Brain Tumor Detector part 1
Introduction
Brain tumor. What a scary cancer that exists worldwide and anyone might have or might not have chace to have brain tumor. There are many types of brain tumor found so far and medical professional is combating these caners.
According to the source. Brain tumors account for 85% to 90% of all primary central nervous system (CNS) tumors. Worldwide, an estimated 308,102 people were diagnosed with a primary brain or spinal cord tumor in 2020
Imaging that a machine is devepled to scan patients’ brain and then detect whether a patient have chance of brain tumor or not. This can be a tool as assistant for medical professional.
Problem
Brain tumor appear with different size, type and location. In early stage brain tumor is small and tiny to human eyes and it require medical professional to have enough experience to analyse MRI image for a patient.
Human eyes often neglect detail of information on object visually. This problem present a risk for a patient when medical professional analysing MRI image. Moreover it could lead to undesired fatal result eventually.
Goal
To solve this problem I can train a deep learning model that learn a ton of MRI image samples and then to predict whether a patient have a chance of having brain tumor or not. In addition the model provide information about the type of brain tumor.
The main feature of the model is to provide a chance in percentage for a patient who might have brain tumor. Another feature is to detect which type of brain tumor Meningioma, Glioma and Pituitary.
Dataset
The dataset that will be used to train the deep learning model is from Kaggle.
This dataset contains 7023 images of human brain MRI images which are classified into 4 classes: glioma, meningioma, no tumor and pituitary.
Next
The dataset need to be preprocessed before it can be used to training a model.
