Skin Cancer Predictor Using Python And Deep Learning

In this project, we will a make a deep learning model that is train on HAM10000 dataset and it is deploy on a web-based application to provide interface to the humans.  HAM10000 dataset consists of different type of skin cancer images.  This model will be used for early detection o

Project Title

Skin Cancer Predictor Using Python And Deep Learning

Project Area of Specialization

Artificial Intelligence

Project Summary

In this project, we will a make a deep learning model that is train on HAM10000 dataset and it is deploy on a web-based application to provide interface to the humans. 
HAM10000 dataset consists of different type of skin cancer images. 
This model will be used for early detection of the type of skin cancer by taking image as an input from the user (i.e: doctor) of the infected area of skin; it will process that image and predict the kind of cancer, skin is at risk of developing
 

Project Objectives

To design a skin cancer prediction model using python and convolutional neural network to predict the type of skin and deploy it on a 
Web-application so that human can easily interact with it.
 

Project Implementation Method

As we know that for training, a machine learning or deep learning model a good data set plays a vital role. We have a skin disease images sample dataset named as “HAM10000”. We got this dataset from Kaggle.com. 
First we will perform cleaning of this dataset and organize the data present in the dataset using Pandas and Numpy. 
We will visualize our data set using Matplotlib and Seaborn. In order to find the best features for prediction purpose.
After visualizing and cleaning the data, we will divide our data into the train set and test set. After that we will train our model with training dataset using Scikit-learn and Tensor flow. Then we will test our model and check the model accuracy. If the accuracy is low, we will perform further cleaning in our dataset. Once the model is build and we are satisfied with the accuracy result. We will deploy our prediction model on a web-based application using Flask, HTML & style it using CSS or Bootstraps.
 

Benefits of the Project

This model application can used for early prediction of skin cancer. It will predict if a person is at risk of developing some Life-Threatening skin cancer. This application can be helpful for doctor in examining the skin and predicting the early symptoms of disease like cancer. With the help of this model, we can identify the type of cancer in the initial stages and cure it early.

Technical Details of Final Deliverable

We will accomplish these tasks in order to complete our project:

i.    In first phase, we will clean and organize our data.
ii.    In the second phase, we will train and test our model.
iii.    In third phase, we will deploy our model and apply styling.

After the completion of these three phases we can easily predict the type of skin cancer by simply giving picture of the skin as input.
 

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

Education , Medical , Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Internet of Things (IoT)

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com