Raspbery Pi based embedded system for Brain Tumor Segmentation by using Deep learning

In this project, we present a handheld device to facilitate the medical specialist for automatic brain tumor detection from Magnetic resonance images (MRI) that based on Deep Neural Networks (DNNs). The proposed approach works on both low and high level/grade images of Brain. The reasons that motiva

Project Title

Raspbery Pi based embedded system for Brain Tumor Segmentation by using Deep learning

Project Area of Specialization

Artificial Intelligence

Project Summary

In this project, we present a handheld device to facilitate the medical specialist for automatic brain tumor detection from Magnetic resonance images (MRI) that based on Deep Neural Networks (DNNs). The proposed approach works on both low and high level/grade images of Brain. The reasons that motivate us is the outstanding performance of medical technology is grooming vastly in this field. The machine learning solution are very outstanding and their performance provide the results that are very close to the expert opinions

Project Objectives

• Embedding an artificial intelligence-based solution in a computer based handheld device for brain tumor segmentation and classification using Deep Neural, to support our medical industry.
• By providing medical staff a handheld device that are going to ease the way of treatment and learning about brain tumors and infections very easily.
• Local hospital use this device easily  that may help in learning and brain tumor diagnosis becomes easy without experts.

Project Implementation Method

• Gathered and download dataset of brain MRI  from a brats challenge (2015)
• Train a model using Convolutional Neural Network (CNN) based network to classify and predict different segments of brain MRI
• Deploy trained network on Raspberry Pie

Benefits of the Project

• Proposed method for brain tumor classification and segmentation for disease screening in order to overcome the burden on specialist and early diagnosis of serious problems before it will affect the activities of brain.
• Efficient way of detecting and classifying brain tumor.
• Manageable and Convenient tool for medical staff.

Technical Details of Final Deliverable

The technical details of this project comprise on the following two requirements that are given below.

Software Requirements:

• Python
• Anaconda

Hardware Requirements:

• Raspberry Pie
• Touch Screen LED
• Heat sink fan kit
• Rx 2080 GPU for Deep learning model training

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Medical

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People, Quality Education, Industry, Innovation and Infrastructure, Life on Land

Required Resources

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