ALL_IDB1 & ALL_IDB2 versions.

Describe alternatives you've considered
Other types of classifiers: Tensorflow/Theano etc

Additional context
NA

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.