Latin America is facing a great challenge due to current situation with COVID-19. At our country, for instance, hospitals are slowly running out of beds, people is getting infected at an increasing rate and governmental politics have shown this matter is not easily solvable. That's why we are trying to contribute by setting the first steps on a model that can help medical staff to diagnose COVID, as it can be confused with other diseases as pneumonia.

What it does

The project itself its divided into two parts, the Jupyter notebook worked in google collaborate contains both algorithms. The first tries to show as an example (not worrying about accuracy) how the system works and the other is a full-builded model that's able of predict and classify images (slower and much more computationally demanding). It can classify a torax plate and tell whether it is an example of a covid, bacterial pneumonia, viral pneumonia or a "not classified" plate.

How We built it

We used several libraries in the process. The first algorithm consists on taking the input (an image), transforming it into an array (1xn) and then working with such information in a logistic classifier using turicreate. It was used in a interface we designed using tkinter that allows user to import images and see the result after being processed by this algorithm. The reason why we didn't use the CNN in the graphical interface was due to its high computational cost, but we still worked in it using google collaborate and hope somecan can implement it ensuring a tremendously accurate result (over 92%).

Challenges we ran into

First of all to import the data. It was challenging to import thousands of images into arrays so that they can be analysed. We tried to use an algorithm that could set deep features but, as this wasn't possible, we implemented the CNN. We thought the challenge was coding the machine learning algorithm but in the end that wasn't a problem. Also RAM was hard to control.

Accomplishments that I'm proud of

The CNN model works nicely, even if due to RAM its hard to use it in our computers. We think it can help other projects on their development

What We learned

In this project we learned to develop and strengthen our programming skills. In addition to that, we managed to carry out a project that solves a problem that has a great incidence in Colombia. On the other hand, the knowledge obtained with the construction of various prediction models, such as neural networks.

What's next for Maching Anding

The idea would be to implement the same algorithm with more data so that it classifies more illness and more type of medical images. It depends on whether we find datasets or people with willing to cooperate with this project.

Built With

Share this project: