BCS

Cancer is a complicated disease caused primarily by genetic unpredictability and growth of multiple molecular alternations. Skin cell grows in a normal way in all humans, but their abnormal growth cause cancer. Among numerous kinds of malignancy. Skin cancers are the most common type of tumors in hu

Project Title

BCS

Project Area of Specialization

Artificial Intelligence

Project Summary

Cancer is a complicated disease caused primarily by genetic unpredictability and growth of multiple molecular alternations. Skin cell grows in a normal way in all humans, but their abnormal growth cause cancer. Among numerous kinds of malignancy. Skin cancers are the most common type of tumors in humans. Current diagnostic and prognostic classifcations do not reflect the entire medical heterogeneity of tumors and are inadequate to make prediction for a successful treatment. It is now quite evident that early finding and treatment of skin cancer can increase the survival rate patients. Although the significant research effort has gone into developing computerized algorithms to segment dermoscopic image properly, still some substantial limitations exists in each effort. To attain an effective way to identify skin cancer at an early stage without performing any unnecessary skin biopsies, digital images of skin lesions are investigated using multiclass classification. In this project, we proposed an intelligent system to detect and classify skin cancer by using state of the art image processing techniques. Textural and color features are extracted from skin lesion to detect and classify cancer.

Project Objectives

Our goal is to develop well organized automatic skin cancer classification system which has accuracy, low complexity  and performance because there is necessity to reduce the number of false detections. Such a system will automate the analysis and help physicians to do fewer tasks and achieve reliable results. The potential advantages of such studies are significant. We also intending to accomplish following sub-objectives: 
• Use in Real time applications.  •  Fast Computational time.  •  Less prone to human error.    •  Robust and flexible to large data amount.  •  Compare Accuracy Results with other techniques. •  Cost effective. 
 

Project Implementation Method

In this project we used machine learning techniques and artificial intelligence. Data is gathered from patients of Skin cancer, the images are collected and formed a huge dataset. This dataset is given as input to system.First of all pre-processing occurs which means your data should be clean. All the images are resized and all images having extension .jpg. Whole dataset is split into two parts. And the end result is generated. 

Benefits of the Project

•Automatic skin cancer classification system will have accuracy, low complexity  and performance because there is necessity to reduce the number of false detections.

•System will automate the analysis and help physicians to do fewer tasks and achieve reliable results.

Technical Details of Final Deliverable

Technical details include understanding basics of neural networks,their implementation in python, understanding working of libraries Keras,tensorflow,openCv. Understanding Deep Learning techniques and Convolutional Neural Networks etc.

Final Deliverable of the Project

Software System

Core Industry

Medical

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

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