Skip to content

Discover DermaScan: A full-stack web app with MobileNetV2-based skin lesion classifier using Harvard's Ham10000 Dataset for precise dermatological diagnosis.

Notifications You must be signed in to change notification settings

ADITYAVOFFICIAL/Skin-Disease-Classifier

Repository files navigation

DermaScan: Advanced Skin Lesion Classifier with Dermatology Chatbot

License: MIT Status Forks Issues PR Maintenance Views

  • Welcome to the DermaScan web app GitHub repository, your gateway to a cutting-edge skin lesion and disease classifier.
  • Leveraging Harvard's Ham10000 dataset and the robust MobileNet V2 model, this system boasts an impressive accuracy rate of 89%.
  • But that's not all – we've integrated "Derma" a dermatology chatbot powered by GPT-3.5 Turbo with internet access, to provide insightful information and guidance.
  • Moreover, our app also connects you with the nearest doctors through an intuitive API, and offers suggestions for relevant medical articles. Explore the future of dermatological diagnostics and treatment right here!

Important

These results are for informational purposes only; consult a healthcare professional for accurate medical advice.

Build Status

Netlify Status

Preview

Web_app
Web_app

Web_app

Web_app

Current Tech Stack 🔻


Python Flask Jupyter Html CSS JS Bootstrap TensorFlow Scikit Pandas Keras OpenCV NumPy JQuery Netlify

Developers of this repository 🔻

ΛDIƬYΛ VΣЯMΛ

Aditya Verma

Installation

Before running the Jupyter Notebook for the model, make sure to install the dependencies listed in the 'requirements.txt' file.

pip install -r requirements.txt

Running website on Local Host

flowchart LR
A(Round)
A[Clone Repo] --> B(Round)
C(Round)
B[Open Folder] --> C[Open index.html]
Loading

Current Contributors 🔻