Stree - A Breast Cancer Diagnostic Platform

Our One-Stop Breast Cancer Solution for your Protection.

Comment

Inspiration

An initiative to raise awareness about breast cancer among women eases and advances the process of diagnosis of breast cancer by the doctors. Giving doctors a supporting pair of eyes and patients a complete vision with a prompt application that makes lives safer and reduces medical errors. This drew us the inspiration for Stree! Breast cancer is the most common invasive cancer in women and the second leading cause of cancer death in women after lung cancer. Understanding it's risk and effect on women life, we aim to provide a platform for you and your doctors to understand the condition of your breasts

What it does

We primarily provide the tool of Breast Cancer Analyser, that accepts Histopathological Image of the breasts along with the prediction type to give the results. There are also guidelines on the importance of Breast Exam and how it can be performed. We are also working towards the feature to connect with the doctor over a video conference, for the patient to connect with the doctor and understand the patient and diagnosis better. We also connect the patient and doctors with dedicated dashboards, while keeping track of their diagnosis i.e. storing and giving prescriptions, lab reports etc on our platform, such that important information cannot be missed out. It will be highly beneficial to this crucial assistance. The features we have are:

Responsive UI for Accessibility, Breast Cancer Detection tool: Detects 2 types of cancers using 2 AI Models, Dedicated Dashboard for Patient and Doctor, Booking Lab/Appointment, Video Conferencing and Previous Prescription & Medical History

How we built it

First, we created a website with HTML/CSS/Bootstrap. Then connected it with server-side using PHP and MySQL for the database. For the cancer detection analysis, we used Python - Sklearn, Keras, Tensorflow etc. for the ML Model(s) and Django REST Framework (for Model Endpoints). Later for the working, we connected the code to Microsoft Azure Machine Learning Studio for the ML Model(s) and run the project in Xampp.

Challenges we ran into

Most web browsers don't support the tiff image format, which is contained in the dataset. While preprocessing the same for our web application we converted the images to .png format such that the model is trained with data i.e. similar to the expected input. Because Tensorflowjs is a new technology, web apps built using it may not work in some browsers. The user will see a message saying the "Ai is loading..." but that message will never go away because the app is actually frozen. It's better to advise users to use the latest version of Chrome. The web app for this project uses the Javascript language for the most part. We also used Javascript to feed the images to the model. The challenge is that Javascript is very fast whereas the model isn't fast enough to keep up. This difference in speed can lead to incorrect predictions. We used async/await to fix this.

Accomplishments that we're proud of

Learning and implementing the Django REST framework in the project with 91% accuracy. Also, completing the prototype and complete website before the deadline.

What we learned

Implementing REST framework and Sklearn, Keras, Tensorflow etc. for the ML model(s) in Python. Got to know many interesting things that we might use in updating our project later.

What's next for Stree - A Breast Cancer Diagnostic Platform

  1. Addition of chatbox for communication.
  2. To draw a 100% accuracy in the functioning of Stree.

Built With

Share this project:

Updates