Search In this Thesis
   Search In this Thesis  
العنوان
Diagnosis of Skin Cancer Using Machine Learning Techniques/
المؤلف
Arasi, Munya Abdulmajid.
هيئة الاعداد
باحث / Munya Abdulmajid Arasi
مشرف / Abdel-Badeeh M. Salem
مشرف / El-Sayed M. El- Horbaty
مشرف / El-Sayed A. El-Dahshan
تاريخ النشر
2018.
عدد الصفحات
230 p. :
اللغة
الإنجليزية
الدرجة
الدكتوراه
التخصص
Computer Science Applications
تاريخ الإجازة
1/1/2018
مكان الإجازة
جامعة عين شمس - كلية الحاسبات والمعلومات - علوم الحاسب الالي
الفهرس
Only 14 pages are availabe for public view

from 230

from 230

Abstract

Dermatology is a medical science which deals with diagnosis of skin problems, hair and nails. Skin is one of the most important parts of the human body which protects the internal parts from the outside world. Therefore, it is necessary to protect the skin from the disease. Many factors such as microbes, different drugs, and exposure to ultraviolet (UV) radiation in sunlight may cause problems to the skin. Despite the ease with which symptoms of dermatology problems can be detected, diagnosed and treated, yet many people remain unaware of this fact [1].
Cancer is a malignant cell which becomes the fastest growing and deadly, generally clinical and data driven statistical research has become a common complement of cancer research. Predicting and diagnosis of a disease is one of the most interesting of researchers where to develop machine learning applications. The medical research groups use the computers with automated tools, and medical data for that purpose [2].
The intersection between science, computer science and health care are produces medical informatics. It means the devices and methods required to improve the acquisition, retrieval use of information, and storage in biomedicine and health. The various tools like computers, formal medical terminologies and information, and clinical guidelines are included by health informatics [3].
Standards, tools, and approaches grow rapidly in biomedical informatics for supporting the cancer clinical data. Individual observations are represented and collected those observations into summaries over the period of cancer care. Deep phenotype is generated by these models that acutely needed to support the development of systems for individual cancer patients [4]; this process remains almost entirely manual in cancer research.The treatment combinations can be found by implementing and using the computerized of the automated information from a Cancer Registry. Therefore, the outcome of cancer patients is improved for years to come [5].