PINK CODE

To try the demo, check google colab notebook.

Your Project Members

• Alejandro Miron
• Carla Cardenas
• Luis Carlos Ramirez
• Jesus Pio
• Juan de la Cruz
• Vianey Avila

What is the name of your project?

• Pink Code

What does this project do?

• The project consists in coding a convolutional neural network(CNN) written in python that reads a dataset of mammography scans from breast cancer patients. Then the CNN, after being trained, is able to quickly tell what density of masses you have and even tell if the type of breast cancer is benign or Malignant.
  As of right now, the accuracy of the CNN is approaching to 93%.

Who did you design this project for?

• By using this program as a guide, general medical practitioners and radiologally technicians will have a special tool to help with faster and easier detection of cancerous tumors in uncertain cases, and especially speed up the process of a valid assessment of the tumor with an oncologist, this tool is not intended to be used by the general public, but only as a guide.

What was your inspiration for this project?

• We are trying to reduce the time it takes for a person with an uncertain case to be diagnosed with a malignant tumor and start their treatment, since this is a very lengthy process in the third world public health system.

What challenges did you run into?

• At first, we could not manage to run the program with so much data, but once amazon gave us access to their servers we managed to run our program achieving a certainty of 93% and if we make our data set bigger, this certainty will be higher.

What accomplishments are you most proud of?

• We managed to get an approx 93% accurate neural network capable of classifying a mammography scan as benign or malignant.

What did your team learn?

• We mainly learned how to get along with a team we are not familiar with in aspects as organization and compromise.