You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Our entry for the Microsoft Hackathon Fabric AI, DermaBot, is a pioneering application designed to transform dermatological care. It features a dual-image classification approach utilizing both YOLO and GPT-4 Vision technologies, specifically tailored for the detection of various skin conditions. Complementing this, our system includes a Retrieval-Augmented Generation (RAG) component, trained on a collection of dermatology documents. This combination enables DermaBot to not only identify skin conditions with high precision but also to provide relevant, evidence-based medical information and treatment recommendations. Our solution aims to assist healthcare professionals and patients by offering a comprehensive tool for faster, more accurate diagnoses and personalized patient care.
Project name
DermaBot
Description
Our entry for the Microsoft Hackathon Fabric AI, DermaBot, is a pioneering application designed to transform dermatological care. It features a dual-image classification approach utilizing both YOLO and GPT-4 Vision technologies, specifically tailored for the detection of various skin conditions. Complementing this, our system includes a Retrieval-Augmented Generation (RAG) component, trained on a collection of dermatology documents. This combination enables DermaBot to not only identify skin conditions with high precision but also to provide relevant, evidence-based medical information and treatment recommendations. Our solution aims to assist healthcare professionals and patients by offering a comprehensive tool for faster, more accurate diagnoses and personalized patient care.
Project Repository URL
https://github.com/AlexAlex777/ms_hack_fabric_ai
Project video
https://youtu.be/IZkvaWa1tYI
Team members
alexbailaww, danielsusanu7, AlexAlex777
The text was updated successfully, but these errors were encountered: