Brain Tumor Segmentation and Localization using Deep Learning

We are proposing the Automatic method for the diagnose of brain tumors by MRI images.  Brain tumor segmentation is the process of separating the tumor from normal brain tissues; in clinical routine, it provides useful information for diagnosis and treatment planning. However, it is still a chal

Project Title

Brain Tumor Segmentation and Localization using Deep Learning

Project Area of Specialization

Artificial Intelligence

Project Summary

We are proposing the Automatic method for the diagnose of brain tumors by MRI images.  Brain tumor segmentation is the process of separating the tumor from normal brain tissues; in clinical routine, it provides useful information for diagnosis and treatment planning. However, it is still a challenging task due to the irregular form and confusing boundaries of tumors. Tumor cells thermally represent a heat source; their temperature is high compared to normal brain cells. Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time-consuming and subjective, this task is at the same time very challenging to solve for automatic segmentation methods. In this project, we present our efforts on developing a robust segmentation algorithm in the form of a convolutional neural network. Our network architecture was inspired by the popular U-Net and has been carefully modified to maximize brain tumor segmentation performance.

Project Objectives

Many of the brain tumor patients die because of the lake of information about the actual position of the tumor where it exists because the brain is a complex system it is still a challenging task to detect a tumor. due to the irregular form and confusing boundaries of tumors.

Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is difficult, time-consuming and subjective, this task is at the same time very challenging to solve for automatic segmentation methods.

 In this project, we present our efforts on developing a robust segmentation algorithm in the form of a convolutional neural network. Where through MRI images our system will automatically detect the tumor from irregular boundaries and structure of the brain.

Project Implementation Method

This project aims to provide the automatic segmentation method based on Convolutional Neural Networks (CNN) for precise quantitative measurements in the clinical practice.

1. Literature review of the existing similar projects
2. Analyze the work of the project
3. Collection of the required knowledge
4. Survey
5. MRI images collection
6. Environment setup
7. Training data-sets

Benefits of the Project

The brain tumor is the most unsafe disease over the past couple of decades. The number of individuals who dies because of brain tumors has been increased. Thus, physicians usually use rough measures for evaluation. The accurate segmentation of gliomas and its intra-tumoral structures is important not only for treatment planning but also for follow-up evaluations. However, manual segmentation is hard and time-consuming for these reasons, accurate semi-automatic or automatic methods are required.

This process is safe and fast, it provides the stats of the tumor region that help the doctor to locate the tumor and treatment.

Technical Details of Final Deliverable

Following tools and technologies are used to do our project.

• MRI images data-set
• Deep learning
• Convolutional Neural Networks 
• Keras
• simpleITK
• jupyter notebook
• Python 3.5 or above
• Tensorflow
• Unet
• Jetson Nano Developer Kit
• .Net Framework
• GPU 1050 Ti
• .Net MVC

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Medical

Other Industries

IT , Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

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