Skip to content

Applying deep neural networks for skin cancer detection

Notifications You must be signed in to change notification settings

dreanyarko/skin_cancer_project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Skin Cancer Classification Using Deep Neural Networks

Overview

In my quest to find a problem to solve in my closing year at college, I chanced upon an online write up by a reputable newspaper which stated that there were only about 25 certified dermatologists in Ghana as at 2017, which was to serve a population of about 25 million at the time. Really!! I very much intrigued by this news. I imagined how the nation would cope if there was an outbreak of a skin disease, coupled with the lack of medical equipment. As a result I teamed up with a colleague of tackle the problem.

The goal of the project was to apply artificial intelligence and computer vision using deep learning techniques to aid physicians detect the deadliest type of skin cancer, melanoma, very early. We developed a deep learning model to accurately classify skin lesions as either benign or malignant using Transfer Learning.

Results - Have a Sneak Peak

Training and validation statistics


Deployed via Streamlit

Technologies Used

  • Python
  • TensorFlow
  • Pandas
  • Matplotlib
  • OpenCV
  • Streamlit

Collaborator

My deepest gratitude goes to Cherif for this great collaboration.

About

Applying deep neural networks for skin cancer detection

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published