Detection of melanoma cancer through image processing

Detection of skin cancer in the earlier stage is very critical. Nowadays, skin cancer is seen as one of the most hazardous form of cancers found in humans. The most common types of skin cancers are Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC) and Melanoma. Among these melanoma is the de

Project Title

Detection of melanoma cancer through image processing

Project Area of Specialization

Artificial Intelligence

Project Summary

Detection of skin cancer in the earlier stage is very critical. Nowadays, skin cancer is seen as one of the most hazardous form of cancers found in humans. The most common types of skin cancers are Basal Cell Carcinoma (BCC), Squamous Cell Carcinoma (SCC) and Melanoma. Among these melanoma is the deadliest type of skin cancer. The detection of Melanoma cancer in early stage can be helpful to cure it. Melanoma is a particularly deadly form of skin cancer and although it accounts for only 4% of all skin cancers it is responsible for 75% of all skin cancer deaths. If melanoma is diagnosed and treated in its early stages, it can be cured but if the diagnosis becomes late, melanoma can grow deeper into the skin and spread to other parts of the body. Its spread in other parts beyond the skin can be hazardous as it is difficult to treat. The presence of Melanocytes in any body part causes the Melanoma .Intensive Exposure of skin to ultraviolet radiation is the main cause of the melanoma. Computer vision plays an important role in medical image diagnosis and this has been proved by many existing systems. A mobile base skin image diagnosis system has a significant potential for screening and prognosis. It is utmost important in countries where unaided visual diagnosis system is the practice and where there is insufficient number of dermatologists. This thesis presents an android mobile application for the detection of melanoma skin cancer using image processing.

Project Objectives

Our main objective is to develop an Android application that helps physicians as a decision support for melanoma management procedures. Along with, we also want to ensure the maximum efficiency and accuracy in the result which we obtain from this application.

Project Implementation Method

The input for the system is the image of the skin lesion which is suspected to be a melanoma lesion. This image is then pre-processed to enhance the image quality. The automatic thresholding process and edge detection is used for image segmentation. The segmented image is given to the feature extraction block which consists of lesion region analysis for its geometrical features and ABCD features. The geometrical features are proposed since they are the most prominent features of the skin cancer lesion. The extracted feature are further given to the feature classification stage which classifies the skin lesion as cancerous or normal by comparing its feature parameters with the predefined thresholds. 

Benefits of the Project

This poject helps in early detection of melanoma cancer.

Technical Details of Final Deliverable

Firstly we used Complex neural network (CNN) algorthm for the training of our data set.After training algorithm we use tensorflow for the development of android application that help in the detection of melanoma cancer.

Final Deliverable of the Project

Software System

Type of Industry

IT , Medical

Technologies

Artificial Intelligence(AI), NeuroTech

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

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