AI Skin Diagnosis

This is an archive site. Current senoir design projects are at https://projects.eng.uci.edu.

Submitted by zhixiuk on Thu, 10/05/2017 - 22:49

Topic:

Idea source:

Team Name: AI Skin Diagnosis

Team Members:

Haixiang Yan, Zhixiu Kang, Ziyuan Cui, Wenrui Lin

Team Mentor: Professor Xiaohui Xie

 

Description:

The project is to design an app to diagnose skin condition with deep learning.

Goal Statement:

Our application will diagnosis the disease by the using convolutional neural network trained by thousands of cases which has proved to be more accurate than human diagnosis.

Introduction: 

Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories.

Approach:

•WeChat Mini App

•Convolutional Neural Network

•Real Data

Schedule:

•10.1-11.20 App design

•11.21-11.30 Main function Implementation

•12.1-12.15 App testing

•Winter Quarter： Algorithm Improvement

Progress & Current Status:

We have finished the design of app.