The problem Stree - A Breast Cancer Diagnostic Platform solves

Stree is an initiative to raise awareness about breast cancer among women, eases and advances the process of diagnosis of breast cancer by the doctors. It gives doctors a supporting pair of eyes, and patients a complete vision with a prompt application that makes lives safer and reduces medical errors. This is HackDivas' Official submission for Hack Nagpur 2020 Hackathon.

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 affect to a women's life, we aim to provide a platfrom for you and your doctors to understand the condition of your breasts. 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
• Previous Prescription & Medical History

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 bulit 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.