Brain Cancer Classification Model

Presenter: Baluge Akiza Innocent, SCES

Abstract

Early cancer diagnosis focuses on detecting symptomatic patients as early as possible so they have the best chance for successful treatment. According to the World Health Organization, early diagnosis improves cancer outcomes by providing care at the earliest possible stage and is therefore a significant public health strategy in all settings.

Using image processing and deep learning, early diagnosis has been made easy. As the diagnosis deals with human lives, there is a need to have a high accuracy rate in the tests. The existing computer vision-based and deep learning solutions for diagnosis are limited to classifying cells as tumorous or not, and the tumor as malign or benign.

Building a deep learning model that, in addition to classifying cells as tumorous or not, detects the location of the tumor in the cells at an early stage, will be used in different medical diagnosis applications and can contribute to generating accurate and faster results and accordingly, the patients can be treated.