What it does

DetAll is a group of medical tools based on the web which allow doctors to perform various types of analysis only through an image.

It consists of three main sections as of now: Eyes, COVID and Skin.

  1. Eyes - performs functions around the eye like cataract detection, diabetic retinopathy detection and redness levels (uveitis) detection
  2. COVID - analyses CT scans of lungs for detection of COVID-19
  3. Skin - detects malignant and benign type of skin cancer

How I built it

  • Trained Models on Google Teachable Machine

  • Then loaded that models and used streamlit to run it on localhost. (You can also run it on Colab Notebook Directly ,Link is provided below and in github)

  • Used Datasets from :

  1. Eyes: https://github.com/javathunderman/retinopathy-dataset https://github.com/yiweichen04/retina_dataset

  2. Skin: https://www.kaggle.com/fanconic/skin-cancer-malignant-vs-benign

  3. COVID: https://github.com/UCSD-AI4H/COVID-CT

Challenges I ran into

Training Models using Teachable Machine

Accomplishments that I'm proud of

Used Streamlit to build Frontend for first time

What I learned

Building UI using Streamlit Using multiple Machine Learning Models for single project

What's next for DetAll

  1. For future use-cases, direct integration with medical hardware and devices is possible which allows better quality computer vision analysis and faster results.
  2. Adding more features to Model like detecting type of Disease
  3. Creating Mobile App using Tflite (currently we have web app)

Built With

Share this project:

Updates