Applying Computer Vision for Red Blood Cell Classification to Diagnose Sickle Cell Disease

Local Chapter Benin Chapter

Coordinated byBenin ,

Status: Completed

Project Duration: 01 Mar 2023 - 30 Apr 2023

Open Source resources available from this project

Project background.

Sickle Cell Disease (SCD) is a genetic disease that affects red blood cells. red blood cells are the transporters of oxygen across the organism. In normal conditions they have a spheric shape, in the case of SCD, those cells have the form of sickles.
More than 66% of 120 million people affected by SCD worldwide live in Africa. Every day, a thousand children are born with this disease, making it the most common genetic disease in the Region.

The problem.

Access to some specific medical diagnoses is challenging for developing countries’ populations. In particular, for rural people, sickle cell anemia or even sickle cell traits are not diagnosed in time because of the remoteness of appropriate medical centers and laboratories and the cost of electrophoresis tests

Project goals.

- Collate and label blood cell dataset for sickle cells anemia; - Build and train a model to detect sickled cells in blood cell images

Project plan.

  • Week 1

    data collection

  • Week 2

    Data exploration, analysis and cleaning

  • Week 3

    Model design and training

  • Week 4

    – Model training and validation

  • Week 5

    Project report

Learning outcomes.

Machine learning, deep neural network, computer vision

Share project on: